SlideShare uma empresa Scribd logo
1 de 45
Baixar para ler offline
NLU / Intent Detection
Benchmark
by Intento
August 2017
About
• At Intento, we want to make Machine Intelligence
services easy to discover, choose and use.
• So far, the evaluation is the most problematic part: to
compare providers, one need to sign a lot of contracts
and integrate a lot of APIs.
• We deliver that for FREE on public datasets. To
evaluate on you own dataset, contact our sales.
• Also, check out our Machine Translation Benchmark.
Machine Translation is an easy way to build a multi-
lingual bot.
Overview
• Natural Language Understanding Services with Public
APIs*
• IBM Watson Conversation
• API.ai API
• Microsoft LUIS
• Amazon Lex
• Recast.ai API
• wit.ai API
• SNIPS API
• Benchmark Dimensions
• Intent Prediction Performance
• False Positives
• Learning Speed (performance on small datasets)
• Language Coverage, Price, Response time
August 2017© Intento, Inc.
* as of today, some of them don’t have a Public API and we’ve got an access for the purpose of this benchmark
NLU Engines Compared
August 2017© Intento, Inc.
API.ai / Google
• Website: https://api.ai
• Launched: 2010 (acquired by Google in 2016)
• Pricing model: FREE
• Interface: HTTP REST API
“Build delightful and natural
conversational experiences”
August 2017© Intento, Inc.
wit.ai / Facebook
• Website: https://wit.ai
• Launched: 2013 (acquired by Facebook in 2015)
• Pricing model: FREE
• Interface: HTTP REST API
“Natural Language for Developers”
August 2017© Intento, Inc.
IBM Watson Conversation
• Website: https://www.ibm.com/watson/services/
conversation/
• Launched: 2016
• Pricing model: Pay As You Go
• Interface: HTTP REST API
“Quickly build and deploy chatbots and
virtual agents across a variety of
channels, including mobile devices,
messaging platforms, and even robots.”
August 2017© Intento, Inc.
Microsoft LUIS
• Website: https://www.luis.ai/
• Launched: 2015
• Pricing model: Pay As You Go
• Interface: HTTP REST API
“Language Understanding
Intelligent Service. Add
conversational intelligence to your
apps.”
August 2017© Intento, Inc.
Amazon Lex
• Website: https://aws.amazon.com/lex/
• Launched: 2016
• Pricing model: Pay As You Go
• Interface: HTTP REST API
• Important Restrictions apply (see Dataset slide)
“Conversational interfaces for your
applications. Powered by the same deep
learning technologies as Alexa”
August 2017© Intento, Inc.
Recast.ai
• Website: https://recast.ai
• Launched: 2016
• Pricing mode: Free tier + Contact sales
• Interface: HTTP REST API
“The collaborative platform to
build, train, deploy and monitor
intelligent bots for developers”
August 2017© Intento, Inc.
SNIPS
• Website: https://snips.ai
• Launched: 2017
• Pricing model: Free to test + Pay per Device
• Interface: On Device*
“Snips is an AI-powered voice
assistant you can add to your
products. It runs on-device and is
Private by Design”
* we’ve tested a hosted version with a private API provided by SNIPS
August 2017© Intento, Inc.
Historical
timeline
2011 2015 20162012 2013 2014 20172010
Conversation
Facebook
Google
LUIS
August 2017© Intento, Inc.
The Approach
August 2017© Intento, Inc.
Dataset
• The original dataset is the SNIPS.ai 2017 NLU Benchmark
• English language only
• We have removed duplicates that differ by number of
whitespaces, quotes, lettercase etc
• Resulting dataset parameters*: 7 intents (next slide),
15.6K samples (~2K per intent), 340K symbols
• We also used ~450 samples from SNIPS.ai 2016 NLU
Benchmark to test for False Positives
* For Amazon Lex, the training set is capped by 200K symbols per API limitation; also symbol limitations
apply, resulting in 4500 utterances (~640 per intent).
August 2017© Intento, Inc.
Intents [*]
• SearchCreativeWork (e.g. Find me the I, Robot television show)
• GetWeather (e.g. Is it windy in Boston, MA right now?)
• BookRestaurant (e.g. I want to book a highly rated restaurant for
me and my boyfriend tomorrow night)
• PlayMusic (e.g. Play the last track from Beyoncé off Spotify)
• AddToPlaylist (e.g. Add Diamonds to my roadtrip playlist)
• RateBook (e.g. Give 6 stars to Of Mice and Men)
• SearchScreeningEvent (e.g. Check the showtimes for Wonder
Woman in Paris)
[*] quoted from https://github.com/snipsco/nlu-benchmark/tree/master/2017-06-custom-intent-engines
August 2017© Intento, Inc.
I. Prediction Performance
August 2017© Intento, Inc.
Experimental setting
• Inspired by the SNIPS Benchmarks (2016, 2017)
• We benchmark intent detection only, no parameter
extraction yet
• For each provider, one model is trained to detect all
intents
• We run all models with the default confidence score
thresholds.
• 3-fold 80/20* Stratified Monte Carlo cross-validation
* 47/20 for Amazon Lex
August 2017© Intento, Inc.
Scores Normalization (I)
Intents: the good, the bad and the ugly
(to compare providers we need to remove intent-related bias)
F1 Scores* Confusion matrix
* F1 Score is a weighted average of the precision and recall; reaches its best value at 1 and worst score at 0.
August 2017© Intento, Inc.
Scores Normalization (II)
• Standardizing F1,
P and R scores
for each intent
(SD-
normalization)
• Then adjusting
scales by
multiplying on the
global std and
adding the global
mean (next slide)
August 2017© Intento, Inc.
Detection Performance*
• Black bars
indicate
confidence
intervals
• Amazon Lex
is trained on a
smaller
dataset due
to its API
limits
* Mean standardized F1 scores, adjusted to the initial scale using global mean and std
August 2017© Intento, Inc.
Average Precision*
• Black bars
indicate
confidence
intervals
• Amazon Lex
is trained on a
smaller
dataset due
to its API
limits
August 2017© Intento, Inc.
* Mean standardized Precision, adjusted to the initial scale using global mean and std
Average Recall*
* Mean standardized Recall, adjusted to the initial scale using global mean and std
• Black bars
indicate
confidence
intervals
• is Amazon Lex
trained on a
smaller dataset
due to its API
limits
August 2017© Intento, Inc.
Precision vs. Recall
August 2017© Intento, Inc.
Discussion
• Training models is cumbersome for most of the services:
• manual work (adding models in the web interface) and
• solving issues with the tech support.
• Based on the confidence intervals, all providers fall into several
groups:
• Top-runners: IBM Watson, API.ai, Microsoft LUIS
• Amazon Lex: API limits don’t allow for training multi-intent
model on enough samples
• Choosing the provider:
• For “good” intents (like GetWeather), all providers are good
enough. For “bad” intents, having a “good” providers is crucial
• Within each tier, the leader depends on the intent data
August 2017© Intento, Inc.
II. False Positives
August 2017© Intento, Inc.
Approach
• How does NLU behaves when a user express an
intent it wasn’t trained for?
• Expected behavior: produce the Fallback Intent
(no trained intents pass the detection threshold)
• 1411 utterances from the domains other than
Music, Movie, Weather, RestaurantReservation,
Entertainment and TV.
• Compare % of (false) positive detections for each
NLU provider
August 2017© Intento, Inc.
Out-of-the-Domain Samples
August 2017© Intento, Inc.
Discussion
• Only Snips.ai and API.ai are somewhat good at
detecting that users asks for something the agent
is not trained for
• IBM Watson and Microsoft LUIS are trying to map
any user request to one of the intents from the
training set
Perhaps the Fallback intent should be manually
added and trained on junk utterances?
August 2017© Intento, Inc.
III. Learning Curve
August 2017© Intento, Inc.
Experimental Setting
• Similar to the Prediction Performance (slide 18)
• 20% of the dataset reserved for testing (stratified)
• From the remaining 80%, for intent we’ve randomly
built a set of training sets of the following cardinality:
10, 25, 50, 100, 200, 500, 1000*
• No cross-validation
• Analyzed F1 Scores, normalised as described on
slides 19-20.
* for Amazon Lex, 10, 25, 50, 100, 200
August 2017© Intento, Inc.
Leaning curve by provider
Vertical bars
denote
confidence
intervals
August 2017© Intento, Inc.
Discussion
• On <100 samples IBM Watson is superior*. API.ai
catches up at >100 samples.
• Detecting the user’s intent is crucial for the
subsequent slot extraction and response generation.
• The learning curve is quite steep, good performance
requires hundreds of utterances to train on.
• Most of the pre-built intents (Microsoft LUIS, API.ai,
etc) are built on 10-50 utterances.
* SNIPS advertises a special enterprise feature to generate additional samples for smaller datasets, but it is not
available by default
August 2017© Intento, Inc.
IV. Language coverage
August 2017© Intento, Inc.
Supported languages
• Merged all
dialects (e.g. en-
uk and en-us).
• Note we’ve tested
the performance
only for English
August 2017© Intento, Inc.
Language popularity
Numberofsupportingproviders
0
2
4
5
7
English
Korean
German
Spanish
French
Italian
Portuguese
Japanese
Chinese
Dutch
Arabic
Russian
Norwegian,
Polish, Hindi,
Finnish, Danish,
Czech, Swedish,
Catalan,
Ukranian +29
August 2017© Intento, Inc.
Discussion
Potentially, Machine Translation may be used to
increase the language coverage and/or performance:
• either by translating both the training and testing
utterances to English
• or by translating only testing utterances and
using the English training model
That’s something to check
in future benchmarks
August 2017© Intento, Inc.
V. Other observations
August 2017© Intento, Inc.
Average response time
*
* Snips assumes on-device deployment, we put here a response time for a hosted test bench August 2017© Intento, Inc.
Price per 1K requests*
* prediction requests; SNIPS has per device pricing and is not shown on this chart
CONTACTSALES
Free Free
August 2017© Intento, Inc.
Conclusions
August 2017© Intento, Inc.
Performance (F1) vs. Price*
Performance
Affordability = 1/Price
wit.ai
amazon.lex
microsoft.luis
ibm.watson api.ai
* Recast and SNIPS are not shown as they don't provide a public pricing
FREE
August 2017© Intento, Inc.
Performance (F1) vs. Latency*
Performance
Speed = 1/Latency
snips
recast
wit.ai
amazon.lex
microsoft.luis
ibm.watson api.ai
* Snips assumes on-device deployment, we put here a response time for a hosted test bench August 2017© Intento, Inc.
Conclusions
1. API.ai, Microsoft LUIS and IBM Watson have overall
best intent detection performance, speed and language
coverage.
• Within this group, API.ai is superior at price (free), Microsoft LUIS at speed
(almost 50% faster response), IBM Watson at performance (esp. at smaller
datasets). Here, only API.ai detects (~40% of) out-of-domain requests and produce
Fallback intent.
2. For extreme language coverage, go with wit.ai.
• It’s interesting if Machine Translation can be applied either on training or on
testing stage to increase language coverage for the top-3 providers.
3. The performance varies a lot for different intents and
dataset sizes. We recommend to evaluate several
providers on your data before making a choice.
August 2017© Intento, Inc.
Discover the best service providers
for your AI task
Evaluate performance on your own
data
Access any provider with no effort
using to our Single API
Intento Service Platform
August 2017© Intento, Inc.
Intento
https://inten.to
Dmitry Labazkin,
Grigory Sapunov,
Konstantin Savenkov
Intento, Inc.

<hello@inten.to>

Mais conteúdo relacionado

Mais procurados

The Future Of Work & The Work Of The Future
The Future Of Work & The Work Of The FutureThe Future Of Work & The Work Of The Future
The Future Of Work & The Work Of The FutureArturo Pelayo
 
Solve for X with AI: a VC view of the Machine Learning & AI landscape
Solve for X with AI: a VC view of the Machine Learning & AI landscapeSolve for X with AI: a VC view of the Machine Learning & AI landscape
Solve for X with AI: a VC view of the Machine Learning & AI landscapeEd Fernandez
 
Human-centric SEO: How to rock future-proof on-page SEO
Human-centric SEO: How to rock future-proof on-page SEOHuman-centric SEO: How to rock future-proof on-page SEO
Human-centric SEO: How to rock future-proof on-page SEOMarjoleinSchollaert1
 
Stanford and the Silicon Valley Ecosystem - Tom Byers - 2013 HBCU Innovation ...
Stanford and the Silicon Valley Ecosystem - Tom Byers - 2013 HBCU Innovation ...Stanford and the Silicon Valley Ecosystem - Tom Byers - 2013 HBCU Innovation ...
Stanford and the Silicon Valley Ecosystem - Tom Byers - 2013 HBCU Innovation ...EpicenterUSA
 
Numbers that Actually Matter. Finding Your North Star
Numbers that Actually Matter. Finding Your North Star Numbers that Actually Matter. Finding Your North Star
Numbers that Actually Matter. Finding Your North Star Mamoon Hamid
 
Writer Pitch Deck
Writer Pitch DeckWriter Pitch Deck
Writer Pitch DeckXavierRoss4
 
Good Audience Fundraising Deck - Angel Round
Good Audience Fundraising Deck - Angel RoundGood Audience Fundraising Deck - Angel Round
Good Audience Fundraising Deck - Angel Roundsherm8n
 
Modern Marketing Data Capabilities.docx
Modern Marketing Data Capabilities.docxModern Marketing Data Capabilities.docx
Modern Marketing Data Capabilities.docxSasikalaKumaravel2
 
Rippling's $175M Series B pitch deck
Rippling's $175M Series B pitch deckRippling's $175M Series B pitch deck
Rippling's $175M Series B pitch deckPitch Decks
 
SEO Restart 2022: Daniel Duriš - Úspešné migrácie veľkých webov: príprava a p...
SEO Restart 2022: Daniel Duriš - Úspešné migrácie veľkých webov: príprava a p...SEO Restart 2022: Daniel Duriš - Úspešné migrácie veľkých webov: príprava a p...
SEO Restart 2022: Daniel Duriš - Úspešné migrácie veľkých webov: príprava a p...Taste
 
Purple Go: 500 Demo Day Batch 23
Purple Go: 500 Demo Day Batch 23Purple Go: 500 Demo Day Batch 23
Purple Go: 500 Demo Day Batch 23500 Startups
 
Monzo: £19.3M VC investment turned into $2B. Monzo's Series C pitch deck
Monzo: £19.3M VC investment turned into $2B. Monzo's Series C pitch deckMonzo: £19.3M VC investment turned into $2B. Monzo's Series C pitch deck
Monzo: £19.3M VC investment turned into $2B. Monzo's Series C pitch deckAA BB
 
Shopify investor deck 11022016
Shopify investor deck 11022016Shopify investor deck 11022016
Shopify investor deck 11022016shopifyInvestors
 
The 10 most interesting slides that helped our SaaS company raise 9 million
The 10 most interesting slides that helped our SaaS company raise 9 millionThe 10 most interesting slides that helped our SaaS company raise 9 million
The 10 most interesting slides that helped our SaaS company raise 9 millionGoCanvas
 
Tomasz Tunguz - 10 Learnings from Redpoint 2020 GTM Survey
Tomasz Tunguz - 10 Learnings from Redpoint 2020 GTM SurveyTomasz Tunguz - 10 Learnings from Redpoint 2020 GTM Survey
Tomasz Tunguz - 10 Learnings from Redpoint 2020 GTM SurveySaaStock
 
Pitch Deck Teardown: Northspyre's $25 million Series B deck
Pitch Deck Teardown: Northspyre's $25 million Series B deckPitch Deck Teardown: Northspyre's $25 million Series B deck
Pitch Deck Teardown: Northspyre's $25 million Series B deckHajeJanKamps
 

Mais procurados (20)

The Future Of Work & The Work Of The Future
The Future Of Work & The Work Of The FutureThe Future Of Work & The Work Of The Future
The Future Of Work & The Work Of The Future
 
Solve for X with AI: a VC view of the Machine Learning & AI landscape
Solve for X with AI: a VC view of the Machine Learning & AI landscapeSolve for X with AI: a VC view of the Machine Learning & AI landscape
Solve for X with AI: a VC view of the Machine Learning & AI landscape
 
Human-centric SEO: How to rock future-proof on-page SEO
Human-centric SEO: How to rock future-proof on-page SEOHuman-centric SEO: How to rock future-proof on-page SEO
Human-centric SEO: How to rock future-proof on-page SEO
 
Stanford and the Silicon Valley Ecosystem - Tom Byers - 2013 HBCU Innovation ...
Stanford and the Silicon Valley Ecosystem - Tom Byers - 2013 HBCU Innovation ...Stanford and the Silicon Valley Ecosystem - Tom Byers - 2013 HBCU Innovation ...
Stanford and the Silicon Valley Ecosystem - Tom Byers - 2013 HBCU Innovation ...
 
Numbers that Actually Matter. Finding Your North Star
Numbers that Actually Matter. Finding Your North Star Numbers that Actually Matter. Finding Your North Star
Numbers that Actually Matter. Finding Your North Star
 
Writer Pitch Deck
Writer Pitch DeckWriter Pitch Deck
Writer Pitch Deck
 
Good Audience Fundraising Deck - Angel Round
Good Audience Fundraising Deck - Angel RoundGood Audience Fundraising Deck - Angel Round
Good Audience Fundraising Deck - Angel Round
 
N26 - NOAH16 London
N26 - NOAH16 LondonN26 - NOAH16 London
N26 - NOAH16 London
 
Modern Marketing Data Capabilities.docx
Modern Marketing Data Capabilities.docxModern Marketing Data Capabilities.docx
Modern Marketing Data Capabilities.docx
 
Rippling's $175M Series B pitch deck
Rippling's $175M Series B pitch deckRippling's $175M Series B pitch deck
Rippling's $175M Series B pitch deck
 
Brex Pitch Deck
Brex Pitch DeckBrex Pitch Deck
Brex Pitch Deck
 
SEO Restart 2022: Daniel Duriš - Úspešné migrácie veľkých webov: príprava a p...
SEO Restart 2022: Daniel Duriš - Úspešné migrácie veľkých webov: príprava a p...SEO Restart 2022: Daniel Duriš - Úspešné migrácie veľkých webov: príprava a p...
SEO Restart 2022: Daniel Duriš - Úspešné migrácie veľkých webov: príprava a p...
 
SEO preciso, MAXI probable
SEO preciso, MAXI probableSEO preciso, MAXI probable
SEO preciso, MAXI probable
 
Purple Go: 500 Demo Day Batch 23
Purple Go: 500 Demo Day Batch 23Purple Go: 500 Demo Day Batch 23
Purple Go: 500 Demo Day Batch 23
 
Monzo: £19.3M VC investment turned into $2B. Monzo's Series C pitch deck
Monzo: £19.3M VC investment turned into $2B. Monzo's Series C pitch deckMonzo: £19.3M VC investment turned into $2B. Monzo's Series C pitch deck
Monzo: £19.3M VC investment turned into $2B. Monzo's Series C pitch deck
 
Shopify investor deck 11022016
Shopify investor deck 11022016Shopify investor deck 11022016
Shopify investor deck 11022016
 
The 10 most interesting slides that helped our SaaS company raise 9 million
The 10 most interesting slides that helped our SaaS company raise 9 millionThe 10 most interesting slides that helped our SaaS company raise 9 million
The 10 most interesting slides that helped our SaaS company raise 9 million
 
Tomasz Tunguz - 10 Learnings from Redpoint 2020 GTM Survey
Tomasz Tunguz - 10 Learnings from Redpoint 2020 GTM SurveyTomasz Tunguz - 10 Learnings from Redpoint 2020 GTM Survey
Tomasz Tunguz - 10 Learnings from Redpoint 2020 GTM Survey
 
Simple. Friendly. Smart.
Simple. Friendly. Smart. Simple. Friendly. Smart.
Simple. Friendly. Smart.
 
Pitch Deck Teardown: Northspyre's $25 million Series B deck
Pitch Deck Teardown: Northspyre's $25 million Series B deckPitch Deck Teardown: Northspyre's $25 million Series B deck
Pitch Deck Teardown: Northspyre's $25 million Series B deck
 

Destaque

State of the Machine Translation by Intento (November 2017)
State of the Machine Translation by Intento (November 2017)State of the Machine Translation by Intento (November 2017)
State of the Machine Translation by Intento (November 2017)Konstantin Savenkov
 
Artificial Intelligence API Services Compared
Artificial Intelligence API Services ComparedArtificial Intelligence API Services Compared
Artificial Intelligence API Services ComparedCraig Milroy
 
BootstrapLabs - Tracxn Report - artificial intelligence for the Applied Arti...
BootstrapLabs - Tracxn  Report - artificial intelligence for the Applied Arti...BootstrapLabs - Tracxn  Report - artificial intelligence for the Applied Arti...
BootstrapLabs - Tracxn Report - artificial intelligence for the Applied Arti...BootstrapLabs
 
Neural Machine Translation: a report from the front line
Neural Machine Translation: a report from the front lineNeural Machine Translation: a report from the front line
Neural Machine Translation: a report from the front lineIconic Translation Machines
 
Create Your Own Voice Assistant Using Watson and IBM Bluemix
Create Your Own Voice Assistant Using Watson and IBM BluemixCreate Your Own Voice Assistant Using Watson and IBM Bluemix
Create Your Own Voice Assistant Using Watson and IBM BluemixVidyasagar Machupalli
 
How to ready your organization for Artificial Intelligence
How to ready your organization for Artificial IntelligenceHow to ready your organization for Artificial Intelligence
How to ready your organization for Artificial IntelligenceCraig Milroy
 

Destaque (7)

State of the Machine Translation by Intento (November 2017)
State of the Machine Translation by Intento (November 2017)State of the Machine Translation by Intento (November 2017)
State of the Machine Translation by Intento (November 2017)
 
Artificial Intelligence API Services Compared
Artificial Intelligence API Services ComparedArtificial Intelligence API Services Compared
Artificial Intelligence API Services Compared
 
BootstrapLabs - Tracxn Report - artificial intelligence for the Applied Arti...
BootstrapLabs - Tracxn  Report - artificial intelligence for the Applied Arti...BootstrapLabs - Tracxn  Report - artificial intelligence for the Applied Arti...
BootstrapLabs - Tracxn Report - artificial intelligence for the Applied Arti...
 
Neural Machine Translation: a report from the front line
Neural Machine Translation: a report from the front lineNeural Machine Translation: a report from the front line
Neural Machine Translation: a report from the front line
 
Machine Translation: The Neural Frontier
Machine Translation: The Neural FrontierMachine Translation: The Neural Frontier
Machine Translation: The Neural Frontier
 
Create Your Own Voice Assistant Using Watson and IBM Bluemix
Create Your Own Voice Assistant Using Watson and IBM BluemixCreate Your Own Voice Assistant Using Watson and IBM Bluemix
Create Your Own Voice Assistant Using Watson and IBM Bluemix
 
How to ready your organization for Artificial Intelligence
How to ready your organization for Artificial IntelligenceHow to ready your organization for Artificial Intelligence
How to ready your organization for Artificial Intelligence
 

Semelhante a NLU / Intent Detection Benchmark by Intento, August 2017

DEV206_Life of a Code Change to a Tier 1 Service
DEV206_Life of a Code Change to a Tier 1 ServiceDEV206_Life of a Code Change to a Tier 1 Service
DEV206_Life of a Code Change to a Tier 1 ServiceAmazon Web Services
 
IOT311_Customer Stories of Things, Cloud, and Analytics on AWS
IOT311_Customer Stories of Things, Cloud, and Analytics on AWSIOT311_Customer Stories of Things, Cloud, and Analytics on AWS
IOT311_Customer Stories of Things, Cloud, and Analytics on AWSAmazon Web Services
 
EXTENT-2017: Putting AI to Test
EXTENT-2017: Putting AI to TestEXTENT-2017: Putting AI to Test
EXTENT-2017: Putting AI to TestIosif Itkin
 
Where Open Source Meets Audit Analytics - ISACA North America CACS 2017
Where Open Source Meets Audit Analytics - ISACA North America CACS 2017Where Open Source Meets Audit Analytics - ISACA North America CACS 2017
Where Open Source Meets Audit Analytics - ISACA North America CACS 2017Andrew Clark
 
GPSTEC201_Building an Artificial Intelligence Practice for Consulting Partners
GPSTEC201_Building an Artificial Intelligence Practice for Consulting PartnersGPSTEC201_Building an Artificial Intelligence Practice for Consulting Partners
GPSTEC201_Building an Artificial Intelligence Practice for Consulting PartnersAmazon Web Services
 
MCL308_Using a Digital Assistant in the Enterprise for Business Productivity
MCL308_Using a Digital Assistant in the Enterprise for Business ProductivityMCL308_Using a Digital Assistant in the Enterprise for Business Productivity
MCL308_Using a Digital Assistant in the Enterprise for Business ProductivityAmazon Web Services
 
2018 04 20 Azure Global Bootcamp - Artificial Intelligence and Cognitive Serv...
2018 04 20 Azure Global Bootcamp - Artificial Intelligence and Cognitive Serv...2018 04 20 Azure Global Bootcamp - Artificial Intelligence and Cognitive Serv...
2018 04 20 Azure Global Bootcamp - Artificial Intelligence and Cognitive Serv...Bruno Capuano
 
Building a Real-Time Data Platform on AWS
Building a Real-Time Data Platform on AWSBuilding a Real-Time Data Platform on AWS
Building a Real-Time Data Platform on AWSInjae Kwak
 
Cloud Sentiment Analysis - Vendor Overview (April 2018)
Cloud Sentiment Analysis - Vendor Overview (April 2018)Cloud Sentiment Analysis - Vendor Overview (April 2018)
Cloud Sentiment Analysis - Vendor Overview (April 2018)Konstantin Savenkov
 
APIs as a Product Strategy
APIs as a Product StrategyAPIs as a Product Strategy
APIs as a Product StrategyRavi Kumar
 
DEV322_Continuous Integration Best Practices for Software Development Teams
DEV322_Continuous Integration Best Practices for Software Development TeamsDEV322_Continuous Integration Best Practices for Software Development Teams
DEV322_Continuous Integration Best Practices for Software Development TeamsAmazon Web Services
 
Introduction to Mobile Development with AWS
Introduction to Mobile Development with AWSIntroduction to Mobile Development with AWS
Introduction to Mobile Development with AWSAmazon Web Services
 
Introduction to Mobile Development with AWS
Introduction to Mobile Development with AWSIntroduction to Mobile Development with AWS
Introduction to Mobile Development with AWSAmazon Web Services
 
MBL306_Mobile State of the Union
MBL306_Mobile State of the UnionMBL306_Mobile State of the Union
MBL306_Mobile State of the UnionAmazon Web Services
 
CON320_Monitoring, Logging and Debugging Containerized Services
CON320_Monitoring, Logging and Debugging Containerized ServicesCON320_Monitoring, Logging and Debugging Containerized Services
CON320_Monitoring, Logging and Debugging Containerized ServicesAmazon Web Services
 
Building your own chat bot with Amazon Lex - Hebrew Webinar
Building your own chat bot with Amazon Lex - Hebrew WebinarBuilding your own chat bot with Amazon Lex - Hebrew Webinar
Building your own chat bot with Amazon Lex - Hebrew WebinarBoaz Ziniman
 
DevOps for a Mobile World: Building an iOS or Android Mobile App in the Cloud...
DevOps for a Mobile World: Building an iOS or Android Mobile App in the Cloud...DevOps for a Mobile World: Building an iOS or Android Mobile App in the Cloud...
DevOps for a Mobile World: Building an iOS or Android Mobile App in the Cloud...Amazon Web Services
 

Semelhante a NLU / Intent Detection Benchmark by Intento, August 2017 (20)

DEV206_Life of a Code Change to a Tier 1 Service
DEV206_Life of a Code Change to a Tier 1 ServiceDEV206_Life of a Code Change to a Tier 1 Service
DEV206_Life of a Code Change to a Tier 1 Service
 
IOT311_Customer Stories of Things, Cloud, and Analytics on AWS
IOT311_Customer Stories of Things, Cloud, and Analytics on AWSIOT311_Customer Stories of Things, Cloud, and Analytics on AWS
IOT311_Customer Stories of Things, Cloud, and Analytics on AWS
 
DevOps on AWS
DevOps on AWSDevOps on AWS
DevOps on AWS
 
DevOps on AWS
DevOps on AWSDevOps on AWS
DevOps on AWS
 
EXTENT-2017: Putting AI to Test
EXTENT-2017: Putting AI to TestEXTENT-2017: Putting AI to Test
EXTENT-2017: Putting AI to Test
 
Where Open Source Meets Audit Analytics - ISACA North America CACS 2017
Where Open Source Meets Audit Analytics - ISACA North America CACS 2017Where Open Source Meets Audit Analytics - ISACA North America CACS 2017
Where Open Source Meets Audit Analytics - ISACA North America CACS 2017
 
GPSTEC201_Building an Artificial Intelligence Practice for Consulting Partners
GPSTEC201_Building an Artificial Intelligence Practice for Consulting PartnersGPSTEC201_Building an Artificial Intelligence Practice for Consulting Partners
GPSTEC201_Building an Artificial Intelligence Practice for Consulting Partners
 
MCL308_Using a Digital Assistant in the Enterprise for Business Productivity
MCL308_Using a Digital Assistant in the Enterprise for Business ProductivityMCL308_Using a Digital Assistant in the Enterprise for Business Productivity
MCL308_Using a Digital Assistant in the Enterprise for Business Productivity
 
Samepoint API
Samepoint APISamepoint API
Samepoint API
 
2018 04 20 Azure Global Bootcamp - Artificial Intelligence and Cognitive Serv...
2018 04 20 Azure Global Bootcamp - Artificial Intelligence and Cognitive Serv...2018 04 20 Azure Global Bootcamp - Artificial Intelligence and Cognitive Serv...
2018 04 20 Azure Global Bootcamp - Artificial Intelligence and Cognitive Serv...
 
Building a Real-Time Data Platform on AWS
Building a Real-Time Data Platform on AWSBuilding a Real-Time Data Platform on AWS
Building a Real-Time Data Platform on AWS
 
Cloud Sentiment Analysis - Vendor Overview (April 2018)
Cloud Sentiment Analysis - Vendor Overview (April 2018)Cloud Sentiment Analysis - Vendor Overview (April 2018)
Cloud Sentiment Analysis - Vendor Overview (April 2018)
 
APIs as a Product Strategy
APIs as a Product StrategyAPIs as a Product Strategy
APIs as a Product Strategy
 
DEV322_Continuous Integration Best Practices for Software Development Teams
DEV322_Continuous Integration Best Practices for Software Development TeamsDEV322_Continuous Integration Best Practices for Software Development Teams
DEV322_Continuous Integration Best Practices for Software Development Teams
 
Introduction to Mobile Development with AWS
Introduction to Mobile Development with AWSIntroduction to Mobile Development with AWS
Introduction to Mobile Development with AWS
 
Introduction to Mobile Development with AWS
Introduction to Mobile Development with AWSIntroduction to Mobile Development with AWS
Introduction to Mobile Development with AWS
 
MBL306_Mobile State of the Union
MBL306_Mobile State of the UnionMBL306_Mobile State of the Union
MBL306_Mobile State of the Union
 
CON320_Monitoring, Logging and Debugging Containerized Services
CON320_Monitoring, Logging and Debugging Containerized ServicesCON320_Monitoring, Logging and Debugging Containerized Services
CON320_Monitoring, Logging and Debugging Containerized Services
 
Building your own chat bot with Amazon Lex - Hebrew Webinar
Building your own chat bot with Amazon Lex - Hebrew WebinarBuilding your own chat bot with Amazon Lex - Hebrew Webinar
Building your own chat bot with Amazon Lex - Hebrew Webinar
 
DevOps for a Mobile World: Building an iOS or Android Mobile App in the Cloud...
DevOps for a Mobile World: Building an iOS or Android Mobile App in the Cloud...DevOps for a Mobile World: Building an iOS or Android Mobile App in the Cloud...
DevOps for a Mobile World: Building an iOS or Android Mobile App in the Cloud...
 

Mais de Konstantin Savenkov

GPT and other Text Transformers: Black Swans and Stochastic Parrots
GPT and other Text Transformers:  Black Swans and Stochastic ParrotsGPT and other Text Transformers:  Black Swans and Stochastic Parrots
GPT and other Text Transformers: Black Swans and Stochastic ParrotsKonstantin Savenkov
 
Dodging AI biases in future-proof Machine Translation solutions
Dodging AI biases in future-proof Machine Translation solutionsDodging AI biases in future-proof Machine Translation solutions
Dodging AI biases in future-proof Machine Translation solutionsKonstantin Savenkov
 
Building Multi-Purpose MT Portfolio
Building Multi-Purpose MT PortfolioBuilding Multi-Purpose MT Portfolio
Building Multi-Purpose MT PortfolioKonstantin Savenkov
 
Как выбрать и приручить машинный перевод / How to choose and tame the Machine...
Как выбрать и приручить машинный перевод / How to choose and tame the Machine...Как выбрать и приручить машинный перевод / How to choose and tame the Machine...
Как выбрать и приручить машинный перевод / How to choose and tame the Machine...Konstantin Savenkov
 
Progress in Commercial Machine Translation Systems
Progress in Commercial Machine Translation SystemsProgress in Commercial Machine Translation Systems
Progress in Commercial Machine Translation SystemsKonstantin Savenkov
 
Cloud Artificial Intelligence Landscape
Cloud Artificial Intelligence LandscapeCloud Artificial Intelligence Landscape
Cloud Artificial Intelligence LandscapeKonstantin Savenkov
 
State of the Machine Translation by Intento (stock engines, Jun 2019)
State of the Machine Translation by Intento (stock engines, Jun 2019)State of the Machine Translation by Intento (stock engines, Jun 2019)
State of the Machine Translation by Intento (stock engines, Jun 2019)Konstantin Savenkov
 
State of the Machine Translation by Intento (stock engines, Jan 2019)
State of the Machine Translation by Intento (stock engines, Jan 2019)State of the Machine Translation by Intento (stock engines, Jan 2019)
State of the Machine Translation by Intento (stock engines, Jan 2019)Konstantin Savenkov
 
State of the Domain-Adaptive Machine Translation by Intento (November 2018)
State of the Domain-Adaptive Machine Translation by Intento (November 2018)State of the Domain-Adaptive Machine Translation by Intento (November 2018)
State of the Domain-Adaptive Machine Translation by Intento (November 2018)Konstantin Savenkov
 
EVALUATION IN USE: NAVIGATING THE MT ENGINE LANDSCAPE WITH THE INTENTO EVALUA...
EVALUATION IN USE: NAVIGATING THE MT ENGINE LANDSCAPE WITH THE INTENTO EVALUA...EVALUATION IN USE: NAVIGATING THE MT ENGINE LANDSCAPE WITH THE INTENTO EVALUA...
EVALUATION IN USE: NAVIGATING THE MT ENGINE LANDSCAPE WITH THE INTENTO EVALUA...Konstantin Savenkov
 
Improving the Demand Side of the AI Economy (API World 2018)
Improving the Demand Side of the AI Economy (API World 2018)Improving the Demand Side of the AI Economy (API World 2018)
Improving the Demand Side of the AI Economy (API World 2018)Konstantin Savenkov
 
Сравнительный анализ систем машинного перевода
Сравнительный анализ систем машинного переводаСравнительный анализ систем машинного перевода
Сравнительный анализ систем машинного переводаKonstantin Savenkov
 
State of the Machine Translation by Intento (July 2018)
State of the Machine Translation by Intento (July 2018)State of the Machine Translation by Intento (July 2018)
State of the Machine Translation by Intento (July 2018)Konstantin Savenkov
 
State of the Machine Translation by Intento (March 2018)
State of the Machine Translation by Intento (March 2018)State of the Machine Translation by Intento (March 2018)
State of the Machine Translation by Intento (March 2018)Konstantin Savenkov
 
Intento Machine Translation Benchmark, July 2017
Intento Machine Translation Benchmark, July 2017Intento Machine Translation Benchmark, July 2017
Intento Machine Translation Benchmark, July 2017Konstantin Savenkov
 
Управление бизнесом на основе данных
Управление бизнесом на основе данныхУправление бизнесом на основе данных
Управление бизнесом на основе данныхKonstantin Savenkov
 
Messengers, Bots and Personal Assistants
Messengers, Bots and Personal AssistantsMessengers, Bots and Personal Assistants
Messengers, Bots and Personal AssistantsKonstantin Savenkov
 

Mais de Konstantin Savenkov (20)

GPT and other Text Transformers: Black Swans and Stochastic Parrots
GPT and other Text Transformers:  Black Swans and Stochastic ParrotsGPT and other Text Transformers:  Black Swans and Stochastic Parrots
GPT and other Text Transformers: Black Swans and Stochastic Parrots
 
Dodging AI biases in future-proof Machine Translation solutions
Dodging AI biases in future-proof Machine Translation solutionsDodging AI biases in future-proof Machine Translation solutions
Dodging AI biases in future-proof Machine Translation solutions
 
Building Multi-Purpose MT Portfolio
Building Multi-Purpose MT PortfolioBuilding Multi-Purpose MT Portfolio
Building Multi-Purpose MT Portfolio
 
Machine Translation Insights
Machine Translation InsightsMachine Translation Insights
Machine Translation Insights
 
Как выбрать и приручить машинный перевод / How to choose and tame the Machine...
Как выбрать и приручить машинный перевод / How to choose and tame the Machine...Как выбрать и приручить машинный перевод / How to choose and tame the Machine...
Как выбрать и приручить машинный перевод / How to choose and tame the Machine...
 
Progress in Commercial Machine Translation Systems
Progress in Commercial Machine Translation SystemsProgress in Commercial Machine Translation Systems
Progress in Commercial Machine Translation Systems
 
Cloud Artificial Intelligence Landscape
Cloud Artificial Intelligence LandscapeCloud Artificial Intelligence Landscape
Cloud Artificial Intelligence Landscape
 
Intento Enterprise MT Hub
Intento Enterprise MT HubIntento Enterprise MT Hub
Intento Enterprise MT Hub
 
State of the Machine Translation by Intento (stock engines, Jun 2019)
State of the Machine Translation by Intento (stock engines, Jun 2019)State of the Machine Translation by Intento (stock engines, Jun 2019)
State of the Machine Translation by Intento (stock engines, Jun 2019)
 
State of the Machine Translation by Intento (stock engines, Jan 2019)
State of the Machine Translation by Intento (stock engines, Jan 2019)State of the Machine Translation by Intento (stock engines, Jan 2019)
State of the Machine Translation by Intento (stock engines, Jan 2019)
 
State of the Domain-Adaptive Machine Translation by Intento (November 2018)
State of the Domain-Adaptive Machine Translation by Intento (November 2018)State of the Domain-Adaptive Machine Translation by Intento (November 2018)
State of the Domain-Adaptive Machine Translation by Intento (November 2018)
 
EVALUATION IN USE: NAVIGATING THE MT ENGINE LANDSCAPE WITH THE INTENTO EVALUA...
EVALUATION IN USE: NAVIGATING THE MT ENGINE LANDSCAPE WITH THE INTENTO EVALUA...EVALUATION IN USE: NAVIGATING THE MT ENGINE LANDSCAPE WITH THE INTENTO EVALUA...
EVALUATION IN USE: NAVIGATING THE MT ENGINE LANDSCAPE WITH THE INTENTO EVALUA...
 
Improving the Demand Side of the AI Economy (API World 2018)
Improving the Demand Side of the AI Economy (API World 2018)Improving the Demand Side of the AI Economy (API World 2018)
Improving the Demand Side of the AI Economy (API World 2018)
 
Сравнительный анализ систем машинного перевода
Сравнительный анализ систем машинного переводаСравнительный анализ систем машинного перевода
Сравнительный анализ систем машинного перевода
 
State of the Machine Translation by Intento (July 2018)
State of the Machine Translation by Intento (July 2018)State of the Machine Translation by Intento (July 2018)
State of the Machine Translation by Intento (July 2018)
 
State of the Machine Translation by Intento (March 2018)
State of the Machine Translation by Intento (March 2018)State of the Machine Translation by Intento (March 2018)
State of the Machine Translation by Intento (March 2018)
 
Intento Machine Translation Benchmark, July 2017
Intento Machine Translation Benchmark, July 2017Intento Machine Translation Benchmark, July 2017
Intento Machine Translation Benchmark, July 2017
 
Building a Data Driven Business
Building a Data Driven BusinessBuilding a Data Driven Business
Building a Data Driven Business
 
Управление бизнесом на основе данных
Управление бизнесом на основе данныхУправление бизнесом на основе данных
Управление бизнесом на основе данных
 
Messengers, Bots and Personal Assistants
Messengers, Bots and Personal AssistantsMessengers, Bots and Personal Assistants
Messengers, Bots and Personal Assistants
 

Último

Glenn Lazarus- Why Your Observability Strategy Needs Security Observability
Glenn Lazarus- Why Your Observability Strategy Needs Security ObservabilityGlenn Lazarus- Why Your Observability Strategy Needs Security Observability
Glenn Lazarus- Why Your Observability Strategy Needs Security Observabilityitnewsafrica
 
Connecting the Dots for Information Discovery.pdf
Connecting the Dots for Information Discovery.pdfConnecting the Dots for Information Discovery.pdf
Connecting the Dots for Information Discovery.pdfNeo4j
 
Emixa Mendix Meetup 11 April 2024 about Mendix Native development
Emixa Mendix Meetup 11 April 2024 about Mendix Native developmentEmixa Mendix Meetup 11 April 2024 about Mendix Native development
Emixa Mendix Meetup 11 April 2024 about Mendix Native developmentPim van der Noll
 
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyesHow to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyesThousandEyes
 
2024 April Patch Tuesday
2024 April Patch Tuesday2024 April Patch Tuesday
2024 April Patch TuesdayIvanti
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity PlanDatabarracks
 
QCon London: Mastering long-running processes in modern architectures
QCon London: Mastering long-running processes in modern architecturesQCon London: Mastering long-running processes in modern architectures
QCon London: Mastering long-running processes in modern architecturesBernd Ruecker
 
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024BookNet Canada
 
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc
 
Bridging Between CAD & GIS: 6 Ways to Automate Your Data Integration
Bridging Between CAD & GIS:  6 Ways to Automate Your Data IntegrationBridging Between CAD & GIS:  6 Ways to Automate Your Data Integration
Bridging Between CAD & GIS: 6 Ways to Automate Your Data Integrationmarketing932765
 
Varsha Sewlal- Cyber Attacks on Critical Critical Infrastructure
Varsha Sewlal- Cyber Attacks on Critical Critical InfrastructureVarsha Sewlal- Cyber Attacks on Critical Critical Infrastructure
Varsha Sewlal- Cyber Attacks on Critical Critical Infrastructureitnewsafrica
 
TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024Lonnie McRorey
 
A Framework for Development in the AI Age
A Framework for Development in the AI AgeA Framework for Development in the AI Age
A Framework for Development in the AI AgeCprime
 
UiPath Community: Communication Mining from Zero to Hero
UiPath Community: Communication Mining from Zero to HeroUiPath Community: Communication Mining from Zero to Hero
UiPath Community: Communication Mining from Zero to HeroUiPathCommunity
 
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxMerck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxLoriGlavin3
 
Genislab builds better products and faster go-to-market with Lean project man...
Genislab builds better products and faster go-to-market with Lean project man...Genislab builds better products and faster go-to-market with Lean project man...
Genislab builds better products and faster go-to-market with Lean project man...Farhan Tariq
 
A Deep Dive on Passkeys: FIDO Paris Seminar.pptx
A Deep Dive on Passkeys: FIDO Paris Seminar.pptxA Deep Dive on Passkeys: FIDO Paris Seminar.pptx
A Deep Dive on Passkeys: FIDO Paris Seminar.pptxLoriGlavin3
 
Digital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxDigital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxLoriGlavin3
 
So einfach geht modernes Roaming fuer Notes und Nomad.pdf
So einfach geht modernes Roaming fuer Notes und Nomad.pdfSo einfach geht modernes Roaming fuer Notes und Nomad.pdf
So einfach geht modernes Roaming fuer Notes und Nomad.pdfpanagenda
 
MuleSoft Online Meetup Group - B2B Crash Course: Release SparkNotes
MuleSoft Online Meetup Group - B2B Crash Course: Release SparkNotesMuleSoft Online Meetup Group - B2B Crash Course: Release SparkNotes
MuleSoft Online Meetup Group - B2B Crash Course: Release SparkNotesManik S Magar
 

Último (20)

Glenn Lazarus- Why Your Observability Strategy Needs Security Observability
Glenn Lazarus- Why Your Observability Strategy Needs Security ObservabilityGlenn Lazarus- Why Your Observability Strategy Needs Security Observability
Glenn Lazarus- Why Your Observability Strategy Needs Security Observability
 
Connecting the Dots for Information Discovery.pdf
Connecting the Dots for Information Discovery.pdfConnecting the Dots for Information Discovery.pdf
Connecting the Dots for Information Discovery.pdf
 
Emixa Mendix Meetup 11 April 2024 about Mendix Native development
Emixa Mendix Meetup 11 April 2024 about Mendix Native developmentEmixa Mendix Meetup 11 April 2024 about Mendix Native development
Emixa Mendix Meetup 11 April 2024 about Mendix Native development
 
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyesHow to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
 
2024 April Patch Tuesday
2024 April Patch Tuesday2024 April Patch Tuesday
2024 April Patch Tuesday
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity Plan
 
QCon London: Mastering long-running processes in modern architectures
QCon London: Mastering long-running processes in modern architecturesQCon London: Mastering long-running processes in modern architectures
QCon London: Mastering long-running processes in modern architectures
 
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
 
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
 
Bridging Between CAD & GIS: 6 Ways to Automate Your Data Integration
Bridging Between CAD & GIS:  6 Ways to Automate Your Data IntegrationBridging Between CAD & GIS:  6 Ways to Automate Your Data Integration
Bridging Between CAD & GIS: 6 Ways to Automate Your Data Integration
 
Varsha Sewlal- Cyber Attacks on Critical Critical Infrastructure
Varsha Sewlal- Cyber Attacks on Critical Critical InfrastructureVarsha Sewlal- Cyber Attacks on Critical Critical Infrastructure
Varsha Sewlal- Cyber Attacks on Critical Critical Infrastructure
 
TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024
 
A Framework for Development in the AI Age
A Framework for Development in the AI AgeA Framework for Development in the AI Age
A Framework for Development in the AI Age
 
UiPath Community: Communication Mining from Zero to Hero
UiPath Community: Communication Mining from Zero to HeroUiPath Community: Communication Mining from Zero to Hero
UiPath Community: Communication Mining from Zero to Hero
 
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxMerck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
 
Genislab builds better products and faster go-to-market with Lean project man...
Genislab builds better products and faster go-to-market with Lean project man...Genislab builds better products and faster go-to-market with Lean project man...
Genislab builds better products and faster go-to-market with Lean project man...
 
A Deep Dive on Passkeys: FIDO Paris Seminar.pptx
A Deep Dive on Passkeys: FIDO Paris Seminar.pptxA Deep Dive on Passkeys: FIDO Paris Seminar.pptx
A Deep Dive on Passkeys: FIDO Paris Seminar.pptx
 
Digital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxDigital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptx
 
So einfach geht modernes Roaming fuer Notes und Nomad.pdf
So einfach geht modernes Roaming fuer Notes und Nomad.pdfSo einfach geht modernes Roaming fuer Notes und Nomad.pdf
So einfach geht modernes Roaming fuer Notes und Nomad.pdf
 
MuleSoft Online Meetup Group - B2B Crash Course: Release SparkNotes
MuleSoft Online Meetup Group - B2B Crash Course: Release SparkNotesMuleSoft Online Meetup Group - B2B Crash Course: Release SparkNotes
MuleSoft Online Meetup Group - B2B Crash Course: Release SparkNotes
 

NLU / Intent Detection Benchmark by Intento, August 2017

  • 1. NLU / Intent Detection Benchmark by Intento August 2017
  • 2. About • At Intento, we want to make Machine Intelligence services easy to discover, choose and use. • So far, the evaluation is the most problematic part: to compare providers, one need to sign a lot of contracts and integrate a lot of APIs. • We deliver that for FREE on public datasets. To evaluate on you own dataset, contact our sales. • Also, check out our Machine Translation Benchmark. Machine Translation is an easy way to build a multi- lingual bot.
  • 3. Overview • Natural Language Understanding Services with Public APIs* • IBM Watson Conversation • API.ai API • Microsoft LUIS • Amazon Lex • Recast.ai API • wit.ai API • SNIPS API • Benchmark Dimensions • Intent Prediction Performance • False Positives • Learning Speed (performance on small datasets) • Language Coverage, Price, Response time August 2017© Intento, Inc. * as of today, some of them don’t have a Public API and we’ve got an access for the purpose of this benchmark
  • 4. NLU Engines Compared August 2017© Intento, Inc.
  • 5. API.ai / Google • Website: https://api.ai • Launched: 2010 (acquired by Google in 2016) • Pricing model: FREE • Interface: HTTP REST API “Build delightful and natural conversational experiences” August 2017© Intento, Inc.
  • 6. wit.ai / Facebook • Website: https://wit.ai • Launched: 2013 (acquired by Facebook in 2015) • Pricing model: FREE • Interface: HTTP REST API “Natural Language for Developers” August 2017© Intento, Inc.
  • 7. IBM Watson Conversation • Website: https://www.ibm.com/watson/services/ conversation/ • Launched: 2016 • Pricing model: Pay As You Go • Interface: HTTP REST API “Quickly build and deploy chatbots and virtual agents across a variety of channels, including mobile devices, messaging platforms, and even robots.” August 2017© Intento, Inc.
  • 8. Microsoft LUIS • Website: https://www.luis.ai/ • Launched: 2015 • Pricing model: Pay As You Go • Interface: HTTP REST API “Language Understanding Intelligent Service. Add conversational intelligence to your apps.” August 2017© Intento, Inc.
  • 9. Amazon Lex • Website: https://aws.amazon.com/lex/ • Launched: 2016 • Pricing model: Pay As You Go • Interface: HTTP REST API • Important Restrictions apply (see Dataset slide) “Conversational interfaces for your applications. Powered by the same deep learning technologies as Alexa” August 2017© Intento, Inc.
  • 10. Recast.ai • Website: https://recast.ai • Launched: 2016 • Pricing mode: Free tier + Contact sales • Interface: HTTP REST API “The collaborative platform to build, train, deploy and monitor intelligent bots for developers” August 2017© Intento, Inc.
  • 11. SNIPS • Website: https://snips.ai • Launched: 2017 • Pricing model: Free to test + Pay per Device • Interface: On Device* “Snips is an AI-powered voice assistant you can add to your products. It runs on-device and is Private by Design” * we’ve tested a hosted version with a private API provided by SNIPS August 2017© Intento, Inc.
  • 12. Historical timeline 2011 2015 20162012 2013 2014 20172010 Conversation Facebook Google LUIS August 2017© Intento, Inc.
  • 13. The Approach August 2017© Intento, Inc.
  • 14. Dataset • The original dataset is the SNIPS.ai 2017 NLU Benchmark • English language only • We have removed duplicates that differ by number of whitespaces, quotes, lettercase etc • Resulting dataset parameters*: 7 intents (next slide), 15.6K samples (~2K per intent), 340K symbols • We also used ~450 samples from SNIPS.ai 2016 NLU Benchmark to test for False Positives * For Amazon Lex, the training set is capped by 200K symbols per API limitation; also symbol limitations apply, resulting in 4500 utterances (~640 per intent). August 2017© Intento, Inc.
  • 15. Intents [*] • SearchCreativeWork (e.g. Find me the I, Robot television show) • GetWeather (e.g. Is it windy in Boston, MA right now?) • BookRestaurant (e.g. I want to book a highly rated restaurant for me and my boyfriend tomorrow night) • PlayMusic (e.g. Play the last track from Beyoncé off Spotify) • AddToPlaylist (e.g. Add Diamonds to my roadtrip playlist) • RateBook (e.g. Give 6 stars to Of Mice and Men) • SearchScreeningEvent (e.g. Check the showtimes for Wonder Woman in Paris) [*] quoted from https://github.com/snipsco/nlu-benchmark/tree/master/2017-06-custom-intent-engines August 2017© Intento, Inc.
  • 16. I. Prediction Performance August 2017© Intento, Inc.
  • 17. Experimental setting • Inspired by the SNIPS Benchmarks (2016, 2017) • We benchmark intent detection only, no parameter extraction yet • For each provider, one model is trained to detect all intents • We run all models with the default confidence score thresholds. • 3-fold 80/20* Stratified Monte Carlo cross-validation * 47/20 for Amazon Lex August 2017© Intento, Inc.
  • 18. Scores Normalization (I) Intents: the good, the bad and the ugly (to compare providers we need to remove intent-related bias) F1 Scores* Confusion matrix * F1 Score is a weighted average of the precision and recall; reaches its best value at 1 and worst score at 0. August 2017© Intento, Inc.
  • 19. Scores Normalization (II) • Standardizing F1, P and R scores for each intent (SD- normalization) • Then adjusting scales by multiplying on the global std and adding the global mean (next slide) August 2017© Intento, Inc.
  • 20. Detection Performance* • Black bars indicate confidence intervals • Amazon Lex is trained on a smaller dataset due to its API limits * Mean standardized F1 scores, adjusted to the initial scale using global mean and std August 2017© Intento, Inc.
  • 21. Average Precision* • Black bars indicate confidence intervals • Amazon Lex is trained on a smaller dataset due to its API limits August 2017© Intento, Inc. * Mean standardized Precision, adjusted to the initial scale using global mean and std
  • 22. Average Recall* * Mean standardized Recall, adjusted to the initial scale using global mean and std • Black bars indicate confidence intervals • is Amazon Lex trained on a smaller dataset due to its API limits August 2017© Intento, Inc.
  • 23. Precision vs. Recall August 2017© Intento, Inc.
  • 24. Discussion • Training models is cumbersome for most of the services: • manual work (adding models in the web interface) and • solving issues with the tech support. • Based on the confidence intervals, all providers fall into several groups: • Top-runners: IBM Watson, API.ai, Microsoft LUIS • Amazon Lex: API limits don’t allow for training multi-intent model on enough samples • Choosing the provider: • For “good” intents (like GetWeather), all providers are good enough. For “bad” intents, having a “good” providers is crucial • Within each tier, the leader depends on the intent data August 2017© Intento, Inc.
  • 25. II. False Positives August 2017© Intento, Inc.
  • 26. Approach • How does NLU behaves when a user express an intent it wasn’t trained for? • Expected behavior: produce the Fallback Intent (no trained intents pass the detection threshold) • 1411 utterances from the domains other than Music, Movie, Weather, RestaurantReservation, Entertainment and TV. • Compare % of (false) positive detections for each NLU provider August 2017© Intento, Inc.
  • 28. Discussion • Only Snips.ai and API.ai are somewhat good at detecting that users asks for something the agent is not trained for • IBM Watson and Microsoft LUIS are trying to map any user request to one of the intents from the training set Perhaps the Fallback intent should be manually added and trained on junk utterances? August 2017© Intento, Inc.
  • 29. III. Learning Curve August 2017© Intento, Inc.
  • 30. Experimental Setting • Similar to the Prediction Performance (slide 18) • 20% of the dataset reserved for testing (stratified) • From the remaining 80%, for intent we’ve randomly built a set of training sets of the following cardinality: 10, 25, 50, 100, 200, 500, 1000* • No cross-validation • Analyzed F1 Scores, normalised as described on slides 19-20. * for Amazon Lex, 10, 25, 50, 100, 200 August 2017© Intento, Inc.
  • 31. Leaning curve by provider Vertical bars denote confidence intervals August 2017© Intento, Inc.
  • 32. Discussion • On <100 samples IBM Watson is superior*. API.ai catches up at >100 samples. • Detecting the user’s intent is crucial for the subsequent slot extraction and response generation. • The learning curve is quite steep, good performance requires hundreds of utterances to train on. • Most of the pre-built intents (Microsoft LUIS, API.ai, etc) are built on 10-50 utterances. * SNIPS advertises a special enterprise feature to generate additional samples for smaller datasets, but it is not available by default August 2017© Intento, Inc.
  • 33. IV. Language coverage August 2017© Intento, Inc.
  • 34. Supported languages • Merged all dialects (e.g. en- uk and en-us). • Note we’ve tested the performance only for English August 2017© Intento, Inc.
  • 36. Discussion Potentially, Machine Translation may be used to increase the language coverage and/or performance: • either by translating both the training and testing utterances to English • or by translating only testing utterances and using the English training model That’s something to check in future benchmarks August 2017© Intento, Inc.
  • 37. V. Other observations August 2017© Intento, Inc.
  • 38. Average response time * * Snips assumes on-device deployment, we put here a response time for a hosted test bench August 2017© Intento, Inc.
  • 39. Price per 1K requests* * prediction requests; SNIPS has per device pricing and is not shown on this chart CONTACTSALES Free Free August 2017© Intento, Inc.
  • 41. Performance (F1) vs. Price* Performance Affordability = 1/Price wit.ai amazon.lex microsoft.luis ibm.watson api.ai * Recast and SNIPS are not shown as they don't provide a public pricing FREE August 2017© Intento, Inc.
  • 42. Performance (F1) vs. Latency* Performance Speed = 1/Latency snips recast wit.ai amazon.lex microsoft.luis ibm.watson api.ai * Snips assumes on-device deployment, we put here a response time for a hosted test bench August 2017© Intento, Inc.
  • 43. Conclusions 1. API.ai, Microsoft LUIS and IBM Watson have overall best intent detection performance, speed and language coverage. • Within this group, API.ai is superior at price (free), Microsoft LUIS at speed (almost 50% faster response), IBM Watson at performance (esp. at smaller datasets). Here, only API.ai detects (~40% of) out-of-domain requests and produce Fallback intent. 2. For extreme language coverage, go with wit.ai. • It’s interesting if Machine Translation can be applied either on training or on testing stage to increase language coverage for the top-3 providers. 3. The performance varies a lot for different intents and dataset sizes. We recommend to evaluate several providers on your data before making a choice. August 2017© Intento, Inc.
  • 44. Discover the best service providers for your AI task Evaluate performance on your own data Access any provider with no effort using to our Single API Intento Service Platform August 2017© Intento, Inc.