PROGRESS IN
COMMERCIAL MACHINE
TRANSLATION SYSTEMS
by Konstantin Savenkov, 

Ph.D., CEO Intento

October 29-30, 2019
Stanford University, Human-Centered Artificial Intelligence (HAI) and AI Index
Workshop on Measurement in AI Policy: Opportunities and Challenges
Intento
Alibaba Amazon Baidu
Cloud
Translate
DeepL eBay
Globalese Google GTCom IBM Iconic Kakao
KantanMT Microsoft Mirai ModernMT Naver Niutrans
Omniscien
Pangea
MT
PROMT PrompsIT Rozetta SAP
SDL Sogou Systran Tencent Tilde Yandex
Youdao
COMMERCIAL MT SYSTEMS
2
All product names, trademarks and registered trademarks are property of their respective owners. All company, product and service names used in this website are for
identification purposes only. Use of these names, trademarks and brands does not imply endorsement.
© Intento, Inc. / October 2019
Intento
VENDOR DYNAMICS (STOCK MODELS)
3
Commercial
Alibaba, Amazon,
Baidu, CloudTranslate,
DeepL, Google,
GTCom, IBM, Mirai,
Microsoft, ModernMT,
Naver, Niutrans,
PROMT, Rozetta, SAP,
SDL, Sogou, Systran,
Tilde, Tencent, Yandex,
Youdao
Preview / Limited
eBay, Kakao, QCRI
0
5
10
15
20
25
Mar 18 Jul 18 Dec 18 Jun 19 Nov 19
Preview
Commercial
Intento, Inc. • June 2019
© Intento, Inc. / October 2019
Intento
SUPPORTED LANGUAGE PAIRS
4
1
100
10000
N
iutrans
G
oogle
Yandex
M
icrosoftv3
Sogou
Baidu
Am
azon
Kakao
Systran
Tencent
SDL
PRO
M
T
G
TC
om
SAP
DeepL
M
odernM
TIBM
W
atson
v3
N
aver
Youdao
Alibaba
eBay
Tilde
1
3
2
54
6
8
272
2 202
1
2
20
24
38
5256
72
9090
111121122139
342
594
756
3 4223 782
7 482
10 50613 340
Total
Unique
* where possible, we have checked via API if all language pairs advertised by the
documentation are supported and removed the pairs we were unable to locate in the API.
** as advertised (not validated via API)
Unique
language pairs
- supported
exclusively by
one provider
© Intento, Inc. / October 2019
Intento
MT QUALITY EVALUATION
5
Intento monitors MT Quality since May 2017 (public report
every 4-6 months).
—
48 popular language pairs, based on WMT and other public
news corpora.
—
Reference-based evaluation using hLEPOR score (n=2000,
statistically significant)
© Intento, Inc. / October 2019
Intento
BEST MT
ENGINES
(AS OF
JUNE 2019)
6
en ru ja de es fr pt it zh cs tr fi ro ko ar nl
en
ru
ja
de
es
fr
pt
it
zh
cs
tr
fi
ro
ko
ar
nl
MT Engines
deepl
google
amazon
yandex
systran-pnmt
modernmt
ibm
promt
microsoft
tencent
baidu
6
In several cases, there’s no
statistically significant difference
between the top engines.
changed since
Jan 2019:
19 pairs
© Intento, Inc. / October 2019
Intento
MORE INVESTMENT IN MT QUALITY GOES
INTO POPULAR LANGUAGE PAIRS
7
Intento
data curation
—
new architectures
—
direct translation
© Intento, Inc. / October 2019
Intento
MT PROGRESS BEYOND LOW-IMPACT CONTENT
REQUIRES MORE THAN GENERIC MODELS
8
Intento
Cross-language
NLP
High-volume low
impact
Low-impact
(inbound etc)
High-impact
generic
High-impact in-
domain
MACHINES
HUMANS
© Intento, Inc. / October 2019
Intento
MT PROGRESS BEYOND LOW-IMPACT CONTENT
REQUIRES MORE THAN GENERIC MODELS
9
Intento
Cross-language
NLP
High-volume low
impact
Low-impact
(inbound etc)
High-impact
generic
High-impact in-
domain
MACHINES
HUMANS
HOT TOPIC
© Intento, Inc. / October 2019
Intento
2018: RAISE OF DOMAIN-ADAPTIVE NMT
10
Intento
Sep
2017
Oct
2018
Nov
2017
May
2018
Jun
2018
Jul
2018
Globalese
Custom
NMT
Lilt
Adaptive
NMT
IBM
Custom
NMT
Microsoft
Custom
Translator
Google
AutoML
Translation
SDL
ETS 8.0
ModernMT
Enterprise
Apr
2018
Systran
PNMT
© Intento, Inc. / October 2019
Intento
2019: CUSTOM TERMINOLOGY SUPPORT
11
Intento
Jun
2018
Oct
2019
Oct
2018
Jan
2019
Apr
2019
Amazon
Translate
Google
Translate
v3
SDL
BeGlobal
4.1
Microsoft
Custom
Translator
Nov
2018
Systran
PNMT
IBM
Custom
NMT
“forced glossary customisation”
“phrase dictionaries”
“custom terminology”
“syntax-aware
custom terminology”
May
2019
Yandex
Cloud
Translate v2
dynamic glossaries
“glossaries”
“glossary feature”
© Intento, Inc. / October 2019
Intento
IMPROVEMENT BEYOND STOCK MODELS
12
Intento
Stock models define starting
points
—

Adaptation based on
Translation Memory and
Terminology drives further
improvement
—

Depends on architecture, data
volume and quality
© Intento, Inc. / October 2019
Intento
GENERIC STOCK MODELS
Alibaba Amazon Baidu DeepL eBay Google
GTCom IBM Kakao Microsoft Mirai ModernMT
Niutrans Naver Omniscien PROMT Rozetta SAP
SDL Sogou Systran Tencent Tilde Yandex
DOMAIN ADAPTATION CAPABILITIES
13© Intento, Inc. / October 2019
VERTICAL STOCK MODELS
CUSTOM TERMINOLOGY SUPPORT
AUTO DOMAIN ADAPTATION MANUAL DOMAIN ADAPTATION
Youdao
Alibaba Baidu
Cloud
Translate
Microsoft Omniscien PROMT
SAP Systran
Amazon Baidu Google IBM Microsoft Rozetta SDL Systran Yandex
Globalese Google IBM
Kantan Microsoft ModernMT
Omniscien SDL Systran
Alibaba Baidu
Cloud
Translate
Iconic
Omniscien PangeaMT Prompsit PROMT
SDL Systran Tilde Yandex
All product names, trademarks and registered trademarks are property of their respective owners. All company, product and service names used in this website are for
identification purposes only. Use of these names, trademarks and brands does not imply endorsement.
Intento
DATA COLLECTION PRACTICES NEED TO
MATCH GROWING MT UBIQUITY
14
Growing MT quality makes it
ubiquitous
—

Enterprise adoption is far behind
user adoption
—

Data collection policy remains in
the fine print of “free” MT services
—

That’s more important than
collecting cookies (we think)
“We recently found that ~2Gb of
confidential data monthly goes
from our network to (free MT
service)”
company Y (2019)
“We tried to block traffic to (free MT
service), but SVP said it will stop
the entire company’s operations”
company X (2018)
“We discovered text that had been
typed in on (MT service) could be
found by anyone conducting a web
search.”
Statoil (Sept 2017, link)
© Intento, Inc. / October 2019
THANKS!
by Konstantin Savenkov, 

Ph.D., CEO Intento

October 29-30, 2019
Stanford University, Human-Centered Artificial Intelligence (HAI) and AI Index
Workshop on Measurement in AI Policy: Opportunities and Challenges
THANK YOU!
Konstantin Savenkov

ks@inten.to

2150 Shattuck Ave

Berkeley CA 94704
INTENTO
https://inten.to
16

Progress in Commercial Machine Translation Systems

  • 1.
    PROGRESS IN COMMERCIAL MACHINE TRANSLATIONSYSTEMS by Konstantin Savenkov, Ph.D., CEO Intento October 29-30, 2019 Stanford University, Human-Centered Artificial Intelligence (HAI) and AI Index Workshop on Measurement in AI Policy: Opportunities and Challenges
  • 2.
    Intento Alibaba Amazon Baidu Cloud Translate DeepLeBay Globalese Google GTCom IBM Iconic Kakao KantanMT Microsoft Mirai ModernMT Naver Niutrans Omniscien Pangea MT PROMT PrompsIT Rozetta SAP SDL Sogou Systran Tencent Tilde Yandex Youdao COMMERCIAL MT SYSTEMS 2 All product names, trademarks and registered trademarks are property of their respective owners. All company, product and service names used in this website are for identification purposes only. Use of these names, trademarks and brands does not imply endorsement. © Intento, Inc. / October 2019
  • 3.
    Intento VENDOR DYNAMICS (STOCKMODELS) 3 Commercial Alibaba, Amazon, Baidu, CloudTranslate, DeepL, Google, GTCom, IBM, Mirai, Microsoft, ModernMT, Naver, Niutrans, PROMT, Rozetta, SAP, SDL, Sogou, Systran, Tilde, Tencent, Yandex, Youdao Preview / Limited eBay, Kakao, QCRI 0 5 10 15 20 25 Mar 18 Jul 18 Dec 18 Jun 19 Nov 19 Preview Commercial Intento, Inc. • June 2019 © Intento, Inc. / October 2019
  • 4.
    Intento SUPPORTED LANGUAGE PAIRS 4 1 100 10000 N iutrans G oogle Yandex M icrosoftv3 Sogou Baidu Am azon Kakao Systran Tencent SDL PRO M T G TC om SAP DeepL M odernM TIBM W atson v3 N aver Youdao Alibaba eBay Tilde 1 3 2 54 6 8 272 2 202 1 2 20 24 38 5256 72 9090 111121122139 342 594 756 3 4223 782 7 482 10 50613 340 Total Unique *where possible, we have checked via API if all language pairs advertised by the documentation are supported and removed the pairs we were unable to locate in the API. ** as advertised (not validated via API) Unique language pairs - supported exclusively by one provider © Intento, Inc. / October 2019
  • 5.
    Intento MT QUALITY EVALUATION 5 Intentomonitors MT Quality since May 2017 (public report every 4-6 months). — 48 popular language pairs, based on WMT and other public news corpora. — Reference-based evaluation using hLEPOR score (n=2000, statistically significant) © Intento, Inc. / October 2019
  • 6.
    Intento BEST MT ENGINES (AS OF JUNE2019) 6 en ru ja de es fr pt it zh cs tr fi ro ko ar nl en ru ja de es fr pt it zh cs tr fi ro ko ar nl MT Engines deepl google amazon yandex systran-pnmt modernmt ibm promt microsoft tencent baidu 6 In several cases, there’s no statistically significant difference between the top engines. changed since Jan 2019: 19 pairs © Intento, Inc. / October 2019
  • 7.
    Intento MORE INVESTMENT INMT QUALITY GOES INTO POPULAR LANGUAGE PAIRS 7 Intento data curation — new architectures — direct translation © Intento, Inc. / October 2019
  • 8.
    Intento MT PROGRESS BEYONDLOW-IMPACT CONTENT REQUIRES MORE THAN GENERIC MODELS 8 Intento Cross-language NLP High-volume low impact Low-impact (inbound etc) High-impact generic High-impact in- domain MACHINES HUMANS © Intento, Inc. / October 2019
  • 9.
    Intento MT PROGRESS BEYONDLOW-IMPACT CONTENT REQUIRES MORE THAN GENERIC MODELS 9 Intento Cross-language NLP High-volume low impact Low-impact (inbound etc) High-impact generic High-impact in- domain MACHINES HUMANS HOT TOPIC © Intento, Inc. / October 2019
  • 10.
    Intento 2018: RAISE OFDOMAIN-ADAPTIVE NMT 10 Intento Sep 2017 Oct 2018 Nov 2017 May 2018 Jun 2018 Jul 2018 Globalese Custom NMT Lilt Adaptive NMT IBM Custom NMT Microsoft Custom Translator Google AutoML Translation SDL ETS 8.0 ModernMT Enterprise Apr 2018 Systran PNMT © Intento, Inc. / October 2019
  • 11.
    Intento 2019: CUSTOM TERMINOLOGYSUPPORT 11 Intento Jun 2018 Oct 2019 Oct 2018 Jan 2019 Apr 2019 Amazon Translate Google Translate v3 SDL BeGlobal 4.1 Microsoft Custom Translator Nov 2018 Systran PNMT IBM Custom NMT “forced glossary customisation” “phrase dictionaries” “custom terminology” “syntax-aware custom terminology” May 2019 Yandex Cloud Translate v2 dynamic glossaries “glossaries” “glossary feature” © Intento, Inc. / October 2019
  • 12.
    Intento IMPROVEMENT BEYOND STOCKMODELS 12 Intento Stock models define starting points — Adaptation based on Translation Memory and Terminology drives further improvement — Depends on architecture, data volume and quality © Intento, Inc. / October 2019
  • 13.
    Intento GENERIC STOCK MODELS AlibabaAmazon Baidu DeepL eBay Google GTCom IBM Kakao Microsoft Mirai ModernMT Niutrans Naver Omniscien PROMT Rozetta SAP SDL Sogou Systran Tencent Tilde Yandex DOMAIN ADAPTATION CAPABILITIES 13© Intento, Inc. / October 2019 VERTICAL STOCK MODELS CUSTOM TERMINOLOGY SUPPORT AUTO DOMAIN ADAPTATION MANUAL DOMAIN ADAPTATION Youdao Alibaba Baidu Cloud Translate Microsoft Omniscien PROMT SAP Systran Amazon Baidu Google IBM Microsoft Rozetta SDL Systran Yandex Globalese Google IBM Kantan Microsoft ModernMT Omniscien SDL Systran Alibaba Baidu Cloud Translate Iconic Omniscien PangeaMT Prompsit PROMT SDL Systran Tilde Yandex All product names, trademarks and registered trademarks are property of their respective owners. All company, product and service names used in this website are for identification purposes only. Use of these names, trademarks and brands does not imply endorsement.
  • 14.
    Intento DATA COLLECTION PRACTICESNEED TO MATCH GROWING MT UBIQUITY 14 Growing MT quality makes it ubiquitous — Enterprise adoption is far behind user adoption — Data collection policy remains in the fine print of “free” MT services — That’s more important than collecting cookies (we think) “We recently found that ~2Gb of confidential data monthly goes from our network to (free MT service)” company Y (2019) “We tried to block traffic to (free MT service), but SVP said it will stop the entire company’s operations” company X (2018) “We discovered text that had been typed in on (MT service) could be found by anyone conducting a web search.” Statoil (Sept 2017, link) © Intento, Inc. / October 2019
  • 15.
    THANKS! by Konstantin Savenkov, Ph.D., CEO Intento October 29-30, 2019 Stanford University, Human-Centered Artificial Intelligence (HAI) and AI Index Workshop on Measurement in AI Policy: Opportunities and Challenges
  • 16.
    THANK YOU! Konstantin Savenkov ks@inten.to 2150Shattuck Ave Berkeley CA 94704 INTENTO https://inten.to 16