Design of a Multilingual MT for Realtime Broadcast Captioning

1
Design of a Multi-lingual MT for Real-time
Broadcast Captioning

• Course Project for 11-731
• Ying Zhang (Joy) Joy_at_cs.cmu.edu
• Advisor Eric Nyberg
• April 18th, 2001

2
Project Description

• A broadcasting company wishes to translate the
  captioning for their show. Translations must be
  provided from English to multiple target
  languages. Real-time, high-accuracy translations
  are required. If the captions are poorly formed,
  then they need not be translated, but the
  customer would like you to consider teaching a
  controlled language to the captioners, so that
  high-quality translation can be achieved.

3
Domain Analysis (Cont.)

• Special requirements
• Translating spoken language
• The system must perform in real-time
• The system can not make pre-edit and post-edit
• The system should provide positive information to
  users as much as possible

4
Domain Analysis

• Characteristics amenable for MT
• The domain is narrow
• Possible to build large scale monolingual corpus
• Not necessary to translate every utterance in the
  broadcast
• Well-defined discourse structure (greetings, etc)
• No correspondence in another culture (the bulls
  outrunning the bears today on Wall Street)

5
Domain Analysis-Data(1)

• Fixed Patterns
• 000084 WWW.MEDIACAPTIONING.COM CLOSED
  CAPTIONING
• 000085 PROVIDED BY BELL ATLANTIC, THE
• 000089 HEART OF COMMUNICATION gtgt
• 000090 FROM CNN IN WASHINGTON, THIS
• 000091 IS "WORLDVIEW." I'M BERNARD
• 000094 SHAW. gtgt AND I'M JUDY WOODRUFF. gtgtgt
• 000095 TALKS BETWEEN PROTESTANT AND

6
Domain Analysis-Data(2)

• Idioms, Phrases and Acronyms
• 000218 SCHEDULE? gtgt THE DISARMAMENT OF ALL
• 000220 PARAMILITARIES INCLUDING THE IRA
• 000223 OR THE INSTITUTION OF A
• 000225 CABINET FOR THE NEW NORTHERN
• 000227 IRELAND ASSEMBLY INCLUDING SINN FEIN
• 000270 ALL THIS INDICATE THAT THE
• 000271 ORIGINAL GOOD FRIDAY AGREEMENT WAS
• 000276 JUST NOT REALISTIC? gtgt NO,

7
Domain Analysis-Data(3)

• Sentence Boundary
• 000112 PARAMILITARIES MUST DISARM. MR. BLAIR AND
• 00140 BEFORE TOO LONG JUDY, YOU CAN SEE
• 000141 BEHIND ME THAT PEOPLE ARE
• 000143 STILL AT WORK HERE ALMOST 24 HOURS
• 000145 AFTER THE DEADLINE PASSED
• 000147 WHERE THERE'S LIFE, THERE'S HOPE
• 000149 AND WHEN THERE'S TALK, I GUESS
• 000151 THERE IS LIFE. WE'RE TOLD BY

8
Assumptions (1)

• Partial Translation is acceptable
• Users may know some English, although their
  vocabulary size may not be large enough
• Users have visual information
• Users may have background information for the
  topic
• Provide only positive information to user, do not
  translate everything unless confident

9
Assumptions (2)

• 10 seconds delay is acceptable

100122am
100112 am
10
Risk Factors

• Technical risks
• Business risks

11
Technical Risks

• Performance constraints
• Real-time
• High-quality, even if partial translation is
  acceptable
• Interface with hardware and software in
  broadcasting system
• Specialized user interface if a human translator
  works together with MT
• The domain of news broadcasting may be too wide
  to be covered by current MT technology

12
Business Risks

• If the quality or real-time requirement can not
  be reached, the customer will not accept this
  product
• The population of potential customers who need
  partial translation result is not large enough
• Human translators provided with transcribed
  caption can translate it in real-time
• Sales force do not think they can sell this
  translated service

13
Technical Rationale

• Multi-engine machine translation system (the
  requirement of multi target languages can not be
  satisfied now)
• Automated update corpus/lexicon from news source
• Provide only positive information, un-translated
  text has 0 information, wrong translation has
  negative information!
• Translate only chunks with high confidence
• Translate only simple structures, leave
  conjunction and prepositions for complex
  structures untranslated

14
System Architecture
Nyberg and Mitamura (1997) "A Real-Time MT
System for Translating Broadcast
Captions"Proceedings of MT Summit VI
15
Extracting Lexicon/Phrase

• The lexicon/phrase used in news domain changes
  rapidly
• Comparable corpus exists
• Extracting lexicon/phrase from comparable corpus

16
Comparable corpus
17
Plan Overview
Research on extracting lexicon from comparable
corpus
Augmenting rules for news domain

• Constructing bilingual corpus

Research on effects of partial translation
Training EBMT
Adjust chart manager for partial translation
18
Resources

• Existing KBMT system
• Existing EBMT software
• Transcribed caption (monolingual) data
• Dictionary

19
Bibliography

• Nyberg and Mitamura, 1997, A Real-Time MT System
  for Translating Broadcast Captions, Proceedings
  of MT Summit VI
• David Turcato, A Unified Example-Based and
  Lexical Approach to Machine Translation, TMI 99
• Pascale Fung, A Statistical View on Bilingual
  Lexicon Extraction From Parallel Corpora to
  Non-parallel Corpora, Lecture Notes in Artificial
  Intelligence, Springer Publisher, vol 1529, 1-17.
  

20
Thanks!

• Questions?