Outline for MT

1
Outline for MT

• Intro and a little history
• Language Similarities and Divergences
• Four main MT Approaches
• Transfer
• Interlingua
• Direct
• Statistical
• Evaluation

2
Project Description

• YES
• Andy Cotton, Ross Cranford, Ralph Harris, Andrew
  Martin, Matt Ratliff, Allen Rawls, Chris Tripp
• KINDA
• Jason Forsythe, Matt Singletary
• NO
• Jerry Martin, Bret Mohler, Rose Rahiminejad, Dan
  Reeves, Bill Shipman, Tom Starr,

3
What is MT?

• Translating a text from one language to another
  automatically.

4
Machine Translation

• As she lay there alone, Dai-yus thoughts turned
  to Bao-chai Then she listened to the insistent
  rustle of the rain on the bamboos and plantains
  outside her window. The coldness penetrated the
  curtains of her bed. Almost without noticing it
  she had begun to cry.

• Dai-yu alone on bed top think-of-with-gratitude
  Bao-chai again listen to window outside bamboo
  tip plantain leaf of on-top rain sound sigh drop
  clear cold penetrate curtain not feeling again
  fall down tears come

5
Machine Translation

• The Story of the Stone
• The Dream of the Red Chamber (Cao Xueqin 1792)
• Issues
• Breaking up into words
• Breaking up into sentences
• Anaphora
• Penetrate - penetrated
• Bamboo tip plaintain leaf - bamboos and
  plantains
• Curtain - curtains of her bed
• Rain sound sigh drop - insistent rustle of the
  rain

6
What is MT not good for?

• Really hard stuff
• Literature
• Natural spoken speech (meetings, court reporting)
• Really important stuff
• Medical translation in hospitals, 911

7
What is MT good for?

• Tasks for which a rough translation is fine
• Web pages, email
• Tasks for which MT can be post-edited
• MT as first pass
• Computer-aided human translation
• Tasks in sublanguage domains where high-quality
  MT is possible

8
Sublanguage domain

• Weather forecasting
• Cloudy with a chance of showers today and
  Thursday
• Low tonight 4
• Can be modeling completely enough to use raw MT
  output
• Word classes and semantic features like MONTH,
  PLACE, DIRECTION, TIME POINT

9
History of MT Pessimism

• 1959/1960 Bar-Hillel Report on the state of MT
  in US and GB
• Argued FAHQT too hard (semantic ambiguity, etc)
• Should work on semi-automatic instead of
  automatic
• His argumentLittle John was looking for his toy
  box. Finally, he found it. The box was in the
  pen. John was very happy.
• Only human knowledge lets us know that
  playpens are bigger than boxes, but writing
  pens are smaller
• His claim we would have to encode all of human
  knowledge

10
History of MT

• 1976 Meteo, weather forecasts from English to
  French
• Systran (Babelfish) been used for 40 years
• 1970s
• European focus in MT mainly ignored in US
• 1980s
• ideas of using AI techniques in MT (KBMT, CMU)
• 1990s
• Commercial MT systems
• Statistical MT
• Speech-to-speech translation

11
Language Similarities and Divergences

• Some aspects of human language are universal or
  near-universal, others diverge greatly.
• Typology the study of systematic
  cross-linguistic similarities and differences
• What are the dimensions along with human
  languages vary?

12
Morphological Variation

• Isolating languages
• Cantonese, Vietnamese each word generally has
  one morpheme
• Vs. Polysynthetic languages
• Siberian Yupik (Eskimo) single word may have
  very many morphemes
• Agglutinative languages
• Turkish morphemes have clean boundaries
• Vs. Fusion languages
• Russian single affix may have many morphemes

13
Syntactic Variation

• SVO (Subject-Verb-Object) languages
• English, German, French, Mandarin
• SOV Languages
• Japanese, Hindi
• VSO languages
• Irish, Classical Arabic
• SVO lgs generally prepositions to Yuriko
• VSO lgs generally postpositions Yuriko ni

14
Segmentation Variation

• Not every writing system has word boundaries
  marked
• Chinese, Japanese, Thai, Vietnamese
• Some languages tend to have sentences that are
  quite long, closer to English paragraphs than
  sentences
• Modern Standard Arabic, Chinese

15
Inferential Load

• Some languages require the hearer to do more
  figuring out of who the various actors in the
  various events are
• Japanese, Chinese,
• Other languages are pretty explicit about saying
  who did what to whom.
• English

16
Inferential Load (2)
All noun phrases in blue do not appear in Chinese
text But they are needed for a good translation
17
Lexical Divergences

• Word to phrases
• English computer science French
  informatique
• POS divergences
• Eng. she likes/VERB to sing
• Ger. Sie singt gerne/ADV
• Eng Im hungry/ADJ
• Sp. tengo hambre/NOUN

18
Lexical Divergences Specificity

• Grammatical constraints
• English has gender on pronouns, Mandarin not.
• So translating 3rd person from Chinese to
  English, need to figure out gender of the person!
• Similarly from English they to French
  ils/elles
• Semantic constraints
• English brother
• Mandarin gege (older) versus didi (younger)
• English wall
• German Wand (inside) Mauer (outside)
• German Berg
• English hill or mountain

19
Lexical Divergence one-to-many
20
Lexical Divergence lexical gaps

• Japanese no word for privacy
• English no word for Cantonese haauseun or
  Japanese oyakoko (something like filial
  piety)
• English cow versus beef, Cantonese ngau

21
Event-to-argument divergences

• English
• The bottle floated out.
• Spanish
• La botella salió flotando.
• The bottle exited floating
• Verb-framed lg mark direction of motion on verb
• Spanish, French, Arabic, Hebrew, Japanese, Tamil,
  Polynesian, Mayan, Bantu familiies
• Satellite-framed lg mark direction of motion on
  satellite
• Crawl out, float off, jump down, walk over to,
  run after
• Rest of Indo-European, Hungarian, Finnish, Chinese

22
MT on the web

• Babelfish
• http//babelfish.altavista.com/

23
3 methods for MT

• Direct
• Transfer
• Interlingua

24
Three MT Approaches Direct, Transfer,
Interlingual
Interlingua
Bonnie Dorr. Original metaphor due to Bernard
Vauquois
Semantic Composition
Semantic Decomposition
Semantic Structure
Semantic Structure
Semantic Analysis
Semantic Generation
Semantic Transfer
Syntactic Structure
Syntactic Structure
Syntactic Transfer
Syntactic Analysis
Syntactic Generation
Word Structure
Word Structure
Direct
Morphological Generation
Morphological Analysis
Target Text
Source Text
25
The Transfer Model

• Idea apply contrastive knowledge, i.e.,
  knowledge about the difference between two
  languages
• Steps
• Analysis Syntactically parse Source language
• Transfer Rules to turn this parse into parse for
  Target language
• Generation Generate Target sentence from parse
  tree

26
Transfer architecture
27
English to French

• Generally
• English Adjective Noun
• French Noun Adjective
• Note not always true
• Route mauvaise bad road, badly-paved road
• Mauvaise route wrong road)
• But is a reasonable first approximation
• Rule

28
Lexical Transfer

• Man
• Ojisan old man
• Man is the only linguistic animal -
• Ningen man, human being
• Or
• Hito person, persons
• Can treat like lexical ambiguity,
• Disambiguate during parsing

29
Transfer some problems

• N2 sets of transfer rules!
• Grammar and lexicon full of language-specific
  stuff
• Hard to build, hard to maintain

30
MT Method 2 Interlingua

• Intuition Instead of lg-lg knowledge rules, use
  the meaning of the sentence to help
• Steps
• 1) translate source sentence into meaning
  representation
• 2) generate target sentence from meaning.

31
Interlingua forthere was an old man gardening

• EVENT GARDENING
• AGENT MAN
• NUMBER SG
• DEFINITENESS INDEF
• ASPECT PROGRESSIVE
• TENSE PAST

32
Interlingua

• Idea is that some of the MT work that we need to
  do is part of other NLP tasks
• E.g., disambiguating Ebook Slibro from Ebook
  Sreservar
• So we could have concepts like BOOKVOLUME and
  RESERVE and solve this problem once for each
  language

33
Vauqois diagram
34
Direct Translation

• Idea more robust, word-specific models
• Start with a Source language sentence
• Write little transformations, directly on words,
  to turn it into a Target language sentence.

35
Direct MT J-to-E

• Watashihatsukuenouenopenwojonniageta.
• 1. Morphological analysis
• Watashi h tsukue no ue no pen wo jon ni ageru
  PAST
• 2) lexical transfer of content words
• I ha desk no ue no pen wo John ni give PAST
• 3) various preposition work
• I ha pen on desk wo John to give PAST.
• 4) SVO rearrangements
• I give PAST pen on desk John to.
• 5) miscellany
• I give PAST the pen on the desk to John.
• 6) morphological generation
• I gave the pen on the desk to John.

36
Direct MT stage 2, (ex. from Panov 1960 via
Hutchins 1986)

• Function direct-translate-much/many
• If preceding word is how
• Return skolko
• Else if preceding word is as
• Return skolko zhe
• Else if word is much
• If preceding words is very
• Return nil (not translated)
• Else if following word is a noun
• Return mnogo
• Else /word is many/
• If preceding word is PREP and following is NOUN
• Return mnogii
• Else return mnogo

37
Three MT Approaches Direct, Transfer,
Interlingual
Interlingua
Slide Bonnie Dorr Original metaphor due
to Bernard Vauquois
Semantic Composition
Semantic Decomposition
Semantic Structure
Semantic Structure
Semantic Analysis
Semantic Generation
Semantic Transfer
Syntactic Structure
Syntactic Structure
Syntactic Transfer
Syntactic Analysis
Syntactic Generation
Word Structure
Word Structure
Direct
Morphological Generation
Morphological Analysis
Target Text
Source Text
38
3 methods pros and cons

• Thanks to Bonnie Dorr!

39
Direct MT pros and cons (Bonnie Dorr)

• Pros
• Fast
• Simple
• Cheap
• No translation rules hidden in lexicon
• Cons
• Unreliable
• Not powerful
• Rule proliferation
• Requires lots of context
• Major restructuring after lexical substitution

40
Interlingual MT pros and cons (B. Dorr)

• Pros
• Avoids the N2 problem
• Easier to write rules
• Cons
• Semantics is HARD
• Useful information lost (paraphrase)

41
Summary

• Intro and a little history
• Language Similarities and Divergences
• Four main MT Approaches
• Transfer
• Interlingua
• Direct
• Statistical
• Evaluation