Chapter 21: Machine Translation

1
Chapter 21 Machine Translation

• Heshaam Faili
• hfaili_at_ece.ut.ac.ir
• University of Tehran

2
What is MT?

• Machine Translation (MT) means translation using
  computers.
• Machine-aided human translation (MAHT)
• Human-aided machine translation (HAMT)
• Fully automated machine translation (FAMT)
• Fully human translation

3
Some definitions

• Machine translation (MT) is the application of
  computers to the task of translating texts from
  one natural language to another. EAMT
• Machine Translation (MT) as it is generally
  known --- the attempt to automate all, or part of
  the process of translating from one human
  language to another. Arnold D J. MACHINE
  TRANSLATION An Introductory Guide
• presumably means going by algorithm from
  machine-readable source text to useful target
  text, without recourse to human translation or
  editing." ALPAC report, 1966

4
An Example Translation between Chinese English
5
Different tasks with MT

• Tasks which rough translation is adequate
• Tasks where a human post-editor is used
• Tasks limited to small sublanguage domains in
  which fully automatic high quality translation
  (FAHQT) is still achievable
• Tasks with Software Localization

6
Machine Translation History

• 1946-1954 Optimistic attitude towards the new
  technologies in MT
• 1949 Informal Memorandum
• Word-to-word translation especially
  Russian-English
• 1954 The demonstration of the Georgetown
  University
• Vocabulary 250 words, Grammar 6 rules, Corpus
  a few simple Russian sentences

7
Machine Translation History

• 1954-1966 Criticism on the subject of MT
• 1966 ALPAC-Report (Automatic Language Processing
  Advisory Committee)
• MT is slower, not very reliable and twice as
  expensive as human translation

8
Machine Translation History

• 1966-1975 Revision of the aims and goals of MT
• Definition of more realistic goals
• Limitation of the research to technical languages
• Syntactical analysis of the source text
• Development of different translation strategies

9
Machine Translation History

• 1975-1989 Increasing interest and promotion
  for MT
• Rapid increase of the demand for translations
• Improvements in hard- and software
• The use of artifical intelligence methodes is now
  possilbe

10
Machine Translation History

• 1990-2000
• Development of comercial products based on
  personal computers
• Specialized supplementary information (medicine,
  law, economics...)
• Translation of spoken language (VERBMOBIL)

11
Machine Translation History

• 2000-Now
• Statistical Approaches and Hybrid Models
• Google Translation Engine ( http//translate.goog
  le.com )
• Yearly MT Official Evaluation race (
  http//www.nist.gov )
• Automated MT Evaluation (NIST, BLEU)

12
Machine Translation History
13
What happened between ALPAC and Now?

• Need for MT and other NLP applications confirmed
• Change in expectations
• Computers have become faster, more powerful
• WWW
• Political state of the world
• Maturation of Linguistics
• Development of hybrid statistical/symbolic
  approaches

14
Language Similarities or Differences

• Universal some aspects which is true for every
  language
• Every Language has words referring to people, or
  every language has nouns or verbs
• Typology Study of systematic cross-linguistics
  similarities and differences
• Morphology Aspects
• isolating Vs. Polysynthetic
• Agglutinative Vs. fusion
• Syntactical Aspects
• SVO , SOV or VSO
• Syntactical-Morphological Aspects
• Head-Marking Vcs. Dependent-marking
• Specific differences Date Format and Standards,
  verb tense differences,
• Lexical Differences Different scenes

15
Lexical Differences
English leg, foot, paw French etape, patte,
jambe, pied
16
Different Machine Translation Systems

• Rule-based
• Statistical Approaches
• Hybrid Systems (Using Statistical approach in an
  Rule-based Architecture or )

17
Three MT Approaches Direct, Transfer, Interlingua
18
Machine Translation Architectures

• Direct architecture
• Direct architecture was used for most MT systems
  of the first generation
• there are no intermediate stages in the process
  of translation

19
Direct Architecture, 4 Steps
20
Machine Translation Architectures

• Characteristics of direct MT systems 
• no complex linguistic theories or parsing
  strategy
• make use of syntactic, semantic and lexical
  similarities between the source and the
  target-language
• based on a single language pair
• direct MT systems are robust, they even
  translate sentences with incomplete information
• dictionaries are the most important components of
  the direct MT systems

21
Machine Translation Architectures

• Transfer architecture
• It consists of three separate stages
• analysis
• Transfer (Syntactical or Lexical)
• synthesis/generation

22
Transfer Architecture,
23
Transfer Example eng-gtSpanishMary did not slap
the green witch
24
Transfer English-gtJapanese
25
Some Examples
26
Persian Example

• I ate the apple ? ?? ??? ?? ?????
• VP ? V NP ? VP ? NP RA V
• I asked the man ? ?? ?? ??? ?????
• VP ? V NP ? VP ? AZ NP V

27
Machine Translation Architectures

• Characteristics of transfer MT systems
• consist of complete linguistic conceptions, not
  only single grammatical or syntactic rules
• the analysis and generation components can be
  used again for further language pairs, if the
  components are exactly separated
• the dictionaries of the transfer MT systems are
  also separated

28
Machine Translation Architectures

• Interlingua architecture
• The interlingua system consists of two stages 
• The source text is analysed into an interlingual
  representation from which the text of the target
  language will be directly generated
• Semantic Analyzer

29
Interlingua Architecture
30
Machine Translation Architectures

• Interlingua architecture
• Advantage
• The interlingua representation can be used for
  any other language
• Disadvantage
• It is difficult to create language-independent
  representations

31
Statistical Approaches
32
Statistical Approach

• 3 stages
• Language model P(E)
• Translation model P(FE)
• Decoder

33
SYSTRAN

• Developed in the late 1950s by Peter Toma
• Initial system for Russian-English translations
• Later adapted for US Air Force and NASA
• Adaptation for other languages
• Important because it had a big influence on many
  Japanese MT systems

34
SYSTRAN

• Rule-based System
• Using finite state grammar (ATN)
• Using a large knowledge-base
• Working on 23 languages specially UE languages
• Customers AltaVista, Lycos, AOL, Compuserve,
  Terra, Google, Apple ?...

35
AppTek TranSphere

• Rule-based System
• Using LFG (Lexical Functional Grammar)
• Analyze the semantic, morphological and syntactic
  structures in English and produce their
  equivalents in the target language
• Utilize a general-purpose lexicon in addition to
  special domain micro-dictionaries
• Translate English to Arabic, Korean, Chinese,
  Turkish, Persian/Dari and Pashto-English
• Bi-Translate French, German, Italian, Portuguese,
  Russian, Spanish, Ukrainian, Hebrew and Dutch

36
MÉTÉO

• Development of an English-French translation
  system by the TAUM Group to cope with the
  bilingual policy of the Canadian government
• 1975 Contract to develop a system to translate
  public weather forecasts
• 1984 Development of Météo 2
• This program proved to be more reliable, faster
  and more cost-effective
• 1989 Development of a French-English version

37
Sakhr Enterprise Machine Translation

• Using transfer Architecture
• analysis on all linguistic levels morphological,
  lexical, syntactic and semantic
• Arabic - English

38
CiyaTran MT

• English - Arabic-scripts languages
  Arabic-Persian-Pashto
• Analyzing the semantic, morphological and
  syntactical structure of input text
• Utilizing Fuzzy Logic and Statistical Analysis
• Using a general-purpose lexicon, as well as 85
  domain-specific databases with over 3,000,000
  words and phrases

39
ARIANE (GETA)

• 1960-1970 Development of CETA System for three
  language pairs
• Change of the name to ARIANE (GETA) as the system
  was changed into a Transfer system

40
EUROTRA

• Developed for the translation requirements within
  the European Community
• A system designed to replace the Systran system
  because of its several limitations
• 3 phases in the development of the program
• One of the biggest MT project regarding
  expenditure, organizations and people involved

41
Google Translation

• Lunched on 2004
• Beta version on English ? Arabic and English ?
  Chinese
• Fully Statistical
• Commercial usage no technical document found
• On 2005, become the best translator on these two
  language http//www.nist.gov

42
Shiraz Project

• This project involved the creation of an
  extensible research prototype of a Persian to
  English machine translation system
• Persian to English
• Transfer Based Translation
• Syntactic Analysis
• Unification Based context free grammar
• Stopped

43
Moses statistical MT

• Open source with C
• allows you to automatically train translation
  models for any language pair.
• All you need is a collection of translated texts
  (parallel corpus).
• beam-search
• phrase-based

44
PSMT (Prolog Statistical Machine Translation)

• Used Prolog to Translate simple structures
• 3 sections
• Language Model Learner
• Dictionary Learner
• Search Program

45
Phramer Statistical Machine Translation

• Phrase-based
• Open-Source with Java
• Using Bayesian model

46
EGYPT

• Statistical MT
• French-English
• Academic
• Some workshops related to EGYPT established

47
MT Challenges Ambiguity

• Syntactic AmbiguityI saw the man with the
  telescope

S
S
NP
VP
NP
VP
VP
PP
NP
V
I
I
PP
NP
V
With the telescope
NP
saw
With the telescope
saw
the man
the man
48
MT Challenges Ambiguity

• Syntactic AmbiguityI saw the man on the hill
  with the telescope
• Lexical Ambiguity
• E book
• Semantic Ambiguity
• Homographyball(E) pelota, baile(S)
• Polysemykill(E), matar, acabar (S)
• Semantic granularityesperar(S) wait, expect,
  hope (E)be(E) ser, estar(S)fish(E) pez,
  pescado(S)

49
How do we evaluate MT?

• Human-based Metrics
• Semantic Invariance
• Pragmatic Invariance
• Lexical Invariance
• Structural Invariance
• Spatial Invariance
• Fluency
• Accuracy
• Do you get it?
• Automatic Metrics Bleu

50
BiLingual Evaluation Understudy (BLEU Papineni,
2001)

• Automatic Technique, but .
• Requires the pre-existence of Human (Reference)
  Translations
• Produce corpus of high-quality human translations
• Judge closeness numerically (word-error rate)
• Compare n-gram matches between candidate
  translation and 1 or more reference translations

51
Other Evaluation metrics

• Bleu, NIST, TER, Precision and Recall, Meteor,
• BLEU rank each MT output by a weighted average
  of the number of N-gram overlaps with the human
  translations

52
BLEU metric
53
BLEU bad results on 1-gram BLEU , better on
modified BLEU
54
BLEU metric
Keep penalty for candidate which is short
Effective reference length