An Introduction to Machine Translation

1
An Introduction to Machine Translation

• Andy Way, DCU

2
The Rise Fall of Different MT Paradigms
3
Three main approaches to RBMT
language-neutral interlingua
TRANSFER
GENERATION
ANALYSIS
direct translation
target text
source text
The Vauquois Pyramid
4
System Design Concerns

• Multilingual vs. Bilingual
• Multilingual
• Extreme Eurotra, i.e. 72 language pairs Modest
  EN ?DE,FR,ES, i.e. 3 language pairs
• Intermediate EN,FR,DE,ES,JP, but not all
  combinations
• Bilingual
• Unidirectional vs. Bidirectional
• EN?FR or FR?EN
• Reversible vs. Non-reversible
• EN?FR, same EN,FR components for Analysis
  Generation, and reversible transfer module
• EN?FR FR?EN, but different EN, FR components
  for Analysis Generation, and different transfer
  modules, NB, lack of modularity
• Direct vs. Transfer vs. Interlingua
• Batch vs. Interactive

5
Advantages/Disadvantages of Direct Systems

• Advantages
• Engine's competence lies in its comparative
  grammar.
• Highly robust. Does not break down or stop
  whenit encounters unknown words, unknown
  grammaticalconstructs, or ill-formed Input
• Designed for unidirectional translation between
  one pair of langs. Not conducive to genuine
  multilingual MT design.
• Disadvantages
• word-for-word' translation local reordering
  poortranslation, using cheap bilingual
  dictionary rudimentary knowledge of target
  language.
• Linguistically, computationally naive. No
  analysis of internalstructure of Input,
  especially w.r.t. the grammatical relationships
  between the main parts of sentences.

6
Advantages/Disadvantages of Interlingual Systems

• Advantages
• Intermediate representation (IR) fully specified,
  i.e. no need to look back' at Source in order to
  generate Target.
• Easy to extend to other langs.
• Built-in back translation useful for testing.
• Disadvantages
• How to define an Interlingua for closely related
  languages?
• Truly universal Interlingua possible?

7
Advantages/Disadvantages of Transfer Systems

• Advantages
• No language-independent representations source
  IR specific to a particular lang., as is the
  target lang. IR.
• So Complexity of Analysis Generation components
  much reduced
• Also, no necessary equivalence between source and
  targetIRs for the same language!
• Disadvantages
• Not so easy to extend to other languages n
  analysis modules, n generation modules, n x n-1
  transfer modules, i.e. not much less than n²
• No guaranteed built-in back translation.

8
Direct, or Indirect?

• Direct
• From manufacturer's viewpoint, better, as it's
  more robust
• Indirect
• Falls over more easily.
• Development phase can be trying.
• Commercially, must be supplemented with
  techniques for dealing with unseen Input.
• What about Translation Quality?
• Indirect systems clearly better in principle.
• However, constructing MT engine requires
  considerable effort.
• Direct Systems can achieve good performance.
• Summary
• Research mostly Transfer-based, with rules
  automatically acquired from data
• Industrially we can expect highly-developed
  Direct Systems to survive for some years to come

9
Other Material

• Arnold, D. et al. (1994) Machine Translation -
  An Introductory Guide NCC Blackwell, Oxford
• Hutchins, J. H. Somers (1992) An Introduction
  to MT Academic Press, London
• Trujillo, A. (1999) Translation Engines
  Springer, London
• Newer books include
• Bowker, L. (2002) Computer-Aided Translation
  Technology, U. of Ottawa Press.
• Somers, H. (2003) Computers and Translation A
  translator's guide, John Benjamins.
• Bond, F. (2005) Translating the Untranslatable,
  CSLI.
• Quah, C. (2006) Translation and Technology,
  Palgrave MacMillan.

10
Why Corpus-Based MT?

• the (relative) failure of rule-based approaches
• the increasing availability of machine-readable
  text
• the increase in capability of hardware (CPU,
  memory, disk space) with associated decrease in
  cost

11
Corpus-Based MT is here to stay

• These approaches are now mainstream
• Most researchers are developing corpus-based
  systems
• First company to use SMT now exists
  http//www.languageweaver.com
• CNGL partner Traslán uses EBMT/SMT hybrid
• In recent large-scale evaluations, corpus-based
  MT systems come first.
• Two caveats
• Most industrial systems are still rule-based (but
  cf. Googles systems now all SMT)
• Current mainstream evaluation metrics favour
  n-gram-based systems (i.e. bias towards SMT).

12
Thanks to Kevin Knight
13
Centauri/Arcturan Exercise
Slides already on CA446 webpage
14
Centauri/Arcturan Knight, 1997

• Your assignment, put these words in order
• jjat, arrat, mat, bat, oloat, at-yurp
• There are 6! different orders possible, so 720
  different translations.
• Best order (according to placement in TL side of
  the corpus is as given above)
• Not just unigrams, but n-grams also

15
Its Really SpanishEnglish!
Clients do not sell pharmaceuticals in Europe gt
Clientes no venden medicinas en Europa
 
16
Some more to try

• iat lat pippat eneat hilat oloat at-yurp.
• totat nnat forat arrat mat bat.
• wat dat quat cat uskrat at-drubel.

17
Some more to try

• iat lat pippat eneat hilat oloat at-yurp.
• totat nnat forat arrat mat bat.
• wat dat quat cat uskrat at-drubel.
• if you have trouble sleeping at nights!

18
What have we just seen?

• what parallel corpora look like
• how relevant parallel corpora are for MT
• how to build bilingual dictionaries from parallel
  corpora
• how cognate information may be useful in MT
• how to do word alignment.

19
What else do we need to know?

• about word alignment on a larger scale
• about phrasal alignment, the norm in real
  translation data
• about unknown words
• the importance of knowing the target language
  (vs. source) in making fluent translations
• about locality in word order shifts
• how to guess the meanings/translations of unknown
  words
• about how much uncertainty the machine faces in
  working with limited data
• about working on different domains

20
Do such methods scale to real MT?

• Availability of monolingual and bilingual
  corpora?
• Possibility of sentence-aligning bilingual
  corpora?
• Can we write an algorithm to extract the
  translation dictionary?
• Can we write an algorithm to extract the
  monolingual word pair counts?
• Can we write an algorithm to generate
  translations using our translation dictionary and
  word pair counts?

21
Do such methods scale to real MT?

• Availability of monolingual and bilingual
  corpora?
• Possibility of sentence-aligning bilingual
  corpora?
• Can we write an algorithm to extract the
  translation dictionary?
• Can we write an algorithm to extract the
  monolingual word pair counts?
• Can we write an algorithm to generate
  translations using our translation dictionary and
  word pair counts?
• WILL THE TRANSLATIONS PRODUCED BE ANY GOOD?

22
Parallel Corpora

• Hugely important but not available in a wide
  range of language pairs
• ChineseEnglish Hong Kong data
• FrenchEnglish Canadian Hansards
• Older EU pairs Europarl Koehn 04
• Newer EU pairs JRC-Acquis Communautaire, very
  recently distributed updated Europarl
• ArabicEnglish LDC Data
• NIST, IWSLT, TC-STAR Evaluations

23
Caveat interpres!

• Beware of sparse data!
• Beware of unrepresentative corpora!
• Beware of poor quality language!
• If the corpora are small, or of poor quality, or
  are unrepresentative, then our statistical
  language models will be poor, so any results we
  achieve will be poor.