Mutual bilingual terminology extraction

1
Mutual bilingual terminology extraction

• Le An Ha, Gabriela Fernandez, Ruslan Mitkov,
  Gloria Corpas
• University of Wolverhampton
• Universidad de Sevilla
• Universidad de Malaga
• E-mail l.a.ha,r.mitkov_at_wlv.ac.uk,
  gfernan_at_us.es, gcorpas_at_ya.com

2
Introduction

• Terms and Terminology
• Terms linguistic units which have specialised
  use.
• Terminology the system of terms in a subject
  field.
• Terminology is vital for specialised
  communication, in both mono lingual and multi
  lingual contexts.

3
Mono and multi lingual terminology processing

• Mono lingual terminology processing
• Three steps extraction, validation, and
  organisation.
• Automatic extraction approaches linguistic (may
  produce noises), statistical (may overlook
  important but low frequency terms), and hybrid
  approaches
• Bilingual/Multilingual term extraction
• The same three steps as in monolingual
  terminology processing extraction, validation,
  and organisation
• Relying on parallel corpora aligned at a certain
  level
• Different models to align term candidates
• Alignment as an independent step

4
Our approach mutual bilingual term extraction

• Alignment plays an active role in term
  extraction.
• Automatic alignment is used to propagate the
  strengths of terminology extraction from one
  language into another.
• Relying on the availability of parallel corpora
  aligned at sentence level.

5
Mutual term extraction Three step

• 1 lists of term candidates are extracted for the
  source and target languages
• 2 term candidates from the target language are
  aligned to those in the source language
• 3 if a term candidate in the target language is
  aligned to a term candidate in the source
  language, its term score is increased this
  candidate promoted.
• Steps 1-3 can be repeated many times.

6
Mono-lingual term extraction

• Lexical-syntactic-statistical approach
• Lexical-syntactic POS patterns
• English AN(NP)?ANN
• Spanish NNA(PN)?NA
• Statistical measures
• Different measures tested
• Frequency is chosen

7
Term alignment

• Contingency table-based method log-likelihood is
  used to estimate the likelihood of a term
  candidate in the source language is translated
  into another term candidate in the target
  language
• The table is built using a parallel corpus
  aligned at sentence level

8
Contingency table for lymph node and ganglio
linfático
9
Boosting algorithms

• Hypothesis the term score of a term candidate in
  one language can be used to improve the term
  score of its aligned candidate in the other
  language, and vice versa via boosting processes
• Given that
• AL(T1,T2) alignment score of the two term
  candidates T1 and T2.
• TCsT term score of the candidate T in the
  source language
• TCtT term score of the candidate T in the
  target language
• BT(TC1,TC2) boosting function, i.e. how the
  term score of the aligned term affects the target
  term score Example simple addition
  BT(TC1,TC2)TC1TC2

10
Boosting algorithms (cont.)

• Single boosting boosting process is performed on
  the target language only
• Foreach term candidate Tt in the target language
• Tsargmax(AL(Tt,Ti))
• TCtTtBT(TCsTs,TCtTt)
• Double boosting boosting process is performed on
  both source and target languages
• Foreach term candidate Ts in the source language
• Ttargmax(AL(Ts,Ti))
• TCsTsBT(TCsTs,TCtTt)
• Foreach term candidate Tt in the target language
• Tsargmax((AL(Tt,Ti))
• TCtTtBT(TCsTs,TCtTt)
• Recursive boosting boosting process is repeated
  for both languages until the term candidate lists
  are stabilised.

11
Parameters

• Factors affecting the outcome of the proposed
  algorithms the alignment function AL, the
  mechanism to calculate the initial term scores
  TCs and TCt, and the boosting function BT.
• Different combinations of these functions have
  been experimented with.
• The best term score function is frequency, and
  the best boosting function is simple addition.
• In our next research, we propose several
  probabilistic models which provide better
  probabilistic foundations for the boosting
  function.

12
Evaluation data, gold standard, and evaluation
metrics

• Data
• MedlinePlus parallel texts (English/Spanish) on
  the topic of Cancer
• 9,250 segments for each language
• 31,498 English words, 30344 Spanish words
• Aligned by Trados winalign, manually corrected
• Gold standard
• 389 English terms, 442 Spanish terms, and 357
  term pairs have been validated and used as a gold
  standard.
• Evaluation metrics
• F-measure

13
Evaluation results

• Alignment accuracy
• In total, the algorithm suggests 472 translation
  pairs, of which 374 are confirmed as correct
  translation. This suggests that the accuracy of
  the alignment is 0.8.
• Term extraction performance improved by 10 to 25

14
Results (cont.)
15
Conclusion and future directions

• A promising approach, but
• More research will be needed
• A better mathematical foundation
• Probabilistic models
• More experiments
• Other domains and language pairs
• Legal
• English-Hindi

16
Thank you very much

• Questions? Comments? Criticisms?