Cover not available
Article published In:
Terminology
Vol. 25:1 (2019) ► pp.93–120

TermEnsembler

An ensemble learning approach to bilingual term extraction and alignment

| Jožef Stefan Institute
| Jožef Stefan Institute
| Jožef Stefan Institute
| Jožef Stefan Institute
| Jožef Stefan Institute

This paper describes TermEnsembler, a bilingual term extraction and alignment system utilizing a novel ensemble learning approach to bilingual term alignment. In the proposed system, the processing starts with monolingual term extraction from a language industry standard file type containing aligned English and Slovenian texts. The two separate term lists are then automatically aligned using an ensemble of seven bilingual alignment methods, which are first executed separately and then merged using the weights learned with an evolutionary algorithm. In the experiments, the weights were learned on one domain and tested on two other domains. When evaluated on the top 400 aligned term pairs, the precision of term alignment is over 96%, while the number of correctly aligned multi-word unit terms exceeds 30% when evaluated on the top 400 term pairs.

Keywords: bilingual terminology alignment, terminology extraction, ensemble learning, evolutionary algorithm
Article outline
  • 1.Introduction
  • 2.Related work
    • 2.1Monolingual term extraction
    • 2.2Bilingual term extraction and alignment
  • 3.TermEnsembler system and methodology
    • 3.1System overview
    • 3.2Monolingual term extraction: LUIZ-CF++ upgrade of LUIZ-CF
    • 3.3Bilingual term alignment: A novel ensemble learning approach
      • 3.3.1Individual bilingual term alignment algorithms
        • Co-frequency
        • Dice
        • Mutual information
        • BI-LUIZ+
        • Novel Phrase-Table-Based Alignment (PTBA) approaches PTBA-1, PTBA-2 and PTBA-3
      • 3.3.2Final term pair ranking by ensemble-based weighting of separate lists of term pairs
      • 3.3.3Evolutionary weighting of term alignment algorithms
  • 4.Experiments and results
    • 4.1Experimental setting
    • 4.2Data
    • 4.3Experimental comparison of individual bilingual term alignment components
      • 4.3.1Precision of individual term alignment components
      • 4.3.2Single vs. multi-word unit terms
    • 4.4Results of the TermEnsembler’s bilingual term alignment approach
      • 4.4.1Optimizing for optimal precision
      • 4.4.2Optimizing for a compromise between optimal precision and number of correct multi-word unit term pairs
      • 4.4.3Recall of the TermEnsembler system
    • 4.5Qualitative analysis of errors
  • 5.Conclusions and future work
  • Acknowledgements
  • Notes
  • References
Available under the Creative Commons Attribution-NonCommercial (CC BY-NC) 4.0 license.

For any use beyond this license, please contact the publisher at [email protected].

Published online: 24 July 2019
DOI logo
https://doi.org/10.1075/term.00029.rep
References
Ahmad, Khurshid, Lee Gillam, and Lena Tostevin
2000 “Weirdness Indexing for Logical Document Extrapolation and Retrieval (WILDER).” In Proceedings of the 8th Text Retrieval Conference (TREC-8), 717–724. Washington, USA.Google Scholar
Aker, Ahmet, Monica Paramita, and Rob Gaizauskas
2013 “Extracting Bilingual Terminologies from Comparable Corpora.” In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 402–411. Sofia, Bulgaria.Google Scholar
Amjadian, Ehsan, Diana Inkpen, Tahereh Paribakht, and Farahnaz Faez
2016 “Local-Global Vectors to Improve Unigram Terminology Extraction.” In Proceedings of the 5th International Workshop on Computational Terminology, 2–11. Osaka, Japan.Google Scholar
Baisa, Vít, Barbora Ulipová, and Michal Cukr
2015 “Bilingual Terminology Extraction in Sketch Engine.” In 9th Workshop on Recent Advances in Slavonic Natural Language Processing, RASLAN 2015 – Proceedings, 61–67. Karlova Studánka, Czech Republic.Google Scholar
Bird, Steven, Ewan Klein, and Edward Loper
2009 Natural Language Processing with Python: Analyzing Text with the Natural Language Toolkit. Sebastopol: O’Reilly Media Inc.Google Scholar
Church, Kenneth Ward, and Patrick Hanks
1990 “Word Association Norms, Mutual Information, and Lexicography.” Computational Linguistics 16 (1): 22–29.Google Scholar
Cohen, Jacob
1968 “Weighted Kappa: Nominal Scale Agreement Provision for Scaled Disagreement or Partial Credit.” Psychological Bulletin 70 (4): 213. DOI logoGoogle Scholar
Conneau, Alexis, Guillaume Lample, Marc’Aurelio Ranzato, Ludovic Denoyer, and Hervé Jégou
2018 “Word Translation Without Parallel Data.” ([URL]) Accessed 2 February 2019.
Daille, Béatrice, and Emmanuel Morin
2005 “French-English Terminology Extraction from Comparable Corpora.” In Proceedings of the 2nd International Joint Conference on Natural Language Processing, 707–718. Jeju Island, South Korea.Google Scholar
Daille, Béatrice, Éric Gaussier, and Jean-Marc Langé
1994 “Towards Automatic Extraction of Monolingual and Bilingual Terminology.” In Proceedings of the 15th Conference on Computational linguistics, 515–521. Kyoto, Japan. DOI logoGoogle Scholar
Dice, LR.
1945 “Measures of the Amount of Ecologic Association between Species.” Ecology 26 (3): 297–302. DOI logoGoogle Scholar
Foo, Jody
2012 Computational Terminology: Exploring Bilingual and Monolingual Term Extraction. Linköping: Linköping University Electronic Press.Google Scholar
Fortin, Félix-Antoine, François-Michel De Rainville, Marc-André Gardner, Marc Parizeau, and Christian Gagné
2012 “DEAP: Evolutionary Algorithms Made Easy.” Journal of Machine Learning Research 131 (no. Jul): 2171–2175.Google Scholar
Frantzi, Katerina, Sophia Ananiadou, and Hideki Mirna
2000 “Automatic Recognition of Multi-Word Terms:. the C-Value/NC-Value Method.” International Journal on Digital Libraries 3(2): 115–130. DOI logoGoogle Scholar
Gouadec, Daniel
2007 Translation as a Profession. Amsterdam/Philadephia: John Benjamins. DOI logoGoogle Scholar
Haque, Rejwanul, Sergio Penkale, and Andy Way
2014 “Bilingual Termbank Creation via Log-Likelihood Comparison and Phrase-Based Statistical Machine Translation.” In Proceedings of the 4th International Workshop on Computational Terminology (Computerm), 42–51. Dublin, Ireland. DOI logoGoogle Scholar
Hazem, Amir, and Emmanuel Morin
2017 “Bilingual Word Embeddings for Bilingual Terminology Extraction from Specialized Comparable Corpora.” In Proceedings of the 8th International Joint Conference on Natural Language Processing, 685–693. Taipei, Taiwan.Google Scholar
Hiemstra, Djoerd
1998 “Multilingual Domain Modeling in Twenty-One: Automatic Creation of a Bi-Directional Translation Lexicon from a Parallel Corpus.” In Proceedings of the 8th CLIN Meeting, 41–58. Amsterdam, The Netherlands.Google Scholar
Justeson, John, and Slava Katz
1995 “Technical Terminology: some Linguistic Properties and an Algorithm for Identification in Text.” Natural Language Engineering 1 (1): 9–27. DOI logoGoogle Scholar
Kageura, Kyo, and Bin Umino
1996 “Methods of Automatic Term Recognition: A Review.” Terminology 3 (2): 259–289. DOI logoGoogle Scholar
Khan, Muhammad Tahir, Yukun Ma, and Jung-jae Kim
2016 “Term Ranker: A Graph-Based Re-Ranking Approach.” In Proceedings of the 29th International Florida Artificial Intelligence Research Society Conference, 310–315. Key Largo, USA.Google Scholar
Koehn, Philipp, Hieu Hoang, Alexandra Birch, Chris Callison-Burch, Marcello Federico, Nicola Bertoldi, Brooke Cowan et al.
2007 “Moses: Open Source Toolkit for Statistical Machine Translation.” In Proceedings of the 45th Annual Meeting of the ACL on Interactive Poster and Demonstration Sessions, 177–180. Prague, Czech Republic. DOI logoGoogle Scholar
Kupiec, Julian
1993 “An Algorithm for Finding Noun Phrase Correspondences in Bilingual Corpora.” In Proceedings of the 31st Annual Meeting on Association for Computational Linguistics, 17–22. Columbus, USA. DOI logoGoogle Scholar
Landis, Richard, and Gary Koch
1977 “The Measurement of Observer Agreement for Categorical Data.” Biometrics 33 (1): 159–174. DOI logoGoogle Scholar
Ljubešić, Nikola, and Tomaž Erjavec
2016 “Corpus vs. Lexicon Supervision in Morphosyntactic Tagging: the Case of Slovene.” In Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC 2016), 23–28. Portorož, Slovenia.Google Scholar
Logar, Nataša, Miha Grčar, Marko Brakus, Tomaž Erjavec, Špela Arhar Holdt, and Simon Krek
2012 Korpusi slovenskega jezika Gigafida, KRES, ccGigafida in ccKRES: gradnja, vsebina, uporaba [Slovenian language corpora Gigafida, KRES, ccGigafida, ccKRES: creation, content, use]. Ljubljana: Trojina, zavod za uporabno slovenistiko; Fakulteta za družbene vede.Google Scholar
Macken, Lieve, Els Lefever, and Veronique Hoste
2013 “Texsis: Bilingual Terminology Extraction from Parallel Corpora using Chunk-Based Alignment.” Terminology 19 (1): 1–30. DOI logoGoogle Scholar
McEnery, Tony, Richard Xiao, and Yukio Tono
2006 Corpus-Based Language Studies: An Advanced Resource Book. London: Taylor & Francis.Google Scholar
Mikolov, Tomas, Kai Chen, Greg Corrado, and Jeffrey Dean
2013 “Efficient Estimation of Word Representations in Vector Space.” ([URL]) Accessed 10 July 2018.
Neubig, Graham, Taro Watanabe, Eiichiro Sumita, Shinsuke Mori, and Tatsuya Kawahara
2011 “An Unsupervised Model for Joint Phrase Alignment and Extraction.” In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics, 632–641. Portland, USA.Google Scholar
Och, Franz Josef, and Hermann Ney
2003 “A Systematic Comparison of Various Statistical Alignment Models.” Computational Linguistics 29 (1): 19–51. DOI logoGoogle Scholar
Pollak, Senja, Anže Vavpetič, Janez Kranjc, Nada Lavrač, and Špela Vintar
2012 “NLP Workflow for On-Line Definition Extraction from English and Slovene Text Corpora.” In Proceedings of KONVENS 2012, 53–60. Vienna, Austria.Google Scholar
Repar, Andraž, and Senja Pollak
2017a “Good Examples for Terminology Databases in Translation.” In Electronic Lexicography in the 21st century. Proceedings of eLex 2017 Conference, 651–661. Leiden, Netherlands.Google Scholar
2017b “Ontology-Based Translation Memory Maintenance.” In Proceedings of the 20th International Multiconference Information Society 2017, 19–22. Ljubljana, Slovenia.Google Scholar
Schmitz, Klaus Dirk, and Daniela Straub
2016 “Tight Budgets and a Growing Number of Languages Impede Terminology Work.” tcworld magazine for international information management ([URL]). Accessed 24 August 2018.
The British National Corpus, version 3 (BNC XML Edition)
2007 Distributed by Bodleian Libraries, University of Oxford, on behalf of the BNC Consortium. (URL: [URL]). Accessed 10 March 2017.
Vintar, Špela
2010 “Bilingual Term Recognition Revisited. The Bag-of-Equivalents Term Alignment Approach.” Terminology 16 (2): 141–158. DOI logoGoogle Scholar
Wang, Rui, Wei Liu, and Chris McDonald
2016 “Featureless Domain-Specific Term Extraction with Minimal Labelled Data.” In Proceedings of the Australasian Language Technology Association Workshop, 103–112. Melbourne, Australia.Google Scholar
Wermter, Joachim, and Udo Hahn
2005 “Paradigmatic Modifiability Statistics for the Extraction of Complex Multi-Word Terms.” In Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing, 843–850. Vancouver, Canada.Google Scholar
Wüster, Eugene
1979 Introduction to the General Theory of Terminology and Terminological Lexicography. Vienna: Springer.Google Scholar
Zhang, Zigi, Jie Gao, and Fabio Ciravegna
2018 “SemRe-Rank: Incorporating Semantic Relatedness to Improve Automatic Term Extraction Using Personalized PageRank.” ([URL]) Accessed 7 January 2019. DOI logo
Cited by

Cited by 4 other publications

Amjadian, Ehsan, Nicholas Prayogo, Serena McDonnell, Cathal Smyth & Muhammad Rizwan Abid
2021. 2021 IEEE Aerospace Conference (50100), ► pp. 1 ff. DOI logo
Ivanović, Tanja, Ranka Stanković, Branislava Šandrih Todorović & Cvetana Krstev
2022. Corpus-based bilingual terminology extraction in the power engineering domain. Terminology. International Journal of Theoretical and Applied Issues in Specialized Communication 28:2 ► pp. 228 ff. DOI logo
Tran, Hanh Thi Hong, Matej Martinc, Antoine Doucet & Senja Pollak
2022. Can Cross-Domain Term Extraction Benefit from Cross-lingual Transfer?. In Discovery Science [Lecture Notes in Computer Science, 13601], ► pp. 363 ff. DOI logo
Tran, Hanh Thi Hong, Matej Martinc, Andraz Pelicon, Antoine Doucet & Senja Pollak
2022. Ensembling Transformers for Cross-domain Automatic Term Extraction. In From Born-Physical to Born-Virtual: Augmenting Intelligence in Digital Libraries [Lecture Notes in Computer Science, 13636], ► pp. 90 ff. DOI logo

This list is based on CrossRef data as of 8 april 2024. Please note that it may not be complete. Sources presented here have been supplied by the respective publishers. Any errors therein should be reported to them.