Elamur Research⌕
☰
home / papers / 2026 / A Comparative Study in Corpus Linguistics Applied to Automatic Terminology Extraction

A Comparative Study in Corpus Linguistics Applied to Automatic Terminology Extraction

Paper · 2026 · Mercè Vàzquez, Sergi Alvarez-Vidal and Antoni Oliver

Summary

Translating specialised terms usually depends on parallel corpora, but these exist only for some languages, domains and genres. Comparable corpora are easier to gather, yet their lack of alignment makes matching equivalents harder. The authors compare three ways of finding term translations in Legislation and Administrative Law for English–Spanish and Catalan–Spanish: parallel corpora alone, comparable corpora alone, and a combined method that uses both types plus word embeddings.

The data come from the DGT Corpus and the DOGC corpus. From each, they derived a 1M-segment parallel subset and a 1M-segment comparable corpus, built by drawing source and target segments from opposite ends of the shuffled data. All experiments run in TBXTools. Evaluation used a terminological thesaurus (a subset of the Catalan IATE glossary) as the gold standard.

The combined method retrieved more terms than either corpus type alone, with the strongest gains for Catalan–Spanish. This matters for less-resourced languages that lack large parallel collections.

Key points

  • Corpora: DGT Corpus (English–Spanish) and the DOGC corpus (Catalan–Spanish), built from Catalan government legislation. Both were deduplicated and shuffled, giving 1M-segment parallel and comparable versions per language pair.
  • Gold standard: a subset of the Catalan IATE glossary with 1,722 terms. Of these, 1,621 have English–Spanish equivalents and 1,232 have Catalan–Spanish equivalents.
  • Terms per subcorpus:
    • English–Spanish: 617 (parallel) and 852 (comparable)
    • Catalan–Spanish: 814 (parallel) and 845 (comparable)
  • Parallel method (TBXTools): for each source term, the tool collects the aligned target segments, runs term extraction on them, and takes the most frequent candidate as the equivalent.
  • Comparable method (TBXTools):
    • Multiword terms are merged into single tokens ("compoundifying", e.g. interest_rate).
    • Target-side candidates are found with statistical term extraction.
    • Embeddings are built for both languages, and the two vector spaces are aligned with vecmap (Artetxe et al., 2018).
    • Results were reported as precision, recall and F1; the exact figures were not in the available text.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Universitat Autònoma de BarcelonaCerdanyola del Vallès · Spain4 works · 9,880 citations🎓Universitat Oberta de CatalunyaBarcelona · Spain3 works

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

Cite

Cite as Mercè Vàzquez, Sergi Alvarez-Vidal and Antoni Oliver. 2026. A Comparative Study in Corpus Linguistics Applied to Automatic Terminology Extraction. Proceedings of the 19th Workshop on Building and Using Comparable Corpora (BUCC).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/2u8zp4nujj25

@inproceedings{vazquez2026comparative,
  title = {{A Comparative Study in Corpus Linguistics Applied to Automatic Terminology Extraction}},
  author = {Mercè Vàzquez, Sergi Alvarez-Vidal and Antoni Oliver},
  booktitle = {Proceedings of the 19th Workshop on Building and Using Comparable Corpora (BUCC)},
  year = {2026},
  doi = {10.63317/2u8zp4nujj25},
  url = {https://doi.org/10.63317/2u8zp4nujj25}
}

References

40 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Aker, A., Paramita, M. and Gaizauskas. R. (2013). Extracting bilingual terminologies from comparable corpora. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (pp 402–411). Sofia, Bulgaria. Association for Computational Linguistics. find
  2. Artetxe, M. Labaka, G. and Agirre. E. (2018). A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (pp 789–798).
  3. Artetxe, M., and Schwenk. H. (2019). Massively multilingual sentence embeddings for zero-shot cross-lingual transfer and beyond. Transactions of the association for computational linguistics, 7, 597–610.
  4. Baisa, V., Ulipová, B. and Cukr. M. (2015). Bilingual terminology extraction in Sketch Engine. 9th Workshop on Recent Advances in Slavonic Natural Language Processing, 61–67. find
  5. Bouamor, D., Semmar, N. and Zweigenbaum. P. (2013). Context vector disambiguation for bilingual lexicon extraction from comparable corpora. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (pp 759–764). find
  6. Castor, A. and Pollux, L. E. (1992). The use of user modelling to guide inference and learning. Applied Intelligence, 2(1):37–53. find
  7. Chiao, Y. C., and Zweigenbaum. P. (2002). Looking for candidate translational equivalents in specialized, comparable corpora. In Proceedings of the 19th International Conference on Computational Linguistics (pp 1–5). Association for Computational Linguistics.
  8. Daille, B., and Morin. E. (2005). French-English terminology extraction from comparable corpora” International Conference on Natural Language Processing, 707–718. find
  9. Berlin, Heidelberg: Springer Berlin Heidelberg. Durán-Muñoz, I. (2019). Methodological Proposal to Build a Corpus-Based Ontology in Terminology” Lingue e Linguaggi, 29, 581–597. find
  10. El-Sappagh, S., Franda, F., Ali, F., and Kwak K. S. (2018). SNOMED CT standard ontology based on the ontology for general medical science. BMC medical informatics and decision making, 18, 1–19. find
  11. Fung, P., and Yee, L. Y. (1998). An IR approach for translating new words from nonparallel, comparable texts. In Proceedings of the 17th International Conference on Computational Linguistics (pp 414–420).
  12. Gaussier, E. (1998). Flow network models for word alignment and terminology extraction from bilingual corpora. In Proceedings of the 17th International Conference on Computational Linguistics (pp 444–450). find
  13. Gornostay, T., Ramm, A., Heid, U., Morin, E., Harastani R., and Planas E. (2012). Terminology Extraction from Comparable Corpora for Latvian. find
  14. HLT 2012: 5th International Conference Human Language Technologies, 66–73. find
  15. Estonia. Gurrutxaga, A., Leturia, I., Saralegi, X., and Vicente, I. S. (2013). Automatic comparable web corpora collection and bilingual terminology extraction for specialized dictionary making. Building and using comparable corpora, 51–75. find
  16. Ha, L. A., Fern, G., Mitkov, R., and Corpas, G. (2008). Mutual bilingual terminology extraction” In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08) (pp 1818–1824). find
  17. Haque, R., Penkale, S., and Way, A. (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) (pp 42–51). find
  18. Haque, R, Hasanuzzaman, Md., and Way, A. (2019). Investigating Terminology Translation in Statistical and Neural Machine Translation: A Case Study on English-to-Hindi and Hindi-to-English. Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019) (pp… find
  19. Varna, Bulgaria. Hazem, A., and Morin, E. (2016). Efficient Data Selection for Bilingual Terminology Extraction from Comparable Corpora. 26th International Conference on Computational Linguistics (COLING), 3401–3411. find
  20. Osaka, Japan. Hazem, A., and Morin, E. (2017). Bilingual word embeddings for bilingual terminology extraction from specialized comparable corpora. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (pp 685–693). find
  21. Koehn, P. (2005). Europarl: A Parallel Corpus for Statistical Machine Translation. The 10th Machine Translation Summit Proceedings of Conference. 79–86. International Association for Machine Translation. find
  22. Kupiec, J. (1993). An algorithm for finding noun phrase correspondences in bilingual corpora. In Proceedings of the 31st Annual Meeting on Association for Computational Linguistics (pp 17–22). Association for Computational Linguistics.
  23. L’Homme, M.-C., Bourigault, D., and Jacquemin, C. (1998). First Workshop on Computational Terminology (COMPUTERM’98), Montréal, Canada. find
  24. Lingpeng, Y., Donghong, J., Guodong, Z., and Yu, N. (2005). Improving Retrieval Effectiveness by Using Key Terms in Top Retrieved Documents. In Losada, D.E., Fernández-Luna, J.M. (Eds.) Advances in Information Retrieval. find
  25. ECIR 2005. Lecture Notes in Computer Science, 3408 (pp 169–184). find
  26. Springer, Berlin, Heidelberg. Macken, L., Lefever, E., and Hoste, V. (2013). ExSIS: Bilingual Terminology Extraction from Parallel Corpora Using Chunk-Based Alignment. Terminology. International Journal of Theoretical and Applied Issues in Specialized Communication, 19(1), 1–30. find
  27. Maynard, D., and Ananiadou, S. (2001). TRUCKS: A model for automatic multi-word term recognition. Journal of Natural Language Processing, 8(1), 101–125. find
  28. Mayorov, V., Andrianov, I., Astrakhantsev, N., Avanesov, V., Kozlov, I., and Turdakov. D. (2015). A High Precision Method for Aspect Extraction in Russian. Computational Linguistics and Intellectual Technologies: Papers from the Annual Conference “Dialogue.”, 2, 34–43. find
  29. Moscow, Russia. McEnery, A., and Xiao, R. Z. (2007). Parallel and comparable corpora: What are they up to. Incorporating corpora: Translation and the linguist. Translating Europe. Multilingual matters, 1–13. find
  30. Michon, E., Crego, J., and Senellart, J. (2020). Integrating Domain Terminology into Neural Machine Translation. In Proceedings of the 28th International Conference on Computational Linguistics (pp 3925–3937). Barcelona, Spain. International Committee on Computational Linguistics. find
  31. Morin, E., and Hazem, A. (2014). Looking at unbalanced specialized comparable corpora for bilingual lexicon extraction. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (pp 1284–1293). find
  32. Moslem, Y., Romani, G., Molaei, M., Kelleher, J. D., Haque, R., and Way, A. (2023). Domain Terminology Integration into Machine Translation: Leveraging Large Language Models. In Proceedings of the 8th Conference on Machine Translation (pp 902–911). Singapore. Association for Computational Linguistic… find
  33. Oliver, A. 2022. El corpus paral·lel del Diari Oficial de la Generalitat de Catalunya. find
  34. Oliver, A., and Vàzquez. M. (2015). TBXTools: A Free, Fast and Flexible Tool for Automatic Terminology Extraction. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (pp 473–479). find
  35. Rapp, R. (1999). Automatic identification of word translations from unrelated English and German corpora. In Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics on Computational Linguistics (pp 519–526).
  36. Rigouts Terryn, A., Hoste, V., and Lefever, E. (2020). In no uncertain terms: a dataset for monolingual and multilingual automatic term extraction from comparable corpora. Language Resources and Evaluation, 54(2), 385–418. find
  37. Rigouts Terryn, A. (2023). Supervised Feature-based Classification Approach to Bilingual Lexicon Induction from Specialised Comparable Corpora. In Proceedings of the Workshop on Computational Terminology in NLP and Translation Studies (ConTeNTS) Incorporating the 16th Workshop on Building and Using… find
  38. Steinberger, R., Eisele A., Klocek, S., Pilos, S. and Schlüter, P. (2013). DGT-TM: A freely available translation memory in 22 languages.
  39. European Commission. Vázquez, M., Oliver, A., and Casademont, E. (2019). Using open data to create the Catalan IATE e-dictionary. Terminology. International Journal of Theoretical and Applied Issues in Specialized Communication, 25(2) (pp. 175– 197). find
  40. Zweigenbaum, P., Sharoff, S., & Rapp, R. (2024). Preface. In Proceedings of the 17th Workshop on Building and Using Comparable Corpora. LREC-COLING-2024. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/vazquez-2026-comparative-study-corpus-linguistics-applied/