Abstract
This paper presents a method to automatically identify bilingual equivalents of collocations using only monolingual corpora in two languages. The method takes advantage of cross-lingual distributional semantics models mapped into a shared vector space, and of compositional methods to find appropriate translations of non-congruent collocations (e.g., pay attention–prestar atenção in English–Portuguese). This strategy is evaluated in the translation of English–Portuguese and English–Spanish collocations belonging to two syntactic patterns: adjective-noun and verb-object, and compared to other methods proposed in the literature. The results of the experiments performed show that the compositional approach, based on a weighted additive model, behaves better than the other strategies that have been evaluated, and that both the asymmetry and the compositional properties of collocations are captured by the combined vector representations. This paper also contributes with two freely available gold-standard data sets which are useful to evaluate the performance of automatic extraction of multilingual equivalents of collocations.
This research was supported by a 2017 Leonardo Grant for Researchers and Cultural Creators (BBVA Foundation), by Ministerio de Economía, Industria y Competitividad (FFI2016-78299-P), and by the Galician Government (ED431B-2017/01). Marcos Garcia has been funded by a Juan de la Cierva-incorporación grant (IJCI-2016-29598), and Marcos García-Salido by a post-doctoral grant from Xunta de Galicia (ED481D 2017/009). We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPU used for this research.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
In this regard, note that in an adj-noun collocation, the syntactic head is occupied by the base, while in verb-obj collocations the syntactic head is the collocate.
- 2.
It is worth noting that the candidate cobrar atenção, which exists in Brazilian Portuguese with a slightly different meaning, could be selected if we had used more resources from this variety and from other typologies. In our data, mostly composed of corpora from Portugal (besides the Wikipedia, with mixed varieties), this combination has a frequency of only 1.
- 3.
Both the gold-standard data as well as the output of each system can be downloaded at https://github.com/marcospln/bilingual_collocations.
- 4.
This gold-standard includes an average of 3.65 translations for each collocation, but, as discussed in Sect. 4.4, there may be more suitable equivalents for some of them.
- 5.
- 6.
Note that the high precision of the non-compositional method is an evidence of the good performance of the distributional approach and of the cross-lingual mapping, but it does not necessarily imply that collocations are non-compositional.
References
Artetxe, M., Labaka, G., Agirre, E.: 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 (Volume 1: Long Papers), pp. 789–798 (2018)
Baldwin, T., Tanaka, T.: Translation by machine of complex nominals: getting it right. In: Second ACL Workshop on Multiword Expressions: Integrating Processing, pp. 24–31. ACL, Barcelona (2004)
Baroni, M.: Composition in distributional semantics. Lang. Linguist. Compass 7(10), 511–522 (2013)
Baroni, M., Zamparelli, R.: Frege in space: a program of compositional distributional semantics. LiLT (Linguist. Issues Lang. Technol.) 9, 241–346 (2014)
Coecke, B., Sadrzadeh, M., Clark, S.: Mathematical foundations for a compositional distributional model of meaning. Linguist. Anal. 36, 345–384 (2010)
Cordeiro, S., Villavicencio, A., Idiart, M., Ramisch, C.: Unsupervised compositionality prediction of nominal compounds. Am. J. Comput. Linguist. 45(1), 1–57 (2019)
Delpech, E., Daille, B., Morin, E., Lemaire, C.: Extraction of domain-specific bilingual lexicon from comparable corpora: compositional translation and ranking. Proc. COLING 2012, 745–762 (2012)
Fung, P.: A statistical view on bilingual lexicon extraction: from parallel corpora to non-parallel corpora. In: Farwell, D., Gerber, L., Hovy, E. (eds.) AMTA 1998. LNCS (LNAI), vol. 1529, pp. 1–17. Springer, Heidelberg (1998). https://doi.org/10.1007/3-540-49478-2_1
Fung, P., McKeown, K.: Finding terminology translations from non-parallel corpora. In: Fifth Workshop on Very Large Corpora, pp. 192–202. ACL (1997)
Fung, P., Yee, L.Y.: An IR approach for translating new words from nonparallel, comparable texts. In: Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics, Volume 1, pp. 414–420. ACL (1998)
Gamallo, P.: Comparing explicit and predictive distributional semantic models endowed with syntactic contexts. Lang. Resour. Eval. 51(3), 727–743 (2017)
Gamallo, P.: The role of syntactic dependencies in compositional distributional semantics. Corpus Linguist. Linguist. Theory 13(2), 261–289 (2017)
Gamallo, P., Garcia, M.: Unsupervised compositional translation of multiword expressions. In: Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019). ACL, Florence (2019)
Gamallo, P., Garcia, M., Pineiro, C., Martinez-Castaño, R., Pichel, J.C.: LinguaKit: a big data-based multilingual tool for linguistic analysis and information extraction. In: Proceedings of the Fifth International Conference on Social Networks Analysis, Management and Security (SNAMS), pp. 239–244. IEEE (2018)
Garcia, M., García-Salido, M., Alonso-Ramos, M.: Using bilingual word-embeddings for multilingual collocation extraction. In: Proceedings of the 13th Workshop on Multiword Expressions (MWE 2017), pp. 21–30. ACL (2017)
Garcia, M., García-Salido, M., Sotelo, S., Mosqueira, E., Alonso-Ramos, M.: Pay attention when you pay the bills. A multilingual corpus with dependency-based and semantic annotation of collocations. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019). ACL, Florence (2019)
Grefenstette, G.: The world wide web as a resource for example-based machine translation tasks. In: Proceedings of the ASLIB Conference on Translating and the Computer, vol. 21 (1999)
Haruno, M., Ikehara, S., Yamazaki, T.: Learning bilingual collocations by word-level sorting. In: Proceedings of the 16th Conference on Computational Linguistics. COLING 1996, vol. 1, pp. 525–530 (1996)
Hausmann, F.J.: Le dictionnaire de collocations. In: Hausmann, F.J., Reichmann, O., Wiegand, H., Zgusta, L. (eds.) Wörterbücher: ein internationales Handbuch zur Lexikographie. Dictionaries. Dictionnaires, pp. 1010–1019. Mouton De Gruyter, Berlin (1989)
Koehn, P.: EuroParl: a parallel corpus for statistical machine translation. In: Proceedings of the 10th Machine Translation Summit, Phuket, pp. 79–86 (2005)
Kupiec, J.: An algorithm for finding noun phrase correspondences in bilingual corpora. In: Proceedings of the 31st Annual Meeting on Association for Computational Linguistics (ACL 1993), pp. 17–22. ACL (1993)
Lample, G., Conneau, A., Denoyer, L., Ranzato, M.: Unsupervised machine translation using monolingual corpora only. In: Proceedings of the Sixth International Conference on Learning Representations (ICLR 2018) (2018)
Lison, P., Tiedemann, J.: OpenSubtitles2016: extracting large parallel corpora from movie and TV subtitles. In: Calzolari, N., et al. (eds.) Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC 2016), pp. 923–929. European Language Resources Association (ELRA) (2016)
Mel’čuk, I.: Collocations and lexical functions. In: Cowie, A.P. (ed.) Phraseology. Theory, Analysis and Applications, pp. 23–53. Clarendon Press, Oxford (1998)
Mel’čuk, I.: Phraseology in the language, in the dictionary, and in the computer. Yearb. Phraseol. 3(1), 31–56 (2012)
Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. In: Workshop Proceedings of the International Conference on Learning Representations (ICLR 2013) (2013). arXiv preprint arXiv:1301.3781
Mikolov, T., Le, Q.V., Sutskever, I.: Exploiting similarities among languages for machine translation. CoRR abs/1309.4168 (2013)
Mitchell, J., Lapata, M.: Vector-based models of semantic composition. In: Proceedings of ACL 2008: HLT, pp. 236–244. ACL (2008)
Mitchell, J., Lapata, M.: Composition in distributional models of semantics. Cognit. Sci. 34(8), 1388–1429 (2010)
Morin, E., Daille, B.: Revising the compositional method for terminology acquisition from comparable corpora. In: Proceedings of COLING 2012, Mumbai, India, pp. 1797–1810 (2012)
Nesselhauf, N.: The use of collocations by advanced learners of English and some implications for teaching. Appl. Linguist. 24(2), 223–242 (2003)
Rapp, R.: Automatic identification of word translations from unrelated English and German corpora. In: Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics (ACL 1999), pp. 519–526. ACL (1999)
Reddy, S., Klapaftis, I., McCarthy, D., Manandhar, S.: Dynamic and static prototype vectors for semantic composition. In: Proceedings of 5th International Joint Conference on Natural Language Processing, pp. 705–713. Asian Federation of Natural Language Processing (2011)
Rivera, O., Mitkov, R., Pastor, G.: A flexible framework for collocation retrieval and translation from parallel and comparable corpora. In: Proceedings of the Workshop on Multi-word Units in Machine Translation and Translation Technology, pp. 18–25 (2013)
Seretan, V., Wehrli, E.: Collocation translation based on sentence alignment and parsing. In: Actes de la 14e conference sur le traitement automatique des langues naturelles, TALN 2007, pp. 401–410. IRIT Press (2007)
Smadja, F.: How to compile a bilingual collocational lexicon automatically. In: Proceedings of the AAAI Workshop on Statistically-Based NLP Techniques, pp. 57–63. AAAI Press (1992)
Straka, M., Straková, J.: Tokenizing, POS tagging, lemmatizing and parsing UD 2.0 with UDPipe. In: Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pp. 88–99. ACL, August 2017
Tanaka, T., Baldwin, T.: Noun-noun compound machine translation a feasibility study on shallow processing. In: Proceedings of the ACL 2003 Workshop on Multiword Expressions: Analysis, Acquisition and Treatment, pp. 17–24. ACL (2003)
Taslimipoor, S., Mitkov, R., Corpas Pastor, G., Fazly, A.: Bilingual contexts from comparable corpora to mine for translations of collocations. In: Gelbukh, A. (ed.) CICLing 2016. LNCS, vol. 9624, pp. 115–126. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-75487-1_10
Upadhyay, S., Faruqui, M., Dyer, C., Roth, D.: Cross-lingual models of word embeddings: an empirical comparison. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1661–1670 (2016)
Vargas, N., Ramisch, C., Caseli, H.: Discovering light verb constructions and their translations from parallel corpora without word alignment. In: Proceedings of the 13th Workshop on Multiword Expressions (MWE 2017), pp. 91–96. ACL (2017)
Weir, D., Weeds, J., Reffin, J., Kober, T.: Aligning packed dependency trees: a theory of composition for distributional semantics. Am. J. Comput. Linguist. 42(4), 727–761 (2016)
Wu, C.C., Chang, J.S.: Bilingual collocation extraction based on syntactic and statistical analyses. In: Proceedings of the 15th Conference on Computational Linguistics and Speech Processing, pp. 1–20. Association for Computational Linguistics and Chinese Language Processing (2003)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Garcia, M., García-Salido, M., Alonso-Ramos, M. (2019). Weighted Compositional Vectors for Translating Collocations Using Monolingual Corpora. In: Corpas Pastor, G., Mitkov, R. (eds) Computational and Corpus-Based Phraseology. EUROPHRAS 2019. Lecture Notes in Computer Science(), vol 11755. Springer, Cham. https://doi.org/10.1007/978-3-030-30135-4_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-30135-4_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30134-7
Online ISBN: 978-3-030-30135-4
eBook Packages: Computer ScienceComputer Science (R0)