A Lexical Resource of Hebrew Verb-Noun Multi-Word Expressions

What it is about

The paper presents a hand-built resource of 505 Hebrew verb-noun multi-word expressions (247 two-word and 258 three-word), collected from five web sources: a Hebrew dictionary, Wiktionary idiom categories (modern, Talmudic and Biblical), and another free dictionary. Two annotators judged 150 candidates, with a Cohen's kappa of 0.86. The expressions are then classed by morphological, syntactic and semantic properties. In a sample of 100 entries, 92% are highly idiomatic, 82% do not allow a change of constituent order, and 87% are non-compositional. The most frequent part-of-speech pattern is verb plus noun (16%), followed by verb plus preposition (about 10%). An automatic tagger mislabels about 20% of the entries, mostly by reading a verb as a noun. The resource is meant as seed or training data for finding such expressions automatically.

Ideas

• I1. A test for the parser: take the 100-entry sample and check, for each entry, whether the parser gives the verb and the noun the expected tags and dependency. The tagger errors the paper lists (a verb read as a noun, a noun read as a proper name) become a fixed confusion set to measure against.
• I2. A candidate rule: a verb followed by a noun, or by a noun and a preposition, with no literal reading for the noun, is flagged as a possible expression rather than read literally. The pattern counts in the paper give the order in which to write these rules.
• I3. Store the frozen form, not only the lemma. The paper keeps a lemmatised form and the POS pattern, but some expressions do not inflate (a noun that stays in one form), so a lemma-only match would miss them. Keep the surface form as well.

For Mova

I1 is a test set for the Modern Hebrew analysis in 11. Modern Hebrew in Universal Dependencies; Mova does not parse Modern Hebrew yet, so it is a plan. I2 goes into 05. The verb: system, binyanim, tense and use and into the idiom matching in prag. I3 goes into the lexicon notes in 8. Lexicon and register.

Topics: Part-of-speech tagging

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.63317/5gagnwddavw5

@inproceedings{liebeskind2016lexical,
  title = {{A Lexical Resource of Hebrew Verb-Noun Multi-Word Expressions}},
  author = {Liebeskind, Chaya and HaCohen-Kerner, Yaakov},
  booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)},
  year = {2016},
  doi = {10.63317/5gagnwddavw5},
  url = {https://doi.org/10.63317/5gagnwddavw5}
}

References

29 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Adler, M., Goldberg, Y., Gabay, D., and Elhadad, M. (2008). Unsupervised lexicon-based resolution of unknown words for full morphological analysis. In Proceedings of ACL-08: HLT, pages 728–736, Columbus, Ohio, June. Association for Computational Linguistics. find
2. Adler, M. (2007). Hebrew Morphological Disambiguation: An Unsupervised Stochastic Word-based Approach. Ph.D. thesis. find
3. Al-Haj, H. and Wintner, S. (2010). Identifying multi-word expressions by leveraging morphological and syntactic idiosyncrasy. In Proceedings of the 23rd International Conference on Computational Linguistics, COLING ’10, pages 10–18, Stroudsburg, PA, USA. Association for Computational Linguistics. find
4. Al-Haj, H., Itai, A., and Wintner, S. (2014). Lexical representation of multiword expressions in morphologically-complex languages. International Journal of Lexicography, 27(2):130–170. ↗
5. Al-Haj, H. (2009). Hebrew multiword expressions: Linguistic properties, lexical representation, morphological processing, and automatic acquisition. Ph.D. thesis, University of Haifa. find
6. Baldwin, T. (2005). Deep lexical acquisition of verb-particle constructions. Comput. Speech Lang., 19(4):398–414, October. ↗
7. Bejcek, E., Stranák, P., and Pecina, P. (2013). Syntactic identification of occurrences of multiword expressions in text using a lexicon with dependency structures. In Proceedings of the 9th Workshop on Multiword Expressions, pages 106–115. find
8. Biber, D., Johansson, S., Leech, G., Conrad, S., Finegan, E., and Quirk, R. (1999). Longman grammar of spoken and written English, volume 2. MIT Press. find
9. Boulaknadel, S., Daille, B., and Aboutajdine, D. (2008). A multi-word term extraction program for arabic language. In LREC. European Language Resources Association. find
10. Breidt, E. (1996). Extraction of vn-collocations from text corpora: A feasibility study for german. arXiv preprint cmp-lg/9603006. find
11. Dandapat, S., Mitra, P., and Sarkar, S. (2006). Statistical investigation of bengali noun-verb (nv) collocations as multi-word-expressions. the Proceedings of MSPIL, pages 230–233. find
12. Deane, P. (2005). A nonparametric method for extraction of candidate phrasal terms. In Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, pages 605–613. Association for Computational Linguistics. find
13. Dias, G., Guilloré, S., and Lopes, J. P. (1999). Language independent automatic acquisition of rigid multiword units from unrestricted text corpora. Traitement Automatique des Langues Naturelles, Institut dEtudes Scientifiques, Cargèse, France, pages 333–339. find
14. Fadida, H., Itai, A., and Wintner, S. (2014). A hebrew ver-bcomplement dictionary. Language Resources and Evaluation, 48(2):249–278. find
15. Farahmand, M. and Nivre, J. (2015). Modeling the statistical idiosyncrasy of multiword expressions. In Proceedings of NAACL-HLT, pages 34–38. find
16. Fazly, A. and Stevenson, S. (2007). Distinguishing subtypes of multiword expressions using linguistically-motivated statistical measures. In Proceedings of the Workshop on A Broader Perspective on Multiword Expressions, pages 9–16. Association for Computational Linguistics. find
17. Fazly, A. (2007). Automatic Acquisition of Lexical Knowledge about Multiword Predicates. Ph.D. thesis, University of Toronto. find
18. Green, S., de Marneffe, M.-C., and Manning, C. D. (2013). Parsing models for identifying multiword expressions. Computational Linguistics, 39(1):195–227, March. ↗
19. Landis, J. R. and Koch, G. G. (1977). The measurement of observer agreement for categorical data. Biometrics, 33(1):159–174. ↗
20. Pecina, P. and Schlesinger, P. (2006). Combining association measures for collocation extraction. In Proceedings of the COLING/ACL on Main Conference Poster Sessions, COLING-ACL ’06, pages 651–658, Stroudsburg, PA, USA. Association for Computational Linguistics. find
21. Ramisch, C., de Medeiros Caseli, H., Villavicencio, A., Machado, A., and Finatto, M. J. (2010). A hybrid approach for multiword expression identification. In Thiago Alexandre Salgueiro Pardo, et al., editors, PRO-POR, volume 6001 of Lecture Notes in Computer Science, pages 65–74. Springer. find
22. Sag, I. A., Baldwin, T., Bond, F., Copestake, A. A., and Flickinger, D. (2002). Multiword expressions: A pain in the neck for nlp. In Proceedings of the Third International Conference on Computational Linguistics and Intelligent Text Processing, CICLing ’02, pages 1–15, London, UK, UK. Springer-Verlag. find our card
23. Sangati, F. and van Cranenburgh, A. (2015). Multiword expression identification with recurring tree fragments and association measures. In Proceedings of NAACL-HLT, pages 10–18. find
24. Schneider, N., Danchik, E., Dyer, C., and Smith, N. A. (2014). Discriminative lexical semantic segmentation with gaps: running the mwe gamut. Transactions of the Association for Computational Linguistics, 2:193–206. ↗
25. Todirascu, A. and Navlea, M. (2015). Aligning verb+noun collocation to improve a french-romanian statistical mt system. Multi-word Units in Machine Translation and Translation Technology. find
26. Tsvetkov, Y. and Wintner, S. (2012). Extraction of multiword expressions from small parallel corpora. Natural Language Engineering, 18(04):549–573. find
27. Tsvetkov, Y. and Wintner, S. (2014). Identification of multiword expressions by combining multiple linguistic information sources. Computational Linguistics, 40(2):449–468. ↗
28. Venkatapathy, S. and Joshi, A. K. (2004). Recognition of multi-word expressions: A study of verb-noun (vn) collocations. In Proceedings of the International Conference on Natural Language Processing, volume 2004. find
29. Zhang, Y., Kordoni, V., Villavicencio, A., and Idiart, M. (2006). Automated multiword expression prediction for grammar engineering. In Proceedings of the Workshop on Multiword Expressions: Identifying and Exploiting Underlying Properties, MWE ’06, pages 36–44, Stroudsburg, PA, USA. Association for Computational Linguistics. # Part-of-speech pattern Relative freq. 16.04% 9.9% 8.91% 8.71% 2.77% 2.57% 2.18% 1 2 3 4 5 6 7 verb+noun verb+preposition noun verb+preposition+definiteArticle noun verb+preposition+noun verb+noun+preposition noun verb+preposition definiteArticle noun verb+preposition noun+noun Table 1: The most frequent POS patterns in our lexical resource (the plus sign separates between the MWE’s constituents) Tagging error Relative freq. 41.3% Examples # find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/lingbulk-2016-liebeskind-lexical-resource-hebrew-verb-noun/