Semantically Motivated Hebrew Verb-Noun Multi-Word Expressions Identification

What it is about

The paper decides, for candidate Hebrew bigrams and trigrams that pair a verb with a noun, whether they are multi-word expressions (VN-MWE) or not. The authors take candidates from four MILA corpora (Knesset, Haaretz, TheMarker and Arutz 7), keep only the 553 that two annotators labelled the same way (kappa 0.59; 306 MWEs, 247 non-MWEs), and describe each with 206 features in three sets. The linguistic set covers POS patterns, prefixes and constituent order; the statistical set covers frequencies and association measures such as PMI and log-likelihood; the semantic set compares the two words in five vector spaces (HAL, COALS, random indexing, reflective random indexing and word embeddings). With a random forest and 10-fold cross-validation, the semantic set alone reaches 77.4% accuracy, against 73.96% for the linguistic set and 72.51% for the statistical one. All three sets together reach 80.47% (F 0.795). Among the semantic spaces, the order-sensitive HAL space performs best (75.04%). The main errors are light verbs (such as "get information") and domain-frequent pairs.

Ideas

• I1. A light-verb list for the MWE step: the false positives came from light verbs, which pair freely with many nouns and so look like collocations. A table of Hebrew light verbs (for example la-ʿasot, "to do") marks a verb-noun pair as light, so that it is checked separately before it is called an expression.
• I2. Constituent order as a rule: the authors report that 82% of their VN-MWEs do not allow the order of the two words to change, and 87% have non-compositional syntax. In a UD tree, a verb with an object whose order cannot change, and whose pair is in the lexicon, is an MWE candidate. Implement the rule and measure it on a gold set.
• I3. An order-sensitive co-occurrence count: HAL, which counts neighbours by side and distance, was the best semantic space here, and the authors link this to word order. A count of this kind over the Mova corpus gives a feature for verb-noun pairs in the frames of world.

For Mova

I1 goes into 05. The verb: system, binyanim, tense and use. I2 goes into 7. Syntax as an MWE rule over the parser output. I3 is a feature for the frames in world. The 553-item labelled set, if obtained, is a test set for I2 and I3.

Cite

The paper itself, not this card. BibTeX from the library's record of the work.

@inproceedings{liebeskind2016semantically,
  title = {{Semantically Motivated Hebrew Verb-Noun Multi-Word Expressions Identification}},
  author = {Liebeskind, Chaya and HaCohen-Kerner, Yaakov},
  booktitle = {Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers},
  year = {2016},
  url = {https://aclanthology.org/C16-1118/}
}

References

47 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Meni Adler. 2007. Hebrew Morphological Disambiguation: An Unsupervised Stochastic Word-based Approach. Ph.D. thesis, Ben-Gurion University of the Negev. find
2. Hassan Al-Haj and Shuly Wintner. 2010. Identifying multi-word expressions by leveraging morphological and syntactic idiosyncrasy. In Proceedings of the 23rd International Conference on Computational Linguistics (Coling 2010), pages 10–18, Beijing, China, August. Coling 2010 Organizing Committee. find
3. Hassan Al-Haj. 2009. Hebrew multiword expressions: Linguistic properties, lexical representation, morphological processing, and automatic acquisition. Ph.D. thesis, University of Haifa. find
4. Timothy Baldwin. 2005. Deep lexical acquisition of verb-particle constructions. 19(4):398–414, October. Comput. ↗
5. Speech Lang., Roy Bar-haim, Khalil Sima’an, and Yoad Winter. 2008. Part-of-speech tagging of modern hebrew text. Natural Language Engineering, 14(2):223–251, April. ↗
6. Marco Baroni and Roberto Zamparelli. 2010. Nouns are vectors, adjectives are matrices: Representing adjective-noun constructions in semantic space. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pages 1183–1193. Association for Computational Linguistics. find
7. Eduard Bejcek, Pavel Stranák, and Pavel Pecina. 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. Chris Biemann and Eugenie Giesbrecht. 2011. Distributional semantics and compositionality 2011: Shared task description and results. In Proceedings of the workshop on distributional semantics and compositionality, pages 21–28. Association for Computational Linguistics. find
9. Dhouha Bouamor, Nasredine Semmar, and Pierre Zweigenbaum. 2012. Identifying bilingual multi-word expressions for statistical machine translation. In LREC, pages 674–679. find
10. Siham Boulaknadel, Be’atrice Daille, and Driss Aboutajdine. 2008. A multi-word term extraction program for arabic language. In LREC, pages 1485–1488. European Language Resources Association. find
11. Daoud Clarke. 2009. Context-theoretic semantics for natural language: an overview. In Proceedings of the Workshop on Geometrical Models of Natural Language Semantics, pages 112–119. Association for Computational Linguistics. find
12. Trevor Cohen, Roger Schvaneveldt, and Dominic Widdows. 2010. Reflective random indexing and indirect inference: A scalable method for discovery of implicit connections. Journal of biomedical informatics, 43(2):240– 256. ↗
13. J. Cohen. 1960. A Coefficient of Agreement for Nominal Scales. Educational and Psychological Measurement, 20(1):37. ↗
14. Paul Deane. 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
15. Gaël Dias, Sylvie Guilloré, and JG Pereira Lopes. 1999. Language independent automatic acquisition of rigid multiword units from unrestricted text corpora. Traitement Automatique des Langues Naturelles, Institut dE-tudes Scientifiques, Cargèse, France, pages 333–339. find
16. Meghdad Farahmand and Joakim Nivre. 2015. Modeling the statistical idiosyncrasy of multiword expressions. In Proceedings of NAACL-HLT, pages 34–38. find
17. Afsaneh Fazly and Suzanne Stevenson. 2006. Automatically constructing a lexicon of verb phrase idiomatic combinations. In Proceedings of the 11th Conference of the European Chapter of the Association for Computational Linguistics (EACL), pages 337–344, Trento Italy. find
18. Spence Green, Marie-Catherine de Marneffe, and Christopher D. Manning. 2013. Parsing models for identifying multiword expressions. Computational Linguistics, 39(1):195–227, March. ↗
19. Edward Grefenstette and Mehrnoosh Sadrzadeh. 2011. Experimental support for a categorical compositional distributional model of meaning. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 1394–1404. Association for Computational Linguistics. ↗
20. Emiliano Guevara. 2011. Computing semantic compositionality in distributional semantics. In Proceedings of the Ninth International Conference on Computational Semantics, IWCS ’11, pages 135–144, Stroudsburg, PA, USA. Association for Computational Linguistics. find
21. Mark Hall, Eibe Frank, Geoffrey Holmes, Bernhard Pfahringer, Peter Reutemann, and Ian H. Witten. 2009. The weka data mining software: An update. SIGKDD Explor. Newsl., 11(1):10–18, November. ↗
22. M. Hall. 1998. Correlation-based feature subset selection for machine learning. Ph.D. thesis, Department of Computer Science, University of Waikato, Hamilton, New Zealand. find
23. E. B. Hunt, J. Marin, and P. J. Stone. 1966. Experiments in Induction. Academic Press, New York. find
24. Alon Itai and Shuly Wintner. 2008. Language resources for hebrew. Language Resources and Evaluation, 42(1):75–98. ↗
25. Ray Jackendoff. 1997. The architecture of the language faculty. Number 28. MIT Press. find
26. John S. Justeson and Slava M. Katz. 1995. Technical terminology: some linguistic properties and an algorithm for identification in text. Natural Language Engineering, 1(1):9–27. ↗
27. Graham Katz and Eugenie Giesbrecht. 2006. Automatic identification of non-compositional multi-word expressions using latent semantic analysis. In Proceedings of the Workshop on Multiword Expressions: Identifying and Exploiting Underlying Properties, pages 12–19. Association for Computational Linguistics. find
28. Lili Kotlerman, Ido Dagan, Idan Szpektor, and Maayan Zhitomirsky-Geffet. 2010. Directional distributional similarity for lexical inference. Natural Language Engineering, 16(4):359–389. ↗
29. J. Richard Landis and Gary G. Koch. 1977. The measurement of observer agreement for categorical data. Biometrics, 33(1):159–174. ↗
30. Chaya Liebeskind and Yaakov HaCohen-Kerner. 2016. A lexical resource of hebrew verb-noun multi-word expressions. In Proceedings of the Tenth International Conference on Language Resources and Evaluation, LREC’16, pages 522–527, Portoroz, Slovenia, may. European Language Resources Association (ELRA). find our card
31. Kevin Lund and Curt Burgess. 1996. Producing high-dimensional semantic spaces from lexical co-occurrence. Behavior Research Methods, Instruments, & Computers, 28(2):203–208. ↗
32. Quinn McNemar. 1947. Note on the sampling error of the difference between correlated proportions or percentages. Psychometrika, 12(2):153–157. ↗
33. Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Advances in neural information processing systems, pages 3111–3119. ↗
34. Pavel Pecina and Pavel Schlesinger. 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
35. Pavel Pecina. 2010. Lexical association measures and collocation extraction. Language Resources and Evaluation, 44:137–158. ↗
36. Douglas L. T. Rohde, Laura M. Gonnerman, and David C. Plaut. 2006. An improved model of semantic similarity based on lexical co-occurence. Communications of the ACM, 8:627–633. find
37. Ivan A. Sag, Timothy Baldwin, Francis Bond, Ann A. Copestake, and Dan Flickinger. 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
38. Magnus Sahlgren. 2005. An introduction to random indexing. In Methods and applications of semantic indexing workshop at the 7th international conference on terminology and knowledge engineering, TKE, volume 5. find
39. Bahar Salehi, Paul Cook, and Timothy Baldwin. 2015. A word embedding approach to predicting the compositionality of multiword expressions. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 977–983. find
40. Livnat Herzig Sheinfux, Tali Arad Greshler, Nurit Melnik, and Shuly Wintner. 2015. Hebrew verbal multi-word expressions. In Proceedings of the 22nd international conference on Head-Driven Phrase Structure Grammar (HPSG 2015), pages 123–136. ↗
41. Richard Socher, Brody Huval, Christopher D Manning, and Andrew Y Ng. 2012. Semantic compositionality through recursive matrix-vector spaces. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 1201–1211. Association for Computational Linguistics. find
42. Caroline Sporleder and Linlin Li. 2009. Unsupervised recognition of literal and non-literal use of idiomatic expressions. In Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics, pages 754–762. Association for Computational Linguistics. find
43. Yulia Tsvetkov and Shuly Wintner. 2012. Extraction of multi-word expressions from small parallel corpora. Natural Language Engineering, 18(04):549–573. ↗
44. Yulia Tsvetkov and Shuly Wintner. 2014. Identification of multiword expressions by combining multiple linguistic information sources. Computational Linguistics, 40(2):449–468. ↗
45. Julie Weeds and David Weir. 2003. A general framework for distributional similarity. In Proceedings of the 2003 conference on Empirical methods in natural language processing, pages 81–88. Association for Computational Linguistics. find
46. Ian H. Witten and Eibe Frank. 2005. Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems). Morgan Kaufmann Publishers Inc., San Francisco, CA, USA. find
47. Shlomo Yona and Shuly Wintner. 2008. A finite-state morphological grammar of hebrew. Natural Language Engineering, 14:173–190, 4. ↗ our card

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2016-liebeskind-semantically-motivated-hebrew-verb-noun/