Automatic Thesaurus Construction for Modern Hebrew

What it is about

The authors build corpus-based thesauri for Modern Hebrew, a morphologically rich language where taggers and parsers are weak. They use four newspaper and parliamentary corpora (about 42 million tokens in total), a list of 3,362 target terms from Hebrew WordNet with at least five occurrences, and a co-occurrence method (PMI, window of three words on each side, top 50 terms grouped by lemma variants). They compare three levels of term representation (surface form, best lemma from a tagger with about 90% accuracy, and all lemmas), in nine first-order configurations and, with a distributional second-order method, in 27 configurations. The gold standard is Hebrew WordNet, which has low coverage, so a manual evaluation was added. The best first-order setting takes the surface form as candidate and groups variants into lemma clusters afterwards; the default best-lemma setting is significantly worse (p < 0.01). The conclusion is that the usual choose-the-lemma-first pipeline is not optimal for Hebrew.

Ideas

• I1. Count surface forms first and fold morphological variants into lemma groups after ranking, instead of choosing a lemma for each token. This is the "resolve in retrospect" option, and it avoids the tagger error that the paper measures.
• I2. Measure any induced Hebrew lexical relation with the paper's two scores, relative recall and mean average precision, against a gold list. The gold must be a resource whose licence allows testing (see Data and model licences).
• I3. Use a second-order (distributional) similarity only as a test of the lexicon, never as part of the parser, since Mova is rule-based. The paper's lesson for that test is that the comparison is only meaningful with the same term representation on both sides.

For Mova

I1 goes into 8. Lexicon and register as a note on how to build a Hebrew lexicon before the tagger is trusted. I2 and I3 are measurements to run for the Hebrew lexicon. No code is taken from this paper, and the text may not be carried into a release.

Topics: Part-of-speech tagging

Cite

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

@inproceedings{liebeskind2018automatic,
  title = {{Automatic Thesaurus Construction for Modern Hebrew}},
  author = {Liebeskind, Chaya and Dagan, Ido and Schler, Jonathan},
  booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)},
  year = {2018},
  url = {https://aclanthology.org/L18-1229/}
}

References

36 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Bar-haim, R., Sima’an, K., and Winter, Y. (2008). Part-of-speech tagging of modern hebrew text. Natural Language Engineering, 14(2), 223–251. find
2. Bullinaria, J. A., and Levy, J. P. (2012). Extracting semantic representations from word co-occurrence statistics: stop-lists, stemming, and SVD. Behavior research methods, 44(3), 890–907. find
3. Caraballo, S. A. (1999). Automatic construction of a hypernym-labeled noun hierarchy from text. In Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics (pp. 120–126). Association for Computational Linguistics. find
4. Chen, X., Liu, Z., and Sun, M. (2014). A unified model for word sense representation and disambiguation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) (pp. 1025–1035). find
5. Church, K. W., and Hanks, P. (1990). Word association norms, mutual information, and lexicography. Computational linguistics, 16(1), 22–29. find
6. Dunning, T. (1993). Accurate methods for the statistics of surprise and coincidence. Computational linguistics, 19(1), 61–74. find
7. Gasperin, C., Gamallo, P., Agustini, A., Lopes, G., and Lima, V. de. (2001). Using Syntactic Contexts for Measuring Word Similarity. In the Workshop on Semantic Knowledge Acquisition and Categorisation (ESSLI 2001). find
8. Gauch, S., Wang, J., and Rachakonda, S. M. (1999). A corpus analysis approach for automatic query expansion and its extension to multiple databases. ACM Transactions on Information Systems (TOIS), 17(3), 250–269. find
9. Harris, Z. S. (1968). Mathematical Structures of Language. New York, NY, USA: Wiley. find
10. Hindle, D. (1990). Noun classification from predicate-argument structures. In Proceedings of the 28th annual meeting on Association for Computational Linguistics (pp. 268–275). Association for Computational Linguistics. find
11. Irvine, A., and Callison-Burch, C. (2013). Combining bilingual and comparable corpora for low resource machine translation. In Proceedings of the eighth workshop on statistical machine translation (pp. 262– 270). find
12. Itai, A., and Wintner, S. (2008). Language resources for Hebrew. Language Resources and Evaluation, 42(1), 75–98. find
13. Kiela, D., and Clark, S. (2014). A systematic study of semantic vector space model parameters. In Proceedings of the 2nd Workshop on Continuous Vector Space Models and their Compositionality (CVSC) at EACL (pp. 21–30). find
14. Kotlerman, L., Dagan, I., Szpektor, I., and Zhitomirsky-Geffet, M. (2010). Directional distributional similarity for lexical inference. Natural Language Engineering, 16(4), 359–389. find
15. Lapesa, G., and Evert, S. (2014). A Large Scale Evaluation of Distributional Semantic Models: Parameters, Interactions and Model Selection. Transactions of the Association for Computational Linguistics, 2, 531–545. find
16. Liebeskind, C., Dagan, I., and Schler, J. (2012). Statistical Thesaurus Construction for a Morphologically Rich Language. In *SEM 2012: The First Joint Conference on Lexical and Computational Semantics (pp. 59–64). Montréal, Canada. find
17. Lin, D. (1998). Automatic retrieval and clustering of similar words. In Proceedings of the 17th international conference on Computational Linguistics-Volume 2 (pp. 768–774). Association for Computational Linguistics. find
18. Lindén, K., and Piitulainen, J. (2004). Discovering Synonyms and Other Related Words. In S. Ananadiou and P. Zweigenbaum (Eds.), COLING 2004 CompuTerm 2004: 3rd International Workshop on Computational Terminology (pp. 63–70). Geneva, Switzerland. find
19. Melamud, O., Dagan, I., Goldberger, J., Szpektor, I., and Yuret, D. (2014). Proceedings of the Eighteenth Conference on Computational Natural Language Learning (pp. 181–190). Ann Arbor, Michigan: Association for Computational Linguistics. find
20. Pantel, P., and Ravichandran, D. (2004). Automatically labeling semantic classes. In Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics: HLT-NAACL 2004. find
21. Peirsman, Y., Heylen, K., and Speelman, D. (2008). Putting things in order. First and second order context models for the calculation of semantic similarity. In 9es Journées internationales d’Analyse statistique des Données Textuelles (JADT). Lyon, France. find
22. Rapp, R. (2002). The Computation of Word Associations: Comparing Syntagmatic and Paradigmatic Approaches. In COLING (Vol. 1, pp. 1–7). Stroudsburg, PA, USA. find
23. Rapp, R. (2008). The automatic generation of thesauri of related words for English, French, German, and Russian. International Journal of Speech Technology, 11(3–4), 147–156. find
24. Riedl, M., and Biemann, C. (2013). Scaling to Large3 Data: An Efficient and Effective Method to Compute Distributional Thesauri. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, EMNLP 2013, 18-21 October 2013, Grand Hyatt Seattle, Seattle, Washington, USA, A meeting of SIGDAT, a Special Interest Group of the ACL (pp. 884–890). find
25. Ruge, G. (1992). Experiments on Linguistically-Based Term Associations. Information Processing and Management, 28(3), 317–332. find
26. Salton, G., and McGill (Eds.). (1983). Introduction to Modern Information Retrieval. McGraw-Hill. find
27. Schütze, H., and Pedersen, J. O. (1997). A cooccurrence-based thesaurus and two applications to information retrieval. Information Processing and Management, 33(3), 307–318. find
28. Smadja, F., McKeown, K. R., and Hatzivassiloglou, V. (1996). Translating collocations for bilingual lexicons: a statistical approach. Computational Linguistics, 22(1), 1–38. find
29. Weeds, J., and Weir, D. (2003). A general framework for distributional similarity. In Proceedings of the 2003 conference on Empirical methods in natural language processing (pp. 81–88). Association for Computational Linguistics. find
30. Wilcoxon, F. (1945). Individual Comparisons by Ranking Methods. Biometrics Bulletin, 1(6), 80–83. find
31. Yang, Y., Yih, W., and Meek, C. (2015). Wikiqa: A challenge dataset for open-domain question answering. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (pp. 2013– 2018). find
32. Yona, S., and Wintner, S. (2008). A finite-state morphological grammar of hebrew. Natural Language Engineering, 14(2), 173–190. 6. find our card
33. Language Resource References Bentivogli, L., Pianta, E., and Pianesi, F. (2000). Coping with Lexical Gaps when Building Aligned Multilingual Wordnets. In Proceedings of the Second International Conference on Language Resources and Evaluation, LREC 2000, 31 May - June 2, 2000, Athens, Greece. find
34. Fellbaum, C. (1998). WordNet. Wiley Online Library. find
35. Hayoun, A., and Elhadad, M. (2016). The Hebrew FrameNet Project. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016). Portorož, Slovenia: European Language Resources Association (ELRA). find our card
36. Ordan, N., Ilan, B., Ordan, N., and Wintner, S. (2007). S.: Hebrew WordNet: a test case of aligning lexical databases across languages. International Journal of Translation, 19, 39–58. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/lingbulk-2018-liebeskind-automatic-thesaurus-construction-modern-hebrew/