Mova0.5 pre-release⌕
☰
home / docs / papers / Modern Hebrew / Word Segmentation, Unknown-word Resolution, and Morphological Agreement in a Hebrew Parsing System

Word Segmentation, Unknown-word Resolution, and Morphological Agreement in a Hebrew Parsing System

What it is about

The paper builds a constituency parser for Modern Hebrew on the BerkeleyParser (PCFG with latent annotations) and extends it for a small treebank of 6,220 sentences. Three parts. (1) Word segmentation and parsing are done jointly over a lattice of possible segmentations, which beats a pipeline clearly: on the dev set, gold-segmentation parsing reaches F1 about 83.6 and the pipeline about 77.2 (5 split-merge cycles), so segmentation errors are costly. (2) A lexicon-based analyser (about 25,000 lemmas, extended by a learned guesser for unknown words) and an HMM tagger trained by EM on about 70M words are used to add coverage; the lexicon uses a lexical tag set that does not map simply to the treebank's syntactic tags. (3) Gender, number and person agreement are applied as a filter on the parser's output, which fixes a few agreement errors without new ones. The paper ends with the claim that the approach extends to other morphologically rich languages.

Ideas

For Mova

I1 goes into tools/hbo (segmenter output as a lattice before gparse) and into Syntax: the clause and the sentence for the joint treatment. I2 goes into Syntax: the clause and the sentence for Biblical agreement and into 7. Syntax for Modern Hebrew. I3 goes into 11. Modern Hebrew in Universal Dependencies and 05b. Verb paradigms: the strong verb in seven binyanim and the weak roots for the participle case. The paper is NC: only this summary is kept, and nothing from it is built into a release.

Topics: Part-of-speech tagging

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.1162/coli_a_00137

@article{goldberg2013word,
  title = {{Word Segmentation, Unknown-word Resolution, and Morphological Agreement in a Hebrew Parsing System}},
  author = {Goldberg, Yoav and Elhadad, Michael},
  journal = {Computational Linguistics},
  year = {2013},
  doi = {10.1162/coli\_a\_00137},
  url = {https://doi.org/10.1162/coli_a_00137}
}

References

57 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Abeillé, Anne, Lionel Clément, and François Toussenel. 2003. Building a treebank for French. In A. Abeillé, editor. Treebanks: Building and Using Parsed Corpora. Springer, Berlin, pages 165–188. find
  2. Adler, Meni. 2001. Hidden Markov model for Hebrew part-of-speech tagging. Master’s thesis, Ben-Gurion University of the Negev. find
  3. Adler, Meni. 2007. Hebrew Morphological Disambiguation: An Unsupervised Stochastic Word-based Approach. Ph.D. thesis, Ben-Gurion University of the Negev. find
  4. Adler, Meni and Michael Elhadad. 2006. An unsupervised morpheme-based HMM for Hebrew morphological disambiguation. In Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, pages 665–672, Sydney. find our card
  5. Adler, Meni, Yoav Goldberg, David Gabay, and Michael Elhadad. 2008a. Unsupervised lexicon-based resolution of unknown words for full morphological analysis. In Proceedings of ACL-08: HLT, pages 728–736, Columbus, OH. find
  6. Adler, Meni, Yael Netzer, David Gabay, Yoav Goldberg, and Michael Elhadad. 2008b. Tagging a Hebrew corpus: The case of participles. In Proceedings of LREC 2008, pages 3167–3174, Marrakech. find our card
  7. Attia, Mohammed, Jennifer Foster, Deirdre Hogan, Joseph Le Roux, Lamia Tounsi, and Josef van Genabith. 2010. Handling unknown words in statistical latent-variable parsing models for Arabic, English and French. In Proceedings of the NAACL HLT 2010 First Workshop on Statistical Parsing of Morphologically-Rich Languages, pages 67–75, Los Angeles, CA. find
  8. Bar-Haim, Roy, Khalil Sima’an, and Yoad Winter. 2005. Choosing an optimal architecture for segmentation and POS-tagging of Modern Hebrew. In Proceedings of the ACL Workshop on Computational Approaches to Semitic Languages, pages 39–46, Ann Arbor, MI. find our card
  9. Bar-Haim, Roy, Khalil Sima’an, and Yoad Winter. 2008. Part-of-speech tagging of Modern Hebrew text. Natural Language Engineering, 14(2):223–251. find
  10. Billott, Sylvie and Bernard Lang. 1989. The structure of shared forests in ambiguous parsing. In Proceedings of the 27th Annual Meeting of the Association for Computational Linguistics, pages 143–151, Vancouver. find
  11. BGU Computational Linguistics Group. 2008. Hebrew morphological tagging guidelines. Technical report, Ben Gurion University of the Negev. find
  12. Cai, Shu, David Chiang, and Yoav Goldberg. 2011. Language-independent parsing with empty elements. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 212–216, Portland, OR. find
  13. Candito, Marie and Benoı̂t Crabbé. 2009. Improving generative statistical parsing with semi-supervised word clustering. In Proceedings of the 11th International Conference on Parsing Technologies (IWPT’09), pages 138–141, Paris. find
  14. Candito, Marie, Benoı̂t Crabbé, and Djamé Seddah. 2009. On statistical parsing of French with supervised and semi-supervised strategies. In EACL 2009 Workshop Grammatical Inference for Computational Linguistics, pages 49–57, Athens. find
  15. Chappelier, J., M. Rajman, R. Aragues, and A. Rozenknop. 1999. Lattice parsing for speech recognition. In Sixth Conference sur le Traitement Automatique du Langage Naturel (TANL’99), pages 95–104, Cargése. find
  16. Charniak, Eugene and Mark Johnson. 2005. Coarse-to-fine n-best parsing and maxent discriminative reranking. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL’05), pages 173–180, Ann Arbor, MI. find our card
  17. Cohen, Shay B. and Noah A. Smith. 2007. Joint morphological and syntactic disambiguation. In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pages 208–217, Prague. find
  18. Collins, Michael and Terry Koo. 2005. Discriminative reranking for natural language parsing. Computational Linguistics, 31(1):25–69. find our card
  19. Crabbé, Benoı̂t and Marie Candito. 2008. Expériences d’analyses syntaxique statistique du français. In Proceedings of TALN, pages 45–54, Avignon. find
  20. Dantzig, G. B. and P. Wolfe. 1960. Decomposition principle for linear programs. Operations Research, 8:101–111. find
  21. Falk, Yehuda N. 2001. Lexical-Functional Grammar: An Introduction to Parallel Constraint-Based Syntax. CSLI Publications, Stanford, CA. find
  22. Glinert, Lewis. 1989. The Grammar of Modern Hebrew. Cambridge University Press. find
  23. Goldberg, Yoav, Meni Adler, and Michael Elhadad. 2008. EM can find pretty good HMM POS-taggers (when given a good start). In Proceedings of ACL-08: HLT, pages 746–754, Columbus, OH. find
  24. Goldberg, Yoav and Michael Elhadad. 2011. Joint Hebrew segmentation and parsing using a PCFGLA lattice parser. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 704–709, Portland, OR. find our card
  25. Goldberg, Yoav and Reut Tsarfaty. 2008. A single generative model for joint morphological segmentation and syntactic parsing. In Proceedings of ACL-08: HLT, pages 371–379, Columbus, OH. find
  26. Goldberg, Yoav, Reut Tsarfaty, Meni Adler, and Michael Elhadad. 2009. Enhancing unlexicalized parsing performance using a wide coverage lexicon, fuzzy tag-set mapping, and EM-HMM-based lexical probabilities. In Proceedings of the 12th Conference of the European Chapter of the ACL (EACL 2009), pages 327–335, Athens. find
  27. Green, Spence and Christopher D. Manning. 2010. Better Arabic parsing: Baselines, evaluations, and analysis. In Proceedings of the 23rd International Conference on Computational Linguistics (Coling 2010), pages 394–402, Beijing. find our card
  28. Guthmann, Noemie, Yuval Krymolowski, Adi Milea, and Yoad Winter. 2009. Automatic annotation of morpho-syntactic dependencies in a Modern Hebrew Treebank. In Proceedings of the 1st Workshop on Treebanks and Linguistic Theories (TLT), pages 1–12, Groningen. find
  29. Hall, Keith. 2005. Best-first Word-lattice Parsing: Techniques for Integrated Syntactic Language Modeling. Ph.D. thesis, Brown University. find
  30. Huang, Zhongqiang and Mary Harper. 2009. Self-training PCFG grammars with latent annotations across languages. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pages 832–841, Singapore. find
  31. Itai, Alon and Shuly Wintner. 2008. Language resources for Hebrew. Language Resources and Evaluation, 42(1):75–98. find
  32. Jiang, Wenbin, Liang Huang, and Qun Liu. 2009. Automatic adaptation of annotation standards: Chinese word segmentation and POS tagging—a case study. In Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP, pages 522–530, Suntec. find
  33. Johnson, Mark. 1998. PCFG models of linguistic tree representations. Computational Linguistics, 24:613–632. find
  34. Klein, Dan and Christopher D. Manning. 2003. Accurate unlexicalized parsing. In Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics, pages 423–430, Sapporo. find our card
  35. Lang, Bernard. 1974. Deterministic techniques for efficient non-deterministic parsers. In J. Loeckx, editor, Automata, Languages and Programming, volume 14 of Lecture Notes in Computer Science. Springer, Berlin Heidelberg, pages 255–269. find
  36. Lang, Bernard. 1988. Parsing incomplete sentences. In Proceedings of COLING, pages 365–371, Budapest. find
  37. Matsuzaki, Takuya, Yusuke Miyao, and Jun’ichi Tsujii. 2005. Probabilistic CFG with latent annotations. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL’05), pages 75–82, Ann Arbor, MI. find
  38. Netzer, Yael, Meni Adler, David Gabay, and Michael Elhadad. 2007. Can you tag the modal? You should! In Proceedings of the 2007 Workshop on Computational Approaches to Semitic Languages: Common Issues and Resources, pages 57–64, Prague. find
  39. Petrov, Slav. 2009. Coarse-to-Fine Natural Language Processing. Ph.D. thesis, University of California at Berkeley. find
  40. Petrov, Slav. 2010. Products of random latent variable grammars. In Proceedings of NAACL, pages 19–27, Los Angeles, CA. find
  41. Petrov, Slav, Leon Barrett, Romain Thibaux, and Dan Klein. 2006. Learning accurate, compact, and interpretable tree annotation. In Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, pages 433–440, Sydney. find our card
  42. Petrov, Slav and Dan Klein. 2007. Improved inference for unlexicalized parsing. In Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Proceedings of the Main Conference, pages 404–411, Rochester, NY. find
  43. Petrov, Slav and Dan Klein. 2008. Parsing German with latent variable grammars. In Proceedings of the Workshop on Parsing German, pages 33–39, Columbus, OH. find
  44. Pollard, Carl and Ivan A. Sag. 1994. Head-driven phrase structure grammar. University of Chicago Press. find
  45. Prescher, Detlef. 2005. Inducing head-driven PCFGs with latent heads: Refining a treebank grammar for parsing. In Proceedings of the European Conference on Machine Learning (ECML), pages 292–304, Porto. find
  46. Rush, Alexander M, David Sontag, Michael Collins, and Tommi Jaakkola. 2010. On dual decomposition and linear programming relaxations for natural language processing. In Proceedings of EMNLP, pages 1–11, Cambridge, MA. find
  47. Sima’an, Khalil. 1996. Computational complexity of probabilistic disambiguation by means of tree grammars. In Proceedings of COLING, pages 1175–1180, Copenhagen. find
  48. Sima’an, Khalil. 1999. Learning Efficient Disambiguation. Ph.D. thesis, ILLC Dissertation Series, University of Amsterdam. find
  49. Sima’an, Khalil, Alon Itai, Yoad Winter, Alon Altman, and Noa Nativ. 2001. Building a tree-bank of Modern Hebrew text. Traitement Automatique des Langues, 42(2):1–32. find
  50. Smith, Noah A., David A. Smith, and Roy W. Tromble. 2005. Context-based morphological disambiguation with random fields. In Proceedings of EMNLP, pages 475–482, Vancouver. find
  51. Tsarfaty, Reut. 2006a. Integrated morphological and syntactic disambiguation for Modern Hebrew. In Proceedings of the COLING/ACL 2006 Student Research Workshop, pages 49–54, Sydney. find our card
  52. Tsarfaty, Reut. 2006b. The Interplay of Syntax and Morphology in Building Parsing Models for Modern Hebrew. In Proceedings of ESSLI Student Session, pages 263–274, Malaga. find
  53. Tsarfaty, Reut. 2010. Relational-Realizational Parsing. Ph.D. thesis, ILLC Dissertation Series, University of Amsterdam. find
  54. Tsarfaty, Reut and Khalil Sima’an. 2007. Three-dimensional parametrization for parsing morphologically rich languages. In Proceedings of the Tenth International Conference on Parsing Technologies, pages 156–167, Prague. find
  55. Tsarfaty, Reut and Khalil Sima’an. 2008. Relational-realizational parsing. In Proceedings of CoLING, pages 889–896, Manchester. find
  56. Tsarfaty, Reut and Khalil Sima’an. 2010. Modeling morphosyntactic agreement in constituency-based parsing of Modern Hebrew. In Proceedings of the NAACL HLT 2010 First Workshop on Statistical Parsing of Morphologically-Rich Languages, pages 40–48, Los Angeles, CA. find our card
  57. Tsarfaty, Reut, Khalil Sima’an, and Remko Scha. 2009. An alternative to head-driven approaches for parsing a (relatively) free word-order language. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pages 842–851, Singapore. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/cl-2013-goldberg-word-segmentation-unknown-word-resolution/