Mova0.5 pre-release⌕
☰
home / docs / papers / Semitic languages / Better Arabic Parsing: Baselines, Evaluations, and Analysis

Better Arabic Parsing: Baselines, Evaluations, and Analysis

What it is about

Green and Manning ask why constituency parsers for Modern Standard Arabic lag behind English results on the Penn Arabic Treebank (ATB). They name three sources: ambiguity created by unvocalized script (one surface form can be a particle, a pseudo-verb or a verb), discourse-level use of the conjunction wa that the ATB tags the same as noun-noun coordination, and weaker annotation consistency than in the WSJ (a variation n-gram sample gives a much higher type-level error rate for the ATB, about 37% against about 12%). They write a hand-built grammar that is competitive with a latent-variable PCFG, and improve three parsers (Stanford, Berkeley, Bikel) with preprocessing and tag fixes. Their conclusion: without gold segmentation, parsing scores drop by 2–5 F1 points.

Ideas

For Mova

I1 goes into Syntax: the clause and the sentence (waw coordination). I2 goes into The lexicon and the unpointed mode of tools/hbo. I3 is a test for tools/hbo, reported against gold segmentation. I4 is a check for tools/macula compare and treebanks/hbo/ptnk.

Cite

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

@inproceedings{green2010better,
  title = {{Better Arabic Parsing: Baselines, Evaluations, and Analysis}},
  author = {Green, Spence and Manning, Christopher D.},
  booktitle = {Proceedings of the 23rd International Conference on Computational Linguistics (Coling 2010)},
  year = {2010},
  url = {https://aclanthology.org/C10-1045/}
}

References

46 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Al-Batal, M. 1990. Connectives as cohesive elements in a modern expository Arabic text. In Eid, Mushira and John McCarthy, editors, Perspectives on Arabic Linguistics II. John Benjamins. find
  2. Arun, A and F Keller. 2005. Lexicalization in crosslinguistic probabilistic parsing: The case of French. In ACL. find
  3. Bikel, D M. 2004. Intricacies of Collins’ parsing model. Computational Linguistics, 30:479–511. find
  4. Chappelier, J-C, M Rajman, R Arages, and A Rozenknop. 1999. Lattice parsing for speech recognition. In TALN. find
  5. Chiang, D, M Diab, N Habash, O Rambow, and S Shareef. 2006. Parsing Arabic dialects. In EACL. find our card
  6. Clegg, A and A Shepherd. 2005. Evaluating and integrating treebank parsers on a biomedical corpus. In ACL Workshop on Software. find
  7. Cohen, S and N A Smith. 2007. Joint morphological and syntactic disambiguation. In EMNLP. find
  8. Collins, M, J Hajic, L Ramshaw, and C Tillmann. 1999. A statistical parser for Czech. In ACL. find
  9. Collins, M. 2003. Head-Driven statistical models for natural language parsing. Computational Linguistics, 29(4):589– 637. find our card
  10. Cowan, B and M Collins. 2005. Morphology and reranking for the statistical parsing of Spanish. In NAACL. find
  11. Diab, M. 2007. Towards an optimal POS tag set for Modern Standard Arabic processing. In RANLP. find
  12. Dickinson, M. 2005. Error Detection and Correction in Annotated Corpora. Ph.D. thesis, The Ohio State University. find
  13. Dubey, A and F Keller. 2003. Probabilistic parsing for German using sister-head dependencies. In ACL. find
  14. Dyer, C. 2009. Using a maximum entropy model to build segmentation lattices for MT. In NAACL. find
  15. Fassi Fehri, A. 1993. Issues in the structure of Arabic clauses and words. Kluwer Academic Publishers. find
  16. Gabbard, R and S Kulick. 2008. Construct state modification in the Arabic treebank. In ACL. find our card
  17. Goldberg, Y and R Tsarfaty. 2008. A single generative model for joint morphological segmentation and syntactic parsing. In ACL. find
  18. Green, S, C Sathi, and C D Manning. 2009. NP subject detection in verb-initial Arabic clauses. In Proc. of the Third Workshop on Computational Approaches to Arabic Script-based Languages (CAASL3). find
  19. Habash, N and O Rambow. 2005. Arabic tokenization, part-of-speech tagging and morphological disambiguation in one fell swoop. In ACL. find our card
  20. Habash, N and O Rambow. 2007. Arabic diacritization through full morphological tagging. In NAACL. find our card
  21. Habash, N and R Roth. 2009. CATiB: The Columbia Arabic Treebank. In ACL, Short Papers. find our card
  22. Habash, N and F Sadat. 2006. Arabic preprocessing schemes for statistical machine translation. In NAACL. find
  23. Habash, N, B Dorr, and C Monz. 2006. Challenges in building an Arabic-English GHMT system with SMT components. In EAMT. find
  24. Hajič, J and P Zemánek. 2004. Prague Arabic dependency treebank: Development in data and tools. In NEMLAR. find
  25. Huang, Z and M Harper. 2009. Self-training PCFG grammars with latent annotations across languages. In EMNLP. find
  26. Klein, D and C D Manning. 2002. Fast exact inference with a factored model for natural language parsing. In NIPS. find
  27. Klein, D and C D Manning. 2003. Accurate unlexicalized parsing. In ACL. find our card
  28. Kulick, S, R Gabbard, and M Marcus. 2006. Parsing the Arabic Treebank: Analysis and improvements. In TLT. find
  29. Kübler, S. 2005. How do treebank annotation schemes influence parsing results? Or how not to compare apples and oranges. In RANLP. find
  30. Levy, R and C D Manning. 2003. Is it harder to parse Chinese, or the Chinese treebank? In ACL. find
  31. Maamouri, M and A Bies. 2004. Developing an Arabic Treebank: Methods, guidelines, procedures, and tools. In Proc. of the Workshop on Computational Approaches to Arabic Script-based Languages (CAASL1). find our card
  32. Maamouri, M, A Bies, T Buckwalter, and W Mekki. 2004. The Penn Arabic Treebank: Building a large-scale annotated Arabic corpus. In NEMLAR. find
  33. Maamouri, M, A Bies, and S Kulick. 2008. Enhancing the Arabic Treebank: A collaborative effort toward new annotation guidelines. In LREC. find
  34. Maamouri, M, A Bies, S Krouna, F Gaddeche, and B Bouziri. 2009a. Penn Arabic Treebank guidelines v4.92. Technical report, Linguistic Data Consortium, University of Pennsylvania, August 5. find
  35. Maamouri, M, A Bies, and S Kulick. 2009b. Creating a methodology for large-scale correction of treebank annotation: The case of the Arabic Treebank. In MEDAR. find
  36. Marcus, M, M A Marcinkiewicz, and B Santorini. 1993. Building a large annotated corpus of English: The Penn Treebank. Computational Linguistics, 19:313–330. find our card
  37. Petrov, S, L Barrett, R Thibaux, and D Klein. 2006. Learning accurate, compact, and interpretable tree annotation. In ACL. find our card
  38. Petrov, S. 2009. Coarse-to-Fine Natural Language Processing. Ph.D. thesis, University of California-Berkeley. find
  39. Rehbein, I and J van Genabith. 2007. Treebank annotation schemes and parser evaluation for German. In EMNLP-CoNLL. find
  40. Roark, B, M Harper, E Charniak, B Dorr, M Johnson, J G Kahne, Y Liuf, Mari Ostendorf, J Hale, A Krasnyanskaya, M Lease, I Shafran, M Snover, R Stewart, and L Yung. 2006. SParseval: Evaluation metrics for parsing speech. In LREC. find
  41. Ryding, K. 2005. A Reference Grammar of Modern Standard Arabic. Cambridge University Press. find
  42. Sampson, G and A Babarczy. 2003. A test of the leaf-ancestor metric for parse accuracy. Natural Language Engineering, 9:365–380. find
  43. Toutanova, K, D Klein, C D Manning, and Y Singer. 2003. Feature-rich part-of-speech tagging with a cyclic dependency network. In NAACL. find
  44. Tsarfaty, R and K Sima’an. 2008. Relational-realizational parsing. In COLING. find
  45. Tsarfaty, R. 2006. Integrated morphological and syntactic disambiguation for Modern Hebrew. In ACL. find our card
  46. Zitouni, I, J S Sorensen, and R Sarikaya. 2006. Maximum entropy based restoration of Arabic diacritics. In ACL. find our card

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2010-green-better-arabic-parsing-baselines-evaluations/