Mova0.5 pre-release⌕
☰
home / docs / papers / Semitic languages / Comparing Neural Network Parsers for a Less-resourced and Morphologically-rich Language: Amharic Dependency Parser

Comparing Neural Network Parsers for a Less-resourced and Morphologically-rich Language: Amharic Dependency Parser

What it is about

The paper compares four off-the-shelf neural dependency parsers (UDPipe, jPTDP, UUParser, Turku) on the Amharic UD treebank, which has about 1,074 manually annotated sentences. Evaluation is ten-fold cross-validation, since the data is too small for a fixed split. The best result is UDPipe with a LAS of 83.79, rising to 85.26 when pretrained fastText vectors are added. The authors then run the pipeline from raw text: word segmentation drops from about 98% to about 80%, tagging falls from 93–95% to 74–77% with predicted segmentation, and attachment falls with it. Their conclusion is that the segmentation of clitics, done before tagging, is the bottleneck for a small-data parser, and that a joint model with morphological tags is a promising direction.

Ideas

For Mova

I1 is a reporting rule for tools/hbo (segmenter then gparse) and for treebanks/hbo/ptnk. I2 is an evaluation protocol for gparse in treebanks/hbo/. I3 is an experiment for the unpointed mode of tools/hbo, and a reason to keep the segmenter's tables visible in its output. The paper is non-commercial: only the summary above is used, and nothing from the text or the treebank is carried into a release.

Topics: Dependency parsing · Treebanks

Cite

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

@inproceedings{seyoum2020comparing,
  title = {{Comparing Neural Network Parsers for a Less-resourced and Morphologically-rich Language: Amharic Dependency Parser}},
  author = {Seyoum, Binyam Ephrem and Miyao, Yusuke and Mekonnen, Baye Yimam},
  booktitle = {Proceedings of the first workshop on Resources for African Indigenous Languages},
  year = {2020},
  url = {https://aclanthology.org/2020.rail-1.5/}
}

References

31 references, 16 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Andor, D., Alberti, C., Weiss, D., Severyn, A., Presta, A., Ganchev, K., Petrov, S., and Collins, M. (2016). Globally Normalized Transition-Based Neural Networks. Association for Computational Linguistics, arXiv preprint arXiv:1603.06042. ↗
  2. Bohnet, B., McDonald, R., Simoes, G., Andor, D., Pitler, E., and Maynez, J. (2018). Morphosyntactic Tagging with a Meta-BiLSTM Model over Context Sensitive Token Encodings. In Proceedings of the 56 th Annual Meeting of the Association for Computational Linguistics (Long Papers), pages 2642–2652, Melbourne, Australia. Association for Computational Linguistics. find
  3. Che, W., Liu, Y., Wang, Y., Zheng, B., and Liu, T. (2018). Towards Better UD Parsing: Deep Contextualized Word Embeddings, Ensemble, and Treebank Concatenation. In Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 55–64. find our card
  4. Chen, D. and Manning, C. D. (2014). A Fast and Accurate Dependency Parser using Neural Networks. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 740– 750, Doha, Qatar. find our card
  5. de Lhoneux, M., Shao, Y., Basirat, A., Kiperwasser, E., Stymne, S., Goldberg, Y., and Nivre, J. (2017). From raw text to universal dependencies-look, no tags! In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 207–217. find our card
  6. Dehdari, J., Tounsi, L., and van Genabith, J. (2011). Morphological Features for Parsing Morphologically-rich Languages: A Case of Arabic. In Proceedings of the 2nd Workshop on Statistical Parsing of Morphologically-Rich Languages (SPMRL 2011), pages 12–21, Dublin, Ireland. Association for Computational Linguistics. find our card
  7. Dozat, T. and Manning, C. D. (2017). Deep Biaffine Attention for Neural Dependency Parsing. In ICLR2017. find our card
  8. Dozat, T., Qi, P., and Manning, C. D. (2017). Stanford’s Graph-based Neural Dependency Parser at the CoNLL 2017 Shared Task. (2016):20–30. find our card
  9. Dyer, C., Ballesteros, M., Ling, W., Matthews, A., and Smith, N. A. (2015). Transition-Based Dependency Parsing with Stack Long Short-Term Memory. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7 th International Joint Conference on Natural Language Processing, pages 334–343, Beijing, China. Association for Computational Linguistics. find our card
  10. Dyer, C., Kuncoro, A., Ballesteros, M., and Smith, N. A. (2016). Recurrent Neural Network Grammars. In Proc. of NAACL. find
  11. Goldberg, Y. (2017). Neural Network Methods for Natural Language Processing. In Synthesis Lectures on Human Language Technologies, volume 10, pages 1–282. Morgan & Claypool Publishers series. find
  12. Grave, E., Bojanowski, P., Gupta, P., Joulin, A., and Mikolov, T. (2018). Learning Word Vectors for 157 Languages. In Proceedings of the International Conference on Language Resources and Evaluation (LREC 2018), pages 1–5. find
  13. Habash, N. Y. (2010). Introduction to Arabic Natural Language Processing. Synthesis Lectures on Human Language Technologies, 3(1):1–187. find
  14. Kanerva, J., Ginter, F., Miekka, N., Leino, A., and Salakoski, T. (2018). Turku Neural Parser Pipeline : An End-to-End System for the CoNLL 2018 Shared Task. In Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 133–142. find our card
  15. Kiperwasser, E. and Goldberg, Y. (2016). Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations. Transactions of the Association for Computational Linguistics, 4:313–327. find our card
  16. Kübler, S., McDonald, R., and Nivre, J. (2009). Dependency Parsing. Synthesis Lectures on Human Language Technologies, 34(1):1–127. find
  17. Kuncoro, A., Ballesteros, M., Kong, L., Dyer, C., Neubig, G., and Smith, N. A. (2017). What Do Recurrent Neural Network Grammars Learn About Syntax? arXiv preprint arXiv:1611.05774. ↗
  18. Lavelli, A. (2016). Comparing State-of-the-art Dependency Parsers on the Italian Stanford Dependency Treebank. CLiC it, pages 173–178. find
  19. Mcdonald, R., Crammer, K., and Pereira, F. (2005). Online Large-Margin Training of Dependency Parsers. pages 91–98. find our card
  20. Nguyen, D. Q. and Verspoor, K. (2018). An improved neural network model for joint POS tagging and dependency parsing. In Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 81–91. find our card
  21. Nivre, J. (2008). Algorithms for Deterministic Incremental Dependency Parsing. Computational Linguistics, 34(4):513–553. find our card
  22. Nivre, J. (2014). Universal Dependencies for Swedish. In The Fifth Swedish Language Technology Conference (Sltc), pages 1579–1585. find
  23. Seyoum, B. E., Miyao, Y., and Mekonnen, B. Y. (2018). Universal Dependencies for Amharic. In Nicoletta Calzolari, et al., editors, Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), pages 2216–2222, Miyazaki, Japan. European Language Resources Association (ELRA). find our card
  24. Smith, A., de Lhoneux, M., Stymne, S., and Nivre, J. (2018). An Investigation of the Interactions Between Pre-Trained Word Embeddings, Character Models and POS Tags in Dependency Parsing. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2711–2720, Brussels, Belgium. Association for Computational Linguistics. find
  25. Straka, M., Hajič, J., and Straková, J. (2016). UDPipe: Trainable Pipeline for Processing CoNLL-U Files Performing Tokenization, Morphological Analysis, POS Tagging and Parsing. In Proceedings of LREC 2016, pages 4290–4297. find our card
  26. Straka, M., Straková, J., and Hajič, J. (2017). Prague at EPE 2017: The UDPipe System. In Proceedings of the 2017 Shared Task on Extrinsic Parser Evaluation at the Fourth International Conference on Dependency Linguistics and the 15 th International Conference on Parsing Technologies, pages 65–74, Pisa (Italy). Association for Computational Linguistics (ACL). find
  27. Straková, J., Straka, M., and Hajič, J. (2014). Open-Source Tools for Morphology, Lemmatization, POS Tagging and Named Entity Recognition. In Proceedings of the 52 nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 13–18, Baltimore, Maryland USA. Association for Computational Linguistics. find
  28. Tsarfaty, R., Seddah, D., Goldberg, Y., Kübler, S., Candito, M., Foster, J., Versley, Y., Rehbein, I., and Tounsi, L. (2010). Statistical parsing of morphologically rich languages (SPMRL): what, how and whither. In Proceedings of the NAACL HLT 2010 First Workshop on Statistical Parsing of Morphologically-Rich Languages, pages 1–12, Los Angeles, California. Association for Computational Linguistics. find
  29. Zeman, D., Popel, M., Straka, M., Hajic, J., Nivre, J., Ginter, F., Luotolahti, J., Pyysalo, S., Petrov, S., Potthast, M., Tyers, F., Badmaeva, E., Gokirmak, M., Nedoluzhko, A., Cinkova, S., Hajic jr., J., Hlavacova, J., Kettnerová, V., Uresova, Z., Kanerva, J., Ojala, S., Missilä, A., Manning, C. D., Schuster, S., Reddy, S., Taji, D., Habash, N., Leung, H., de Marneffe, M.-C., Sanguinetti, M., Simi, M., Kanayama, H., DePaiva, V., Droganova, K., Martı́nez Alonso, H., Çöltekin, Ç., Sulubacak, U., Uszkoreit, H., Macketanz, V., Burchardt, A., Harris, K., Marheinecke, K., Rehm, G., Kayadelen, T., Attia, M., Elkahky, A., Yu, Z., Pitler, E., Lertpradit, S., Mandl, M., Kirchner, J., Alcalde, H. F., Strnadová, J., Banerjee, E., Manurung, R., Stella, A., Shimada, A., Kwak, S., Mendonca, G., Lando, T., Nitisaroj, R., and Li, J. (2017). CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 1–19. Association for Computational Linguistics. find our card
  30. Zeman, D., HajiË, J., Popel, M., Potthast, M., Straka, M., Ginter, F., Nivre, J., and Petrov, S. (2018). CoNLL 2018 Shared Task : Multilingual Parsing from Raw Text to Universal Dependencies. In Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 1–21, Brussels, Belgium. Association for Computational Linguistics. find our card
  31. Zhang, Y. and Nivre, J. (2011). Transition-based Dependency Parsing with Rich Non-local Features. In Proceedings of the 49 th Annual Meeting of the Association for Computational Linguistics: short papers, pages 188– 193. Association for Computational Linguistics. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2020-seyoum-comparing-neural-network-parsers-less/