Abstract
This paper presents an overview of the NLPCC 2019 shared task on cross-domain dependency parsing, including (1) the data annotation process, (2) task settings, (3) methods, results, and analysis of submitted systems and our recent work (Li+19), (4) discussions on related works and future directions. Considering that unsupervised domain adaptation is very difficult and has made limited progress in the past decades, we for the first time setup semi-supervised subtasks that allow to use a few thousand target-domain labeled sentences for training. We provide about 17 K labeled sentences from a balanced corpus as the source domain (BC), and as three target domains 10 K sentences from product comments (PC), 8 K sentences from product blogs (PB), and 3 K sentences from the web fiction named “Zhuxian” (ZX). All information about this task can be found at http://hlt.suda.edu.cn/index.php/Nlpcc-2019-shared-task, including the data sharing agreement.
Supported by National Natural Science Foundation of China (Grant No. 61876116, 61525205).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Webpage for our treebank annotation: http://hlt.suda.edu.cn/index.php/SUCDT.
- 2.
The parser can be tried at http://hlt-la.suda.edu.cn.
- 3.
Our major purpose for annotating these datasets is to support supervised treebank conversion.
- 4.
The word embeddings are obtained by training word2vec on the Chinese Gigaword 3 and all the target-domain unlabeled data.
- 5.
Please notice again that semi-supervised in our domain adaptation scenario is about whether using target-domain labeled training data.
- 6.
References
Buchholz, S., Marsi, E.: CoNLL-X shared task on multilingual dependency parsing. In: In Proceedings of CoNLL, pp. 149–164 (2006)
Che, W., Li, Z., Liu, T.: Chinese dependency treebank 1.0 (Ldc2012t05). In: Philadelphia: Linguistic Data Consortium (2012)
Chen, D., Manning, C.: A fast and accurate dependency parser using neural networks. In: Proceedings of EMNLP, pp. 740–750 (2014)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL, pp. 4171–4186 (2019)
Dredze, M., Blitzer, J., Pratim Talukdar, P., Ganchev, K., Graca, J.a., Pereira, F.: Frustratingly hard domain adaptation for dependency parsing. In: Proceedings of the CoNLL Shared Task Session of EMNLP-CoNLL 2007, pp. 1051–1055 (2007)
Fernández-González, D., Gómez-Rodríguez, C.: Left-to-right dependency parsing with pointer networks. In: Proceedings of NAACL, pp. 710–716 (2019)
Hajič, J., et al.: The CoNLL-2009 shared task: syntactic and semantic dependencies in multiple languages. In: Proceedings of CoNLL (2009)
Ji, T., Wu, Y., Lan, M.: Graph-based dependency parsing with graph neural networks. In: Proceedings of ACL (2019)
Jiang, X., Li, Z., Zhang, B., Zhang, M., Li, S., Si, L.: Supervised treebank conversion: data and approaches. In: Proceedings of ACL, pp. 2706–2716 (2018)
Li, Z., Xue, P., Zhang, M., Wang, R., Si, L.: Semi-supervised domain adaptation for dependency parsing. In: Proceedings of ACL (2019)
Li, Z., Zhou, J., Zhao, H., Wang, R.: Cross-domain transfer learning for dependency parsing (2019)
Ma, X., Hu, Z., Liu, J., Peng, N., Graham, N., Eduard, H.: Stack-pointer networks for dependency parsing. In: Proceedings of ACL, pp. 1403–1414 (2018)
Nivre, J., Hall, J., Kübler, S., McDonald, R., Nilsson, J., Riedel, S., Yuret, D.: The coNLL 2007 shared task on dependency parsing. In: Proceedings of the CoNLL Shared Task Session of EMNLP-CoNLL 2007, pp. 915–932 (2007)
Nivre, J., et al.: Universal dependencies v1: a multilingual treebank collection. In: Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016) (2016)
Peters, M.E., et al.: Deep contextualized word representations. In: Proceedings of NAACL-HLT, pp. 2227–2237 (2018)
Petrov, S., McDonald, R.: Overview of the 2012 shared task on parsing the web. In: Notes of the First Workshop on Syntactic Analysis of Non-Canonical Language (SANCL) (2012)
Ruder, S., Peters, M.E., Swayamdipta, S., Wolf, T.: Transfer learning in natural language processing. In: Proceedings of NAACL: Tutorials, pp. 15–18 (2019)
Sagae, K., Lavie, A.: Parser combination by reparsing. In: Proceedings of NAACL, pp. 129–132 (2006)
Surdeanu, M., Johansson, R., Meyers, A., Màrquez, L., Nivre, J.: The CoNLL-2008 shared task on joint parsing of syntactic and semantic dependencies. In: CoNLL-2008 (2008)
Xia, Z., Wang, L., Qu, W., Zhou, J., Gu, Y.: Neural network based deep transfer learning for cross-domain dependency parsing. arXiv (2019)
Xue, N., Xia, F., Chiou, F.D., Palmer, M.: The Penn Chinese treebank: phrase structure annotation of a large corpus. Nat. Lang. Eng. 11(02), 207–238 (2005)
Yu, N., Liu, Z., Zhen, R., Liu, T., Zhang, M., Fu, G.: Domain information enhanced dependency parser (2019)
Zeman, D., et al.: 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, pp. 1–21 (2018)
Zeman, D., et al.: 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, pp. 1–19, August 2017
Zhang, M., Zhang, Y., Che, W., Liu, T.: Type-supervised domain adaptation for joint segmentation and pos-tagging. In: Proceedings of EACL, pp. 588–597 (2014)
Zhang, Y., Li, Z., Lang, J., Xia, Q., Zhang, M.: Dependency parsing with partial annotations: an empirical comparison. In: Proceedings of IJCNLP, pp. 49–58 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Peng, X., Li, Z., Zhang, M., Wang, R., Zhang, Y., Si, L. (2019). Overview of the NLPCC 2019 Shared Task: Cross-Domain Dependency Parsing. In: Tang, J., Kan, MY., Zhao, D., Li, S., Zan, H. (eds) Natural Language Processing and Chinese Computing. NLPCC 2019. Lecture Notes in Computer Science(), vol 11839. Springer, Cham. https://doi.org/10.1007/978-3-030-32236-6_69
Download citation
DOI: https://doi.org/10.1007/978-3-030-32236-6_69
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32235-9
Online ISBN: 978-3-030-32236-6
eBook Packages: Computer ScienceComputer Science (R0)