Abstract
We show that strong domain adaptation results for dependency parsing can be achieved using a conceptually simple method that learns domain-invariant word representations. Lacking labeled resources, dependency parsing for low-resource domains has been a challenging task. Existing work considers adapting a model trained on a resource-rich domain to low-resource domains. A mainstream solution is to find a set of shared features across domains. For neural network models, word embeddings are a fundamental set of initial features. However, little work has been done investigating this simple aspect. We propose to learn domain-invariant word representations by fine-tuning pretrained word representations adversarially. Our parser achieves error reductions of 5.6% UAS, 7.9% LAS on PTB respectively, and 4.2% UAS, 3.2% LAS on Genia respectively, showing the effectiveness of domain invariant word representations for alleviating lexical bias between source and target data.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Shen, L., Xu, J., Weischedel, R.: A new string-to-dependency machine translation algorithm with a target dependency language model. In: ACL (2008)
McClosky, D., Surdeanu, M., Manning, C.: Event extraction as dependency parsing. In: ACL (2011)
Chen, Q., Zhu, X., Ling, Z.-H., Wei, S., Jiang, H., Inkpen, D.: Enhanced LSTM for natural language inference. In: ACL (2017)
Guo, J., Che, W., Yarowsky, D., Wang, H., Liu, T.: A representation learning framework for multi-source transfer parsing. In: AAAI (2016)
Duong, L., Cohn, T., Bird, S., Cook, P.: Low resource dependency parsing: cross-lingual parameter sharing in a neural network parser. In: ACL (2015)
Ben-David, S., Blitzer, J., Crammer, K., Pereira, F.: Analysis of representations for domain adaptation. In: NIPS (2006)
Marcus, M.P., Santorini, B., Marcinkiewicz, M.A.: Building a large annotated corpus of English: the Penn treebank. Computat. Linguist. 19(2), 313–330 (1993)
Kim, J.-D., Ohta, T., Tateisi, Y., Tsujii, J.: Genia corpus-semantically annotated corpus for bio-textmining. Bioinformatics 19(Suppl 1), i180–i182 (2003)
Koo, T., Carreras, X., Collins, M.: Simple semi-supervised dependency parsing. In: ACL (2008)
Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. CoRR, abs/1301.3781 (2013)
Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein GAN. CoRR, abs/1701.07875 (2017)
Dozat, T., Manning, C.D.: Deep biaffine attention for neural dependency parsing. In: ICLR (2017)
Kim, Y.: Convolutional neural networks for sentence classification. In: EMNLP (2014)
Goodfellow, I., et al.: Generative adversarial nets. In: NIPS (2014)
Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: EMNLP (2014)
Ma, X., Hu, Z., Liu, J., Peng, N., Neubig, G., Hovy, E.: Stack-pointer networks for dependency parsing. In: ACL (2018)
McClosky, D., Charniak, E.: Self-training for biomedical parsing. In: ACL (2008)
Ling, W., Dyer, C., Black, A.W., Trancoso, I.: Two/too simple adaptations of Word2Vec for syntax problems. In: NAACL (2015)
Zhang, Y., Clark, S.: A tale of two parsers: investigating and combining graph-based and transition-based dependency parsing. In: EMNLP (2008)
Liu, J., Zhang, Y.: Encoder-decoder shift-reduce syntactic parsing. In: IWPT (2017)
McClosky, D., Charniak, E., Johnson, M.: Automatic domain adaptation for parsing. In: NAACL (2010)
Jiang, J., Zhai, C.X.: Instance weighting for domain adaptation in NLP. In: ACL (2007)
Wang, R., Utiyama, M., Liu, L., Chen, K., Sumita, E.: Instance weighting for neural machine translation domain adaptation. In: EMNLP (2017)
Chen, W., Zhang, M., Zhang, Y.: Distributed feature representations for dependency parsing. IEEE/ACM TASLP 23, 451–460 (2015)
Long, M., Cao, Y., Wang, J., Jordan, M.I.: Learning transferable features with deep adaptation networks. In: ICML (2015)
Shen, J., Qu, Y., Zhang, W., Yu, Y.: Wasserstein distance guided representation learning for domain adaptation. In: AAAI (2018)
Levy, O., Goldberg, Y.: Dependency-based word embeddings. In: ACL (2014)
Sun, C., Yan, H., Qiu, X., Huang, X.: Gaussian word embedding with a wasserstein distance loss. CoRR, abs/1808.07016 (2018)
Xu, H., Wang, W., Liu, W., Carin, L.: Distilled wasserstein learning for word embedding and topic modeling. In: NIPS (2018)
Sato, M., Manabe, H., Noji, H., Matsumoto, Y.: Adversarial training for cross-domain universal dependency parsing. In: CoNLL (2017)
Acknowledgments
This work was done when the first author was visiting Westlake University. We gratefully acknowledge the funding from the project of National Key Research and Development Program of China (No. 2018YFC0830700). We also thank the anonymous reviewers for their helpful comments and suggestions.
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
Qiao, X., Zhang, Y., Zhao, T. (2019). Learning Domain Invariant Word Representations for Parsing Domain Adaptation. 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 11838. Springer, Cham. https://doi.org/10.1007/978-3-030-32233-5_62
Download citation
DOI: https://doi.org/10.1007/978-3-030-32233-5_62
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32232-8
Online ISBN: 978-3-030-32233-5
eBook Packages: Computer ScienceComputer Science (R0)