Abstract
One great challenge in neural sequence labeling is the data sparsity problem for rare entity words and phrases. Most of test set entities appear only few times and are even unseen in training corpus, yielding large number of out-of-vocabulary (OOV) and low-frequency (LF) entities during evaluation. In this work, we propose approaches to address this problem. For OOV entities, we introduce local context reconstruction to implicitly incorporate contextual information into their representations. For LF entities, we present delexicalized entity identification to explicitly extract their frequency-agnostic and entity-type-specific representations. Extensive experiments on multiple benchmark datasets show that our model has significantly outperformed all previous methods and achieved new start-of-the-art results. Notably, our methods surpass the model fine-tuned on pre-trained language models without external resource.- Anthology ID:
- 2020.acl-main.574
- Volume:
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6441–6451
- Language:
- URL:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2020.acl-main.574/
- DOI:
- 10.18653/v1/2020.acl-main.574
- Cite (ACL):
- Yangming Li, Han Li, Kaisheng Yao, and Xiaolong Li. 2020. Handling Rare Entities for Neural Sequence Labeling. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6441–6451, Online. Association for Computational Linguistics.
- Cite (Informal):
- Handling Rare Entities for Neural Sequence Labeling (Li et al., ACL 2020)
- PDF:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2020.acl-main.574.pdf