Coordination Boundary Identification with Similarity and Replaceability

Hiroki Teranishi, Hiroyuki Shindo, Yuji Matsumoto


Abstract
We propose a neural network model for coordination boundary detection. Our method relies on the two common properties - similarity and replaceability in conjuncts - in order to detect both similar pairs of conjuncts and dissimilar pairs of conjuncts. The model improves identification of clause-level coordination using bidirectional RNNs incorporating two properties as features. We show that our model outperforms the existing state-of-the-art methods on the coordination annotated Penn Treebank and Genia corpus without any syntactic information from parsers.
Anthology ID:
I17-1027
Volume:
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
November
Year:
2017
Address:
Taipei, Taiwan
Editors:
Greg Kondrak, Taro Watanabe
Venue:
IJCNLP
SIG:
Publisher:
Asian Federation of Natural Language Processing
Note:
Pages:
264–272
Language:
URL:
https://aclanthology.org/I17-1027
DOI:
Bibkey:
Cite (ACL):
Hiroki Teranishi, Hiroyuki Shindo, and Yuji Matsumoto. 2017. Coordination Boundary Identification with Similarity and Replaceability. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 264–272, Taipei, Taiwan. Asian Federation of Natural Language Processing.
Cite (Informal):
Coordination Boundary Identification with Similarity and Replaceability (Teranishi et al., IJCNLP 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/I17-1027.pdf