Head-First Linearization with Tree-Structured Representation

Xiang Yu, Agnieszka Falenska, Ngoc Thang Vu, Jonas Kuhn


Abstract
We present a dependency tree linearization model with two novel components: (1) a tree-structured encoder based on bidirectional Tree-LSTM that propagates information first bottom-up then top-down, which allows each token to access information from the entire tree; and (2) a linguistically motivated head-first decoder that emphasizes the central role of the head and linearizes the subtree by incrementally attaching the dependents on both sides of the head. With the new encoder and decoder, we reach state-of-the-art performance on the Surface Realization Shared Task 2018 dataset, outperforming not only the shared tasks participants, but also previous state-of-the-art systems (Bohnet et al., 2011; Puduppully et al., 2016). Furthermore, we analyze the power of the tree-structured encoder with a probing task and show that it is able to recognize the topological relation between any pair of tokens in a tree.
Anthology ID:
W19-8636
Volume:
Proceedings of the 12th International Conference on Natural Language Generation
Month:
October–November
Year:
2019
Address:
Tokyo, Japan
Venue:
INLG
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
279–289
Language:
URL:
https://aclanthology.org/W19-8636
DOI:
10.18653/v1/W19-8636
Bibkey:
Cite (ACL):
Xiang Yu, Agnieszka Falenska, Ngoc Thang Vu, and Jonas Kuhn. 2019. Head-First Linearization with Tree-Structured Representation. In Proceedings of the 12th International Conference on Natural Language Generation, pages 279–289, Tokyo, Japan. Association for Computational Linguistics.
Cite (Informal):
Head-First Linearization with Tree-Structured Representation (Yu et al., INLG 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/remove-xml-comments/W19-8636.pdf