TY - GEN
T1 - End-To-end graph-based TAG parsing with neural networks
AU - Kasai, Jungo
AU - Frank, Robert
AU - Xu, Pauli
AU - Merrill, William
AU - Rambow, Owen
N1 - Publisher Copyright:
© 2018 The Association for Computational Linguistics.
PY - 2018
Y1 - 2018
N2 - We present a graph-based Tree Adjoining Grammar (TAG) parser that uses BiLSTMs, highway connections, and characterlevel CNNs. Our best end-To-end parser, which jointly performs supertagging, POS tagging, and parsing, outperforms the previously reported best results by more than 2.2 LAS and UAS points. The graph-based parsing architecture allows for global inference and rich feature representations for TAG parsing, alleviating the fundamental trade-off between transition-based and graph-based parsing systems. We also demonstrate that the proposed parser achieves state-of-The-Art performance in the downstream tasks of Parsing Evaluation using Textual Entailments (PETE) and Unbounded Dependency Recovery. This provides further support for the claim that TAG is a viable formalism for problems that require rich structural analysis of sentences.
AB - We present a graph-based Tree Adjoining Grammar (TAG) parser that uses BiLSTMs, highway connections, and characterlevel CNNs. Our best end-To-end parser, which jointly performs supertagging, POS tagging, and parsing, outperforms the previously reported best results by more than 2.2 LAS and UAS points. The graph-based parsing architecture allows for global inference and rich feature representations for TAG parsing, alleviating the fundamental trade-off between transition-based and graph-based parsing systems. We also demonstrate that the proposed parser achieves state-of-The-Art performance in the downstream tasks of Parsing Evaluation using Textual Entailments (PETE) and Unbounded Dependency Recovery. This provides further support for the claim that TAG is a viable formalism for problems that require rich structural analysis of sentences.
UR - https://www.scopus.com/pages/publications/85081723657
M3 - Conference contribution
AN - SCOPUS:85081723657
T3 - NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference
SP - 1181
EP - 1194
BT - Long Papers
PB - Association for Computational Linguistics (ACL)
T2 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018
Y2 - 1 June 2018 through 6 June 2018
ER -