A Transition-based Parser for Unscoped Episodic Logical Forms

Gene Kim, Viet Duong, Xin Lu, Lenhart Schubert


Abstract
“Episodic Logic: Unscoped Logical Form” (EL-ULF) is a semantic representation capturing predicate-argument structure as well as more challenging aspects of language within the Episodic Logic formalism. We present the first learned approach for parsing sentences into ULFs, using a growing set of annotated examples. The results provide a strong baseline for future improvement. Our method learns a sequence-to-sequence model for predicting the transition action sequence within a modified cache transition system. We evaluate the efficacy of type grammar-based constraints, a word-to-symbol lexicon, and transition system state features in this task. Our system is available at https://github.com/genelkim/ulf-transition-parser. We also present the first official annotated ULF dataset at https://www.cs.rochester.edu/u/gkim21/ulf/resources/.
Anthology ID:
2021.iwcs-1.18
Volume:
Proceedings of the 14th International Conference on Computational Semantics (IWCS)
Month:
June
Year:
2021
Address:
Groningen, The Netherlands (online)
Venue:
IWCS
SIG:
SIGSEM
Publisher:
Association for Computational Linguistics
Note:
Pages:
184–201
Language:
URL:
https://aclanthology.org/2021.iwcs-1.18
DOI:
Bibkey:
Cite (ACL):
Gene Kim, Viet Duong, Xin Lu, and Lenhart Schubert. 2021. A Transition-based Parser for Unscoped Episodic Logical Forms. In Proceedings of the 14th International Conference on Computational Semantics (IWCS), pages 184–201, Groningen, The Netherlands (online). Association for Computational Linguistics.
Cite (Informal):
A Transition-based Parser for Unscoped Episodic Logical Forms (Kim et al., IWCS 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.iwcs-1.18.pdf
Attachment:
 2021.iwcs-1.18.Attachment.zip
Code
 genelkim/ulf-transition-parser