PATCHCOMM: using commonsense knowledge to guide syntactic parsers
Files
Published version
Date
2021-09
Authors
Xin, Yida
Lieberman, Henry
Chin, Peter
Version
Published version
OA Version
Citation
Y. Xin, H. Lieberman, P. Chin. 2021. "PATCHCOMM: Using Commonsense Knowledge to Guide Syntactic Parsers." Proceedings of the Eighteenth International Conference on Principles of Knowledge Representation and Reasoning. 18th International Conference on Principles of Knowledge Representation and Reasoning {KR-2021}. 2020-11-12 - 2021-11-18. https://doi.org/10.24963/kr.2021/75
Abstract
Syntactic parsing technologies have become significantly more robust thanks to advancements in their underlying statistical and Deep Neural Network (DNN) techniques: most modern syntactic parsers can produce a syntactic parse tree for almost any sentence, including ones that may not be strictly grammatical. Despite improved robustness, such parsers still do not reflect the alternatives in parsing that are intrinsic in syntactic ambiguities. Two most notable such ambiguities are prepositional phrase (PP) attachment ambiguities and pronoun coreference ambiguities. In this paper, we discuss PatchComm, which uses commonsense knowledge to help resolve both kinds of ambiguities. To the best of our knowledge, we are the first to propose the general-purpose approach of using external commonsense knowledge bases to guide syntactic parsers. We evaluated PatchComm against the state-of-the-art (SOTA) spaCy parser on a PP attachment task and against the SOTA NeuralCoref module on a coreference task. Results show that PatchComm is successful at detecting syntactic ambiguities and using commonsense knowledge to help resolve them.
Description
License
Copyright © 2021 International Joint Conferences on Artificial Intelligence Organization.