Monotonicity Marking from Universal Dependency Trees

Zeming Chen, Qiyue Gao


Abstract
Dependency parsing is a tool widely used in the field of Natural language processing and computational linguistics. However, there is hardly any work that connects dependency parsing to monotonicity, which is an essential part of logic and linguistic semantics. In this paper, we present a system that automatically annotates monotonicity information based on Universal Dependency parse trees. Our system utilizes surface-level monotonicity facts about quantifiers, lexical items, and token-level polarity information. We compared our system’s performance with existing systems in the literature, including NatLog and ccg2mono, on a small evaluation dataset. Results show that our system outperforms NatLog and ccg2mono.
Anthology ID:
2021.iwcs-1.12
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:
121–131
Language:
URL:
https://aclanthology.org/2021.iwcs-1.12
DOI:
Award:
 Outstanding Paper
Bibkey:
Cite (ACL):
Zeming Chen and Qiyue Gao. 2021. Monotonicity Marking from Universal Dependency Trees. In Proceedings of the 14th International Conference on Computational Semantics (IWCS), pages 121–131, Groningen, The Netherlands (online). Association for Computational Linguistics.
Cite (Informal):
Monotonicity Marking from Universal Dependency Trees (Chen & Gao, IWCS 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.iwcs-1.12.pdf
Attachment:
 2021.iwcs-1.12.Attachment.zip
Code
 eric11eca/Udep2Mono
Data
Universal Dependencies