Measuring Frame Instance Relatedness

Valerio Basile, Roque Lopez Condori, Elena Cabrio


Abstract
Frame semantics is a well-established framework to represent the meaning of natural language in computational terms. In this work, we aim to propose a quantitative measure of relatedness between pairs of frame instances. We test our method on a dataset of sentence pairs, highlighting the correlation between our metric and human judgments of semantic similarity. Furthermore, we propose an application of our measure for clustering frame instances to extract prototypical knowledge from natural language.
Anthology ID:
S18-2029
Volume:
Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Editors:
Malvina Nissim, Jonathan Berant, Alessandro Lenci
Venue:
*SEM
SIGs:
SIGSEM | SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
245–254
Language:
URL:
https://aclanthology.org/S18-2029
DOI:
10.18653/v1/S18-2029
Bibkey:
Cite (ACL):
Valerio Basile, Roque Lopez Condori, and Elena Cabrio. 2018. Measuring Frame Instance Relatedness. In Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics, pages 245–254, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
Measuring Frame Instance Relatedness (Basile et al., *SEM 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-bitext-workshop/S18-2029.pdf
Data
FrameNet