Lexical Semantic Recognition

Nelson F. Liu, Daniel Hershcovich, Michael Kranzlein, Nathan Schneider


Abstract
In lexical semantics, full-sentence segmentation and segment labeling of various phenomena are generally treated separately, despite their interdependence. We hypothesize that a unified lexical semantic recognition task is an effective way to encapsulate previously disparate styles of annotation, including multiword expression identification / classification and supersense tagging. Using the STREUSLE corpus, we train a neural CRF sequence tagger and evaluate its performance along various axes of annotation. As the label set generalizes that of previous tasks (PARSEME, DiMSUM), we additionally evaluate how well the model generalizes to those test sets, finding that it approaches or surpasses existing models despite training only on STREUSLE. Our work also establishes baseline models and evaluation metrics for integrated and accurate modeling of lexical semantics, facilitating future work in this area.
Anthology ID:
2021.mwe-1.6
Volume:
Proceedings of the 17th Workshop on Multiword Expressions (MWE 2021)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP | MWE
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
49–56
Language:
URL:
https://aclanthology.org/2021.mwe-1.6
DOI:
10.18653/v1/2021.mwe-1.6
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.mwe-1.6.pdf
Optional supplementary material:
 2021.mwe-1.6.OptionalSupplementaryMaterial.zip