Lexical Semantic Recognition
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Lexical Semantic Recognition. / Liu, Nelson F.; Hershcovich, Daniel; Kranzlein, Michael; Schneider, Nathan.
Proceedings of the 17th Workshop on Multiword Expressions (MWE 2021). Association for Computational Linguistics, 2021. p. 49-56.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Lexical Semantic Recognition
AU - Liu, Nelson F.
AU - Hershcovich, Daniel
AU - Kranzlein, Michael
AU - Schneider, Nathan
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
U2 - 10.18653/v1/2021.mwe-1.6
DO - 10.18653/v1/2021.mwe-1.6
M3 - Article in proceedings
SP - 49
EP - 56
BT - Proceedings of the 17th Workshop on Multiword Expressions (MWE 2021)
PB - Association for Computational Linguistics
T2 - 17th Workshop on Multiword Expressions (MWE 2021)
Y2 - 6 August 2021 through 6 August 2021
ER -
ID: 300916255