Training on Lexical Resources

Kenneth Church, Xingyu Cai, Yuchen Bian


Abstract
We propose using lexical resources (thesaurus, VAD) to fine-tune pretrained deep nets such as BERT and ERNIE. Then at inference time, these nets can be used to distinguish synonyms from antonyms, as well as VAD distances. The inference method can be applied to words as well as texts such as multiword expressions (MWEs), out of vocabulary words (OOVs), morphological variants and more. Code and data are posted on https://github.com/kwchurch/syn_ant.
Anthology ID:
2022.lrec-1.676
Volume:
Proceedings of the Thirteenth Language Resources and Evaluation Conference
Month:
June
Year:
2022
Address:
Marseille, France
Editors:
Nicoletta Calzolari, Frédéric Béchet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Hélène Mazo, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
6290–6299
Language:
URL:
https://aclanthology.org/2022.lrec-1.676
DOI:
Bibkey:
Cite (ACL):
Kenneth Church, Xingyu Cai, and Yuchen Bian. 2022. Training on Lexical Resources. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 6290–6299, Marseille, France. European Language Resources Association.
Cite (Informal):
Training on Lexical Resources (Church et al., LREC 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.lrec-1.676.pdf
Code
 kwchurch/syn_ant