Back to Main Conference 2022
LREC 2022main

Training on Lexical Resources

Proceedings of the Thirteenth International Conference on Language Resources and Evaluation (LREC 2022)

DOI:10.63317/492uuneqo3ma

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.

Details

Paper ID
lrec2022-main-676
Pages
pp. 6290-6299
BibKey
church-etal-2022-training
Editor
N/A
Publisher
European Language Resources Association (ELRA)
ISSN
2522-2686
ISBN
79-10-95546-38-2
Conference
Thirteenth Language Resources and Evaluation Conference
Location
Marseille, France
Date
20 June 2022 25 June 2022

Authors

  • KC

    Kenneth Church

  • XC

    Xingyu Cai

  • YB

    Yuchen Bian

Links