| 1 |
Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little Cost
|
|
|
|
In: ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics ; https://hal.archives-ouvertes.fr/hal-03613101 ; ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, May 2022, Dublin, Ireland (2022)
|
|
BASE
|
|
Show details
|
|
|
| 2 |
Imputing out-of-vocabulary embeddings with LOVE makes language models robust with little cost
|
|
|
|
In: ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics ; https://hal.archives-ouvertes.fr/hal-03613101 ; ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, May 2022, Dublin, Ireland (2022)
|
|
Abstract:
International audience ; State-of-the-art NLP systems represent inputs with word embeddings, but these are brittle when faced with Out-of-Vocabulary (OOV) words. To address this issue, we follow the principle of mimick-like models to generate vectors for unseen words, by learning the behavior of pre-trained embeddings using only the surface form of words. We present a simple contrastive learning framework, LOVE, which extends the word representation of an existing pre-trained language model (such as BERT), and makes it robust to OOV with few additional parameters. Extensive evaluations demonstrate that our lightweight model achieves similar or even better performances than prior competitors, both on original datasets and on corrupted variants. Moreover, it can be used in a plug-and-play fashion with FastText and BERT, where it significantly improves their robustness.
|
|
Keyword:
[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]; Language models; Out-of-vocabulary OOV words; Word embeddings
|
|
URL: https://hal.archives-ouvertes.fr/hal-03613101
https://hal.archives-ouvertes.fr/hal-03613101/document
https://hal.archives-ouvertes.fr/hal-03613101/file/Imputing%20OOV%20Embeddings%20with%20LOVE.pdf
|
|
BASE
|
|
Hide details
|
|
|
| 3 |
The Vagueness of Vagueness in Noun Phrases
|
|
|
|
In: International Conference on Automated Knowledge Base Construction (AKBC) ; https://hal-imt.archives-ouvertes.fr/hal-03344675 ; International Conference on Automated Knowledge Base Construction (AKBC), 2021, online, United States (2021)
|
|
BASE
|
|
Show details
|
|
|
| 4 |
Platypus – A Multilingual Question Answering Platform for Wikidata
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-01730479 ; [Technical Report] LIP - ENS Lyon. 2018 (2018)
|
|
BASE
|
|
Show details
|
|
|
| 5 |
Demoing Platypus – A Multilingual Question Answering Platform for Wikidata
|
|
|
|
In: ESWC 2018 - Extended Semantic Web Conference ; https://hal.archives-ouvertes.fr/hal-01824972 ; ESWC 2018 - Extended Semantic Web Conference, Jun 2018, Heracklion, Greece. pp.1-5, ⟨10.1007/978-3-319-98192-5_21⟩ (2018)
|
|
BASE
|
|
Show details
|
|
|
| 6 |
Big Data Methods for Computational Linguistics
|
|
|
|
In: ISSN: 1053-1238 ; Bulletin of the Technical Committee on Data Engineering ; https://hal.archives-ouvertes.fr/hal-01122699 ; Bulletin of the Technical Committee on Data Engineering, IEEE Computer Society, 2012, pp.10 (2012)
|
|
BASE
|
|
Show details
|
|
|
|
|
