MEXMA: Token-level objectives improve sentence representations
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909319827554304 |
|---|---|
| author | Janeiro, João Maria Piwowarski, Benjamin Gallinari, Patrick Barrault, Loïc |
| author_facet | Janeiro, João Maria Piwowarski, Benjamin Gallinari, Patrick Barrault, Loïc |
| contents | Current pre-trained cross-lingual sentence encoders approaches use sentence-level objectives only. This can lead to loss of information, especially for tokens, which then degrades the sentence representation. We propose MEXMA, a novel approach that integrates both sentence-level and token-level objectives. The sentence representation in one language is used to predict masked tokens in another language, with both the sentence representation and all tokens directly updating the encoder. We show that adding token-level objectives greatly improves the sentence representation quality across several tasks. Our approach outperforms current pre-trained cross-lingual sentence encoders on bi-text mining as well as several downstream tasks. We also analyse the information encoded in our tokens, and how the sentence representation is built from them. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_12737 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MEXMA: Token-level objectives improve sentence representations Janeiro, João Maria Piwowarski, Benjamin Gallinari, Patrick Barrault, Loïc Computation and Language Artificial Intelligence Current pre-trained cross-lingual sentence encoders approaches use sentence-level objectives only. This can lead to loss of information, especially for tokens, which then degrades the sentence representation. We propose MEXMA, a novel approach that integrates both sentence-level and token-level objectives. The sentence representation in one language is used to predict masked tokens in another language, with both the sentence representation and all tokens directly updating the encoder. We show that adding token-level objectives greatly improves the sentence representation quality across several tasks. Our approach outperforms current pre-trained cross-lingual sentence encoders on bi-text mining as well as several downstream tasks. We also analyse the information encoded in our tokens, and how the sentence representation is built from them. |
| title | MEXMA: Token-level objectives improve sentence representations |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2409.12737 |