Cross-lingual Contextualized Phrase Retrieval

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Li, Huayang, Cai, Deng, Qu, Zhi, Cui, Qu, Kamigaito, Hidetaka, Liu, Lemao, Watanabe, Taro
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916423031324672
author Li, Huayang
Cai, Deng
Qu, Zhi
Cui, Qu
Kamigaito, Hidetaka
Liu, Lemao
Watanabe, Taro
author_facet Li, Huayang
Cai, Deng
Qu, Zhi
Cui, Qu
Kamigaito, Hidetaka
Liu, Lemao
Watanabe, Taro
contents Phrase-level dense retrieval has shown many appealing characteristics in downstream NLP tasks by leveraging the fine-grained information that phrases offer. In our work, we propose a new task formulation of dense retrieval, cross-lingual contextualized phrase retrieval, which aims to augment cross-lingual applications by addressing polysemy using context information. However, the lack of specific training data and models are the primary challenges to achieve our goal. As a result, we extract pairs of cross-lingual phrases using word alignment information automatically induced from parallel sentences. Subsequently, we train our Cross-lingual Contextualized Phrase Retriever (CCPR) using contrastive learning, which encourages the hidden representations of phrases with similar contexts and semantics to align closely. Comprehensive experiments on both the cross-lingual phrase retrieval task and a downstream task, i.e, machine translation, demonstrate the effectiveness of CCPR. On the phrase retrieval task, CCPR surpasses baselines by a significant margin, achieving a top-1 accuracy that is at least 13 points higher. When utilizing CCPR to augment the large-language-model-based translator, it achieves average gains of 0.7 and 1.5 in BERTScore for translations from X=>En and vice versa, respectively, on WMT16 dataset. Our code and data are available at \url{https://github.com/ghrua/ccpr_release}.
format Preprint
id arxiv_https___arxiv_org_abs_2403_16820
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Cross-lingual Contextualized Phrase Retrieval
Li, Huayang
Cai, Deng
Qu, Zhi
Cui, Qu
Kamigaito, Hidetaka
Liu, Lemao
Watanabe, Taro
Computation and Language
Phrase-level dense retrieval has shown many appealing characteristics in downstream NLP tasks by leveraging the fine-grained information that phrases offer. In our work, we propose a new task formulation of dense retrieval, cross-lingual contextualized phrase retrieval, which aims to augment cross-lingual applications by addressing polysemy using context information. However, the lack of specific training data and models are the primary challenges to achieve our goal. As a result, we extract pairs of cross-lingual phrases using word alignment information automatically induced from parallel sentences. Subsequently, we train our Cross-lingual Contextualized Phrase Retriever (CCPR) using contrastive learning, which encourages the hidden representations of phrases with similar contexts and semantics to align closely. Comprehensive experiments on both the cross-lingual phrase retrieval task and a downstream task, i.e, machine translation, demonstrate the effectiveness of CCPR. On the phrase retrieval task, CCPR surpasses baselines by a significant margin, achieving a top-1 accuracy that is at least 13 points higher. When utilizing CCPR to augment the large-language-model-based translator, it achieves average gains of 0.7 and 1.5 in BERTScore for translations from X=>En and vice versa, respectively, on WMT16 dataset. Our code and data are available at \url{https://github.com/ghrua/ccpr_release}.
title Cross-lingual Contextualized Phrase Retrieval
topic Computation and Language
url https://arxiv.org/abs/2403.16820