Improving Word Translation via Two-Stage Contrastive Learning

• URL: http://arxiv.org/abs/2203.08307v5
• Date: Thu, 17 Oct 2024 21:50:37 GMT
• Title: Improving Word Translation via Two-Stage Contrastive Learning
• Authors: Yaoyiran Li, Fangyu Liu, Nigel Collier, Anna Korhonen, Ivan Vulić,
• Abstract summary: We propose a robust and effective two-stage contrastive learning framework for the BLI task. Comprehensive experiments on standard BLI datasets for diverse languages show substantial gains achieved by our framework.
• Score: 46.71404992627519
• License:
• Abstract: Word translation or bilingual lexicon induction (BLI) is a key cross-lingual task, aiming to bridge the lexical gap between different languages. In this work, we propose a robust and effective two-stage contrastive learning framework for the BLI task. At Stage C1, we propose to refine standard cross-lingual linear maps between static word embeddings (WEs) via a contrastive learning objective; we also show how to integrate it into the self-learning procedure for even more refined cross-lingual maps. In Stage C2, we conduct BLI-oriented contrastive fine-tuning of mBERT, unlocking its word translation capability. We also show that static WEs induced from the `C2-tuned' mBERT complement static WEs from Stage C1. Comprehensive experiments on standard BLI datasets for diverse languages and different experimental setups demonstrate substantial gains achieved by our framework. While the BLI method from Stage C1 already yields substantial gains over all state-of-the-art BLI methods in our comparison, even stronger improvements are met with the full two-stage framework: e.g., we report gains for 112/112 BLI setups, spanning 28 language pairs.

Related papers

• Embracing Language Inclusivity and Diversity in CLIP through Continual Language Learning [58.92843729869586]
  Vision-language pre-trained models (VL-PTMs) have advanced multimodal research in recent years, but their mastery in a few languages like English restricts their applicability in broader communities. We propose to extend VL-PTMs' language capacity by continual language learning (CLL), where a model needs to update its linguistic knowledge incrementally without suffering from catastrophic forgetting (CF) We construct a CLL benchmark covering 36 languages based on MSCOCO and XM3600 datasets and then evaluate multilingual image-text retrieval performance.
  arXiv  Detail & Related papers  (2024-01-30T17:14:05Z)
• On Bilingual Lexicon Induction with Large Language Models [81.6546357879259]
  We examine the potential of the latest generation of Large Language Models for the development of bilingual lexicons. We study 1) zero-shot prompting for unsupervised BLI and 2) few-shot in-context prompting with a set of seed translation pairs. Our work is the first to demonstrate strong BLI capabilities of text-to-text mLLMs.
  arXiv  Detail & Related papers  (2023-10-21T12:43:27Z)
• VECO 2.0: Cross-lingual Language Model Pre-training with Multi-granularity Contrastive Learning [56.47303426167584]
  We propose a cross-lingual pre-trained model VECO2.0 based on contrastive learning with multi-granularity alignments. Specifically, the sequence-to-sequence alignment is induced to maximize the similarity of the parallel pairs and minimize the non-parallel pairs. token-to-token alignment is integrated to bridge the gap between synonymous tokens excavated via the thesaurus dictionary from the other unpaired tokens in a bilingual instance.
  arXiv  Detail & Related papers  (2023-04-17T12:23:41Z)
• Bag of Tricks for Effective Language Model Pretraining and Downstream Adaptation: A Case Study on GLUE [93.98660272309974]
  This report briefly describes our submission Vega v1 on the General Language Understanding Evaluation leaderboard. GLUE is a collection of nine natural language understanding tasks, including question answering, linguistic acceptability, sentiment analysis, text similarity, paraphrase detection, and natural language inference. With our optimized pretraining and fine-tuning strategies, our 1.3 billion model sets new state-of-the-art on 4/9 tasks, achieving the best average score of 91.3.
  arXiv  Detail & Related papers  (2023-02-18T09:26:35Z)
• Multilingual Sentence Transformer as A Multilingual Word Aligner [15.689680887384847]
  We investigate whether multilingual sentence Transformer LaBSE is a strong multilingual word aligner. Experiment results on seven language pairs show that our best aligner outperforms previous state-of-the-art models of all varieties. Our aligner supports different language pairs in a single model, and even achieves new state-of-the-art on zero-shot language pairs that does not appear in the finetuning process.
  arXiv  Detail & Related papers  (2023-01-28T09:28:55Z)
• Improving Bilingual Lexicon Induction with Cross-Encoder Reranking [31.142790337451366]
  We propose a novel semi-supervised post-hoc reranking method termed BLICEr (BLI with Cross-Encoder Reranking) The key idea is to 'extract' cross-lingual lexical knowledge from mPLMs, and then combine it with the original CLWEs. BLICEr establishes new results on two standard BLI benchmarks spanning a wide spectrum of diverse languages.
  arXiv  Detail & Related papers  (2022-10-30T21:26:07Z)
• Exposing Cross-Lingual Lexical Knowledge from Multilingual Sentence Encoders [85.80950708769923]
  We probe multilingual language models for the amount of cross-lingual lexical knowledge stored in their parameters, and compare them against the original multilingual LMs. We also devise a novel method to expose this knowledge by additionally fine-tuning multilingual models. We report substantial gains on standard benchmarks.
  arXiv  Detail & Related papers  (2022-04-30T13:23:16Z)
• Combining Static Word Embeddings and Contextual Representations for Bilingual Lexicon Induction [19.375597786174197]
  We propose a simple yet effective mechanism to combine the static word embeddings and the contextual representations. We test the combination mechanism on various language pairs under the supervised and unsupervised BLI benchmark settings.
  arXiv  Detail & Related papers  (2021-06-06T10:31:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.