Modeling Sequential Sentence Relation to Improve Cross-lingual Dense Retrieval

TL;DR

This paper introduces MSM, a multilingual pre-trained language model that models sequential sentence relations to enhance cross-lingual dense retrieval, significantly outperforming existing models on multiple tasks.

Contribution

The paper proposes a novel masked sentence model (MSM) that captures universal sequential sentence relations across languages for improved cross-lingual retrieval.

Findings

MSM outperforms existing models on four cross-lingual retrieval tasks.

Model effectively captures sentence order information across languages.

Demonstrates stronger cross-lingual retrieval capabilities.

Abstract

Recently multi-lingual pre-trained language models (PLM) such as mBERT and XLM-R have achieved impressive strides in cross-lingual dense retrieval. Despite its successes, they are general-purpose PLM while the multilingual PLM tailored for cross-lingual retrieval is still unexplored. Motivated by an observation that the sentences in parallel documents are approximately in the same order, which is universal across languages, we propose to model this sequential sentence relation to facilitate cross-lingual representation learning. Specifically, we propose a multilingual PLM called masked sentence model (MSM), which consists of a sentence encoder to generate the sentence representations, and a document encoder applied to a sequence of sentence vectors from a document. The document encoder is shared for all languages to model the universal sequential sentence relation across languages. To train the model, we propose a masked sentence prediction task, which masks and predicts the sentence vector via a hierarchical contrastive loss with sampled negatives. Comprehensive experiments on four cross-lingual retrieval tasks show MSM significantly outperforms existing advanced pre-training models, demonstrating the effectiveness and stronger cross-lingual retrieval capabilities of our approach. Code and model are available at https://github.com/shunyuzh/MSM.