Learning to Represent Bilingual Dictionaries

TL;DR

This paper introduces a neural embedding model that uses bilingual dictionaries to improve cross-lingual semantic tasks, demonstrating enhanced performance in reverse dictionary retrieval and paraphrase identification.

Contribution

The paper presents a novel neural model leveraging bilingual dictionaries with multi-task and joint learning strategies for better cross-lingual semantic understanding.

Findings

Effective in cross-lingual reverse dictionary retrieval

Significantly outperforms previous methods in bilingual paraphrase identification

Learning strategies improve model performance with limited resources

Abstract

Bilingual word embeddings have been widely used to capture the similarity of lexical semantics in different human languages. However, many applications, such as cross-lingual semantic search and question answering, can be largely benefited from the cross-lingual correspondence between sentences and lexicons. To bridge this gap, we propose a neural embedding model that leverages bilingual dictionaries. The proposed model is trained to map the literal word definitions to the cross-lingual target words, for which we explore with different sentence encoding techniques. To enhance the learning process on limited resources, our model adopts several critical learning strategies, including multi-task learning on different bridges of languages, and joint learning of the dictionary model with a bilingual word embedding model. Experimental evaluation focuses on two applications. The results of the cross-lingual reverse dictionary retrieval task show our model's promising ability of comprehending bilingual concepts based on descriptions, and highlight the effectiveness of proposed learning strategies in improving performance. Meanwhile, our model effectively addresses the bilingual paraphrase identification problem and significantly outperforms previous approaches.