Cross-lingual text similarity exploiting neural machine translation models
Author:
- 18 March 2020
- journal article
- research article
- Published by SAGE Publications in Journal of Information Science
- Vol. 47 (3) , 404-418
Abstract
This article studies cross-lingual text similarity using neural machine translation models. A straightforward approach based on machine translation is to use translated text so as to make the problem monolingual. Another possible approach is to use intermediate states of machine translation models as recently proposed in the related work, which could avoid propagation of translation errors. We aim at improving both approaches independently and then combine the two types of information, that is, translations and intermediate states, in a learning-to-rank framework to compute cross-lingual text similarity. To evaluate the effectiveness and generalisability of our approach, we conduct empirical experiments on English–Japanese and English–Hindi translation corpora for a cross-lingual sentence retrieval task. It is demonstrated that our approach using translations and intermediate states outperforms other neural network–based approaches and is even comparable with a strong baseline based on a state-of-the-art machine translation system.Keywords
Funding Information
- Japan Science and Technology Agency (18K11558)
- Ministry of Education, Culture, Sports, Science and Technology
This publication has 20 references indexed in Scilit:
- Exploring Neural Translation Models for Cross-Lingual Text Similarity2018
- A resource-light method for cross-lingual semantic textual similarityKnowledge-Based Systems, 2018
- Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot TranslationTransactions of the Association for Computational Linguistics, 2017
- Continuous space models for CLIRInformation Processing & Management, 2017
- News Across Languages - Cross-Lingual Document Similarity and Event TrackingJournal of Artificial Intelligence Research, 2016
- Learning principled bilingual mappings of word embeddings while preserving monolingual invariance2016
- Multilingual Information Retrieval2012
- Learning to Rank for Information RetrievalFoundations and Trends® in Information Retrieval, 2009
- Introduction to Information Retrieval2008
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006