Work

Character-based Neural Machine Translation

Year: 2016

Type: conference-paper

Abstract: Neural Machine Translation (MT) has reached state-of-the-art results.However, one of the main challenges that neural MT still faces is dealing with very large vocabularies and morphologically rich languages.In this paper, we propose a neural MT system using character-based embeddings in combination with convolutional and highway layers to replace the standard lookup-based word representations.The resulting unlimited-vocabulary and affixaware source word embeddings are tested in a state-of-the-art neural MT based on an attention-based bidirectional recurrent neural network.The proposed MT scheme provides improved results even when the source language is not morphologically rich.Improvements up to 3 BLEU points are obtained in the German-English WMT task.

Source: Annual Meeting of the Association for Computational Linguistics (ACL)

DOI: 10.18653/v1/p16-2058

Authors: Marta R. Costa-jussà, José A. R. Fonollosa

Institution: Universitat Politècnica de Catalunya

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: European Commission, Ministerio de Economía y Competitividad

Awards: G2888922458, G6344676564