Work

Learning Topic Representation for SMT with Neural Networks

Year: 2014

Type: conference-paper

Abstract: Statistical Machine Translation (SMT) usually utilizes contextual information to disambiguate translation candidates. However, it is often limited to contexts within sentence boundaries, hence broader topical information cannot be leveraged. In this paper, we propose a novel approach to learning topic representation for paral-lel data using a neural network architec-ture, where abundant topical contexts are embedded via topic relevant monolingual data. By associating each translation rule with the topic representation, topic rele-vant rules are selected according to the dis-tributional similarity with the source text during SMT decoding. Experimental re-sults show that our method significantly improves translation accuracy in the NIST Chinese-to-English translation task com-pared to a state-of-the-art baseline. 1

Source: Proceedings of the conference - Association for Computational Linguistics. Meeting

DOI: 10.3115/v1/p14-1013

Authors: Lei Cui, Dongdong Zhang, Shujie Liu, Qiming Chen, Mu Li, Ming Zhou, Muyun Yang

Institutions: Harbin Institute of Technology, Microsoft (United States)

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W2122993045

FWCI: 1.706

Cites: 41

Cited by: 17

Related to: 10