Work

Topic Modeling-based Domain Adaptation for System Combination

Year: 2012

Type: conference-paper

Abstract: This paper gives the system description of the domain adaptation team of Dublin City University for our participation in the system combination task in the Second Workshop on Applying Machine Learning Techniques to Optimise the Division of Labour in Hybrid MT (ML4HMT-12). We used the results of unsupervised document classification as meta information to the system combination module. For the Spanish-English data, our strategy achieved 26.33 BLEU points, 0.33 BLEU points absolute improvement over the standard confusion-network-based system combination. This was the best score in terms of BLEU among six participants in ML4HMT-12.

Source: Dublin City University Open Access Institutional Repository (Dublin City University)

Authors: Tsuyoshi Okita, Antonio Toral, Josef van Genabith

Institution: Dublin City University

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: European Commission, Science Foundation Ireland, Dublin City University, National Natural Science Foundation of China