Type

Conference Proceedings

Authors

David Lewis
Alfredo Maldonado Guerra
Andy Way
Srivastava Ankit
Jinhua Du

Subjects

Linguistics

Topics
controlled languages empirical study machine learning post editing active learning authoring tools statistical machine translation speechto speech translation

An empirical study of segment prioritization for incrementally retrained post-editing-based SMT (2015)

Abstract Post-editing the output of a statistical machine translation (SMT) system to obtain high-quality translation has become an increasingly common application of SMT, which henceforth we refer to as post-editing-based SMT (PE-SMT). PE-SMT is often deployed as an incrementally retrained system that can learn knowledge from human post-editing outputs as early as possible to augment the SMT models to reduce PE time. In this scenario, the order of input segments plays a very important role in reducing the overall PE time. Under the active learning-based (AL) framework, this paper provides an empirical study of several typical segment prioritization methods, namely the cross entropy difference (CED), n-grams, perplexity (PPL) and translation confidence, and verifies their performance on different data sets and language pairs. Experiments in a simulated setting show that the confidence of translations performs best with decreases of 1.72-4.55 points TER absolute on average compared to the sequential PE-based incrementally retrained SMT.
Collections Ireland -> Dublin City University -> Publication Type = Conference or Workshop Item
Ireland -> Dublin City University -> DCU Faculties and Centres = DCU Faculties and Schools: Faculty of Engineering and Computing: School of Computing
Ireland -> Dublin City University -> DCU Faculties and Centres = Research Initiatives and Centres: ADAPT
Ireland -> Dublin City University -> Status = Published
Ireland -> Dublin City University -> Subject = Computer Science: Machine learning

Full list of authors on original publication

David Lewis, Alfredo Maldonado Guerra, Andy Way, Srivastava Ankit, Jinhua Du

Experts in our system

1
David Lewis
Trinity College Dublin
Total Publications: 65
 
2
Alfredo Maldonado Guerra
Trinity College Dublin
Total Publications: 10
 
3
Andy Way
Dublin City University
Total Publications: 229
 
4
Jinhua Du
Dublin City University
Total Publications: 38