Summary of the paper
| Title | Using Linear Interpolation and Weighted Reordering Hypotheses in the Moses System |
|---|---|
| Authors | Marta R. Costa-jussà and José A. R. Fonollosa |
| Abstract | This paper proposes to introducea novel reordering model in the open-source Moses toolkit. The main idea is to provide weighted reordering hypothesesto the SMT decoder.These hypotheses are built using a first-step Ngram-based SMT translation from a source language into a third representation that is calledreordered source language.Each hypothesis has its own weight provided by the Ngram-based decoder.This proposed reordering technique offers a better and more efficient translationwhen compared to both the distance-based and the lexicalized reordering.In addition to this reordering approach, this paper describes a domainadaptation technique which is based on a linear combination of an specificin-domain and an extra out-domain translation models. Results for both approaches are reported in the Arabic-to-English 2008 IWSLT task. When implementing the weighted reorderinghypotheses and the domain adaptation technique in the final translation system,translation results reach improvements up to 2.5 BLEU compared to a standardstate-of-the-art Moses baseline system. |
| Language | Language modelling |
| Topics | Machine Translation, SpeechToSpeech Translation, Statistical and machine learning methods, Language modelling |
Full paper  |
Using Linear Interpolation and Weighted Reordering Hypotheses in the Moses System |
| Bibtex | @InProceedings{RCOSTAJUSS10.23, author = {Marta R. Costa-jussà and José A. R. Fonollosa}, title = {Using Linear Interpolation and Weighted Reordering Hypotheses in the Moses System}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |