Summary of the paper
| Title | Towards Improving English-Latvian Translation: A System Comparison and a New Rescoring Feature |
|---|---|
| Authors | Maxim Khalilov, José A. R. Fonollosa, Inguna Skadina, Edgars Brālītis and Lauma Pretkalnina |
| Abstract | Translation into the languages with relatively free word order has received alot less attention than translation into fixed word order languages (English),or into analytical languages (Chinese). At the same time this translation taskis found among the most difficult challenges for machine translation (MT), andintuitively it seems that there is some space in improvement intending toreflect the free word order structure of the target language.This paper presents a comparative study of two alternative approaches tostatistical machine translation (SMT) and their application to a task ofEnglish-to-Latvian translation. Furthermore, a novel feature intending toreflect the relatively free word order scheme of the Latvian language isproposed and successfully applied on the n-best list rescoring step. Movingbeyond classical automatic scores of translation quality that are classicallypresented in MT research papers, we contribute presenting a manual erroranalysis of MT systems output that helps to shed light on advantages anddisadvantages of the SMT systems under consideration. |
| Language | |
| Topics | Machine Translation, SpeechToSpeech Translation, Language modelling |
Full paper  |
Towards Improving English-Latvian Translation: A System Comparison and a New Rescoring Feature |
| Bibtex | @InProceedings{KHALILOV10.228, author = {Maxim Khalilov, José A. R. Fonollosa, Inguna Skadina, Edgars Brālītis and Lauma Pretkalnina}, title = {Towards Improving English-Latvian Translation: A System Comparison and a New Rescoring Feature}, 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} } |