Summary of the paper

Title A Study of Word-Classing for MT Reordering
Authors Ananthakrishnan Ramanathan and Karthik Visweswariah
Abstract MT systems typically use parsers to help reorder constituents. However most languages do not have adequate treebank data to learn good parsers, and such training data is extremely time-consuming to annotate. Our earlier work has shown that a reordering model learned from word-alignments using POS tags as features can improve MT performance (Visweswariah et al., 2011). In this paper, we investigate the effect of word-classing on reordering performance using this model. We show that unsupervised word clusters perform somewhat worse but still reasonably well, compared to a part-of-speech (POS) tagger built with a small amount of annotated data; while a richer tag set including case and gender-number-person further improves reordering performance by around 1.2 monolingual BLEU points. While annotating this richer tagset is more complicated than annotating the base tagset, it is much easier than annotating treebank data.
Topics Machine Translation, SpeechToSpeech Translation, Part of speech tagging
Full paper A Study of Word-Classing for MT Reordering
Bibtex @InProceedings{RAMANATHAN12.921,
  author = {Ananthakrishnan Ramanathan and Karthik Visweswariah},
  title = {A Study of Word-Classing for MT Reordering},
  booktitle = {Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC'12)},
  year = {2012},
  month = {may},
  date = {23-25},
  address = {Istanbul, Turkey},
  editor = {Nicoletta Calzolari (Conference Chair) and Khalid Choukri and Thierry Declerck and Mehmet Uğur Doğan and Bente Maegaard and Joseph Mariani and Asuncion Moreno and Jan Odijk and Stelios Piperidis},
  publisher = {European Language Resources Association (ELRA)},
  isbn = {978-2-9517408-7-7},
  language = {english}
 }
Powered by ELDA © 2012 ELDA/ELRA