Coerced Markov Models For Cross-Lingual Lexical-Tag Relations

Pascale Fung, Dekai WuColumbia 1995 · DOI

Abstract

We introduce the Coerced Markov Model (CMM) to model the relationship between the lexical sequence of a source language and the tag sequence of a target language, with the objective of constraining search in statistical transfer-based machine translation systems. CMMs differ from Hidden Markov Models in that state sequence assignments can take on values coerced from external sources. Given a Chinese sentence, a CMM can be used to predict the corresponding English tag sequence, thus constraining the English lexical sequence produced by a translation model. The CMM can also be used to score competing translation hypotheses in N-best models. Three fundamental problems for CMM designed are discussed. Their solutions lead to the training and testing stages of CMM.
BibTeX
@inproceedings{fung1995coerced,
  author = {Pascale Fung and Dekai Wu},
  title = {{Coerced Markov Models For Cross-Lingual Lexical-Tag Relations}},
  booktitle = {Columbia},
  year = {1995},
  doi = {10.7916/d86117mk},
}

Loading related content...

Figure