Unsupervised Vocabulary Adaptation for Morph-based Language Models

@inproceedings{Mansikkaniemi2012UnsupervisedVA,
  title={Unsupervised Vocabulary Adaptation for Morph-based Language Models},
  author={Andr{\'e} Mansikkaniemi and Mikko Kurimo},
  booktitle={WLM@NAACL-HLT},
  year={2012}
}
Modeling of foreign entity names is an important unsolved problem in morpheme-based modeling that is common in morphologically rich languages. In this paper we present an unsupervised vocabulary adaptation method for morph-based speech recognition. Foreign word candidates are detected automatically from in-domain text through the use of letter n-gram perplexity. Over-segmented foreign entity names are restored to their base forms in the morph-segmented in-domain text for easier and more… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.

References

Publications referenced by this paper.
Showing 1-3 of 3 references

2005.Detection of Foreign Words and Names in Written Text

  • B. Ahmed
  • 2005
1 Excerpt

Similar Papers

Loading similar papers…