Filtering Antonymous, Trend-Contrasting, and Polarity-Dissimilar Distributional Paraphrases for Improving Statistical Machine Translation

@inproceedings{Marton2011FilteringAT,
  title={Filtering Antonymous, Trend-Contrasting, and Polarity-Dissimilar Distributional Paraphrases for Improving Statistical Machine Translation},
  author={Yuval Marton and Ahmed El Kholy and Nizar Habash},
  booktitle={WMT@EMNLP},
  year={2011}
}
Paraphrases are useful for statistical machine translation (SMT) and natural language processing tasks. Distributional paraphrase generation is independent of parallel texts and syntactic parses, and hence is suitable also for resource-poor languages, but tends to erroneously rank antonyms, trend-contrasting, and polarity-dissimilar candidates as good paraphrases. We present here a novel method for improving distributional paraphrasing by filtering out such candidates. We evaluate it in… CONTINUE READING
7 Citations
48 References
Similar Papers

Similar Papers

Loading similar papers…