MEANT 2.0: Accurate semantic MT evaluation for any output language

@inproceedings{Lo2017MEANT2A,
  title={MEANT 2.0: Accurate semantic MT evaluation for any output language},
  author={Chi-kiu Lo},
  booktitle={WMT},
  year={2017}
}
We describe a new version of MEANT, which participated in the metrics task of the Second Conference on Machine Translation (WMT 2017). MEANT 2.0 uses idfweighted distributional ngram accuracy to determine the phrasal similarity of semantic role fillers and yields better correlations with human judgments of translation quality than earlier versions. The improved phrasal similarity enables a subversion of MEANT to accurately evaluate translation adequacy for any output language, even languages… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-10 of 13 references

Results of the WMT14 Metrics Shared Task

  • Matous Machacek, Ondrej Bojar.
  • Proceedings of the Ninth Workshop on Statistical…
  • 2014
Highly Influential
5 Excerpts

Results of the WMT15 Metrics Shared Task

  • Miloš Stanojević, Amir Kamran, Philipp Koehn, Ondřej Bojar.
  • Proceedings of the Tenth Workshop on Statistical…
  • 2015
3 Excerpts

Unsupervised vs

  • Chi-kiu Lo, Dekai Wu.
  • supervised weight estimation for semantic MT…
  • 2012
1 Excerpt

Similar Papers

Loading similar papers…