%Aigaion2 BibTeX export from Idiap Publications
%Thursday 21 November 2024 12:44:10 PM

@INPROCEEDINGS{Cartoni_BUCC_2011,
         author = {Cartoni, Bruno and Zufferey, Sandrine and Meyer, Thomas and Popescu-Belis, Andrei},
       keywords = {Comparable Corpora, Corpora, discourse connectives, Homogeneity, Measures, Parallel Corpora, Similarity},
       projects = {Idiap, COMTIS},
          month = jun,
          title = {How Comparable are Parallel Corpora? Measuring the Distribution of General Vocabulary and Connectives},
      booktitle = {Proceedings of 4th Workshop on Building and Using Comparable Corpora},
           year = {2011},
          pages = {78--86},
       location = {Portland, OR},
   organization = {ACL},
       abstract = {In this paper, we question the homogeneity of a large parallel corpus by measuring the similarity between various sub-parts. We compare results obtained using a general measure of lexical similarity based on c2 and by counting the number of discourse connectives. We argue that discourse connectives provide a more sensitive measure, revealing differences that are not visible with the general measure. We also provide evidence for the existence of specific characteristics defining translated texts as opposed to nontranslated ones, due to a universal tendency for explicitation.},
            pdf = {https://publications.idiap.ch/attachments/papers/2011/Cartoni_BUCC_2011.pdf}
}