@inproceedings{lapshinova-koltunski-etal-2019-analysing,
    title = "Analysing Coreference in Transformer Outputs",
    author = "Lapshinova-Koltunski, Ekaterina  and
      Espa\~na-Bonet, Cristina  and
      van Genabith, Josef",
    editor = "Popescu-Belis, Andrei  and
      Lo\'aiciga, Sharid  and
      Hardmeier, Christian  and
      Xiong, Deyi",
    booktitle = "Proceedings of the Fourth Workshop on Discourse in Machine Translation (DiscoMT 2019)",
    month = nov,
    year = "2019",
    address = "Hong Kong, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/build-pipeline-with-new-library/D19-6501/",
    doi = "10.18653/v1/D19-6501",
    pages = "1--12",
    abstract = "We analyse coreference phenomena in three neural machine translation systems trained with different data settings with or without access to explicit intra- and cross-sentential anaphoric information. We compare system performance on two different genres: news and TED talks. To do this, we manually annotate (the possibly incorrect) coreference chains in the MT outputs and evaluate the coreference chain translations. We define an error typology that aims to go further than pronoun translation adequacy and includes types such as incorrect word selection or missing words. The features of coreference chains in automatic translations are also compared to those of the source texts and human translations. The analysis shows stronger potential translationese effects in machine translated outputs than in human translations."
}