English

Zero-shot transfer for implicit discourse relation classification

Computation and Language 2019-07-31 v1

Abstract

Automatically classifying the relation between sentences in a discourse is a challenging task, in particular when there is no overt expression of the relation. It becomes even more challenging by the fact that annotated training data exists only for a small number of languages, such as English and Chinese. We present a new system using zero-shot transfer learning for implicit discourse relation classification, where the only resource used for the target language is unannotated parallel text. This system is evaluated on the discourse-annotated TED-MDB parallel corpus, where it obtains good results for all seven languages using only English training data.

Keywords

Cite

@article{arxiv.1907.12885,
  title  = {Zero-shot transfer for implicit discourse relation classification},
  author = {Murathan Kurfalı and Robert Östling},
  journal= {arXiv preprint arXiv:1907.12885},
  year   = {2019}
}

Comments

to be presented at SIGDIAL 2019

R2 v1 2026-06-23T10:34:43.693Z