Zero-shot transfer for implicit discourse relation classification
This work addresses the problem of cross-lingual discourse analysis for languages lacking annotated resources, though it is incremental as it builds on existing transfer learning methods.
The paper tackled the challenge of implicit discourse relation classification across languages with limited annotated data by developing a zero-shot transfer learning system that uses only English training data and unannotated parallel text for target languages, achieving good results on seven languages in the TED-MDB corpus.
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.