Generating Contrastive Referring Expressions

Martin Villalba, Christoph Teichmann, and Alexander Koller

In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL), Vancouver, 2017.

The referring expressions (REs) produced by a natural language generation (NLG) system can be misunderstood by the hearer, even when they are semantically correct. In an interactive setting, the NLG system can try to recognize such misunderstandings and correct them. We present an algorithm for generating corrective REs that use contrastive focus ("no, the BLUE button") to emphasize the information the hearer most likely misunderstood. We show empirically that these contrastive REs are preferred over REs without contrast marking.

Download: Download

BibTeX Entry
@InProceedings{contrastive-re-17,
	author = {Martin Villalba  and  Christoph Teichmann  and
		Alexander Koller},
	title = {Generating Contrastive Referring Expressions},
	booktitle = {Proceedings of the 55th Annual Meeting of the
		Association for Computational Linguistics (ACL)},
	year = {2017},
	address = {Vancouver}
}

Back: Publications