Natural Language Generation for Dialogue Systems: SIGDIAL 2017 Special Session

NLG4DS 2017


Artificial Intelligence



While natural language generation (NLG) for dialogue interaction has been a long-standing research topic, there has been a recent explosion of work due to industrial interest in conversational assistants such as Alexa, Siri, Cortana and Google Assistant. Recent advances in the field of deep learning together with the availability of large corpora of human dialogues from social media has also contributed to new research techniques for language generation. However, to date, neural methods have not been able to replicate much of the rich dialogue phenomena targeted by previous rule-based, statistical and data-driven approaches for language generation for dialogue.
Therefore we invite submissions for this special session at SIGDIAL 2017.
The deadline for paper submission is: 18th April 2017
TOPICS
We invite submissions which address specific issues including but not limited to:
- Generation in the context of a dialogue with appropriate use of anaphoric forms, such as pronouns and ellipses;
- Generation of turns where information is structured using rhetorical relations, as in the case of recommendations or other persuasive genres;
- Selection and organization of content in a dialogue turn;
- Sentence planning and lexical choice for dialogue interaction;
- Evaluation of language generation for dialogue systems;
- Corpus-based analyses of human-human dialogue to inform NLG for dialogue systems;
- Critical comparison between capabilities of different kinds of models.
- Providing and investigating new resources, such as data sets and tools.
- We also welcome submissions which make use of the new E2E NLG challenge data set.