How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation

Lowe, Ryan; Noseworthy, Mike; Charlin, Laurent; Pineau, Joelle; Liu, Chia-Wei; Serban, Iulian V.

doi:10.18653/v1/D16-1230

Record: found
Abstract: not found
Conference Proceedings: not found

How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation

proceedings-article

Author(s): Chia-Wei Liu , Ryan Lowe , Iulian Serban , Mike Noseworthy , Laurent Charlin , Joelle Pineau

Publication date (Print): 2016

Conference name: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

Conference date: December, 2016 - December, 2016

Read this article at

ScienceOpenPublisher

Bookmark

There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

Related collections

Author and article information

Conference

Publication date (Print): 2016

Pages: 2122-2132

Article

DOI: 10.18653/v1/D16-1230

SO-VID: 6c389f13-d1b5-4d7c-8bf1-abdb334850a0

Conference name: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

Conference location: Austin, Texas

Conference date: December, 2016 - December, 2016

History

Data availability:

How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation

Read this article at

Related collections

Metrics and Research Assessment

Author and article information

Conference

Article

History

Comments

Comment on this article

Similar content 4,393

Cited by 87