Search for: All records | NSF Public Access

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

Target-Guided Dialogue Response Generation Using Commonsense and Data Augmentation

https://doi.org/10.18653/v1/2022.findings-naacl.97

Gupta, Prakhar ; Jhamtani, Harsh ; Bigham, Jeffrey ( January 2022 , Proceedings of NAACL 2022)

Full Text Available
InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning

Prakhar Gupta, Cathy Jiao ( January 2022 , Proceedings of EMNLP 2022)

Full Text Available
Synthesizing Adversarial Negative Responses for Robust Response Ranking and Evaluation

Prakhar Gupta, Yulia Tsvetkov ( January 2021 , Computational linguistics Association for Computational Linguistics)

Full Text Available
Investigating Evaluation of Open-Domain Dialogue Systems With Human Generated Multiple References

Prakhar Gupta, Shikib Mehri ( September 2019 , SIGDIAL 2020)

The aim of this paper is to mitigate the shortcomings of automatic evaluation of open-domain dialog systems through multi-reference evaluation. Existing metrics have been shown to correlate poorly with human judgement, particularly in open-domain dialog. One alternative is to collect human annotations for evaluation, which can be expensive and time consuming. To demonstrate the effectiveness of multi-reference evaluation, we augment the test set of DailyDialog with multiple references. A series of experiments show that the use of multiple references results in improved correlation between several automatic metrics and human judgement for both the quality and the diversity of system output.
more » « less
Full Text Available