Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) 2020
DOI: 10.18653/v1/2020.emnlp-main.739
|View full text |Cite
|
Sign up to set email alerts
|

Like hiking? You probably enjoy nature: Persona-grounded Dialog with Commonsense Expansions

Abstract: Existing persona-grounded dialog models often fail to capture simple implications of given persona descriptions, something which humans are able to do seamlessly. For example, state-of-the-art models cannot infer that interest in hiking might imply love for nature or longing for a break. In this paper, we propose to expand available persona sentences using existing commonsense knowledge bases and paraphrasing resources to imbue dialog models with access to an expanded and richer set of persona descriptions. Ad… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
39
0
1

Year Published

2021
2021
2025
2025

Publication Types

Select...
4
1
1

Relationship

1
5

Authors

Journals

citations
Cited by 47 publications
(40 citation statements)
references
References 32 publications
0
39
0
1
Order By: Relevance
“…Firstly, using the gradient-based decoding approach with retrieved stories (PABST) works significantly better than using distant supervision with stories data (PSEUDO and MULTITASK). Secondly, background stories provide sufficient detail for an engaging conversation compared to DIS-CCHOICE which expands persona attributes using commonsense knowledge (Majumder et al, 2020). Finally, we also observe that PABST performs worse when we do not use the consistency constraint (w/o DNLI).…”
Section: Human Evaluationmentioning
confidence: 82%
See 4 more Smart Citations
“…Firstly, using the gradient-based decoding approach with retrieved stories (PABST) works significantly better than using distant supervision with stories data (PSEUDO and MULTITASK). Secondly, background stories provide sufficient detail for an engaging conversation compared to DIS-CCHOICE which expands persona attributes using commonsense knowledge (Majumder et al, 2020). Finally, we also observe that PABST performs worse when we do not use the consistency constraint (w/o DNLI).…”
Section: Human Evaluationmentioning
confidence: 82%
“…Given dialog history h and persona C consisting of several (typically 3-5, example shown in Figure 1) attributes, our goal is to construct a dialog response x. Our underlying model is based on the discrete persona attribute choice model from Majumder et al (2020). To generate a dialog utterance x, we first sample a persona attribute c ∼ p(c|h) conditioned on the dialog history h. x is then generated conditioned on the dialog history and the chosen persona attribute.…”
Section: Unsupervised Persona Enrichment With Background Storiesmentioning
confidence: 99%
See 3 more Smart Citations