2019 DialogueNaturalLanguageInferenc: Difference between revisions
Jump to navigation
Jump to search
(ContinuousReplacement) Tag: continuous replacement |
|||
| Line 18: | Line 18: | ||
[[In this paper]], we frame the [[consistency of dialogue agent]]s as [[natural language inference (NLI)]] and create a [[new natural language inference dataset]] called [[Dialogue NLI]]. </s> | [[In this paper]], we frame the [[consistency of dialogue agent]]s as [[natural language inference (NLI)]] and create a [[new natural language inference dataset]] called [[Dialogue NLI]]. </s> | ||
[[We]] propose a [[method]] which demonstrates that a [[model trained]] on [[Dialogue NLI]] can be used to improve the [[consistency of a dialogue model]], and [[evaluate the method]] with [[human evaluation]] and with [[automatic metric]]s on a suite of [[evaluation set]]s designed to [[measure]] a [[dialogue modelâs consistency]]. </s> | [[We]] propose a [[method]] which demonstrates that a [[model trained]] on [[Dialogue NLI]] can be used to improve the [[consistency of a dialogue model]], and [[evaluate the method]] with [[human evaluation]] and with [[automatic metric]]s on a suite of [[evaluation set]]s designed to [[measure]] a [[dialogue modelâs consistency]]. </s> | ||
=== 1 Introduction === | === 1 Introduction === | ||
=== 2 Dialogue Consistency and Natural Language Inference === | === 2 Dialogue Consistency and Natural Language Inference === | ||
=== 3 Dialogue NLI Dataset === | === 3 Dialogue NLI Dataset === | ||
==== 3.1 Triple Generation ==== | ==== 3.1 Triple Generation ==== | ||
==== 3.2 Triple Annotation ==== | ==== 3.2 Triple Annotation ==== | ||
==== 3.3 Statistics ==== | ==== 3.3 Statistics ==== | ||
=== 4 Consistent Dialogue Agents Via Natural Language Inference ==== | === 4 Consistent Dialogue Agents Via Natural Language Inference ==== | ||
=== 5 Experiments === | === 5 Experiments === | ||
==== 5.1 Experiment 1: NLI ==== | ==== 5.1 Experiment 1: NLI ==== | ||
==== 5.2 Experiment 2: Consistency in Dialogue ==== | ==== 5.2 Experiment 2: Consistency in Dialogue ==== | ||
==== 5.3 Experiment 3: Human Evaluation ==== | ==== 5.3 Experiment 3: Human Evaluation ==== | ||
=== 6 Conclusion === | === 6 Conclusion === | ||
Revision as of 04:15, 13 September 2019
- (Welleck et al., 2019) ⇒ Sean Welleck, Jason Weston, Arthur Szlam, and Kyunghyun Cho. (2019). “Dialogue Natural Language Inference.” In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019).
Subject Headings: Natural Language Inference Task; Dialogue Natural Language Inference Task.
Notes
- Pre-print(s): arXiv:1811.00671
Cited By
- Google Scholar: ~ 5 Citations
- Semantic Scholar: ~ 5 Citations
Quotes
Abstract
Consistency is a long standing issue faced by dialogue models. In this paper, we frame the consistency of dialogue agents as natural language inference (NLI) and create a new natural language inference dataset called Dialogue NLI. We propose a method which demonstrates that a model trained on Dialogue NLI can be used to improve the consistency of a dialogue model, and evaluate the method with human evaluation and with automatic metrics on a suite of evaluation sets designed to measure a dialogue modelâs consistency.
1 Introduction
2 Dialogue Consistency and Natural Language Inference
3 Dialogue NLI Dataset
3.1 Triple Generation
3.2 Triple Annotation
3.3 Statistics
4 Consistent Dialogue Agents Via Natural Language Inference =
5 Experiments
5.1 Experiment 1: NLI
5.2 Experiment 2: Consistency in Dialogue
5.3 Experiment 3: Human Evaluation
6 Conclusion
References
;
| Author | volume | Date Value | title | type | journal | titleUrl | doi | note | year | |
|---|---|---|---|---|---|---|---|---|---|---|
| 2019 DialogueNaturalLanguageInferenc | Jason Weston Kyunghyun Cho Sean Welleck Arthur Szlam | Dialogue Natural Language Inference | 2019 |