Student or educator? Sign up with your school email and get 6 months of Pro free.

The DOI matches its Crossref record; 40 of the 42 references it cites were found in a registry or an index.

What makes a good conversation? How controllable attributes affect human judgments

Open access
See, Abigail, Roller, Stephen, Kiela, Douwe, Weston, Jason·2019·Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

Abstract

Abigail See, Stephen Roller, Douwe Kiela, Jason Weston. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 2019.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.18653/v1/n19-1170

Cites

40 of 42 references verified0 citation errors · 2 not checkable

Statistics

Figures

Figure 1 We manipulate four low-level attributes and measure their effect on human judgments of individual conversational aspects, as well as overall quality.
Figure 1 We manipulate four low-level attributes and measure their effect on human judgments of individual conversational aspects, as well as overall quality.CC-BY · From the PDF
Figure 2 Controlling question-asking via Conditional Training (CT). See Appendix F for exact numbers.
Figure 2 Controlling question-asking via Conditional Training (CT). See Appendix F for exact numbers.CC-BY · From the PDF
Figure 3 Calibrated human judgments of engagingness for the baselines and best controlled models (left); for different specificity control settings (middle); and for different question-asking control settings (right).
Figure 3 Calibrated human judgments of engagingness for the baselines and best controlled models (left); for different specificity control settings (middle); and for different question-asking control settings (right).CC-BY · From the PDF
Figure 4 Calibrated human judgments of conversational aspects for the baselines and best controlled models. Note: In Figure 3 and here, the Specificity and Question controlled models both include Repetition control, but Question control doesn't include Specificity control, or vice versa. See Table 8 for exact numbers.
Figure 4 Calibrated human judgments of conversational aspects for the baselines and best controlled models. Note: In Figure 3 and here, the Specificity and Question controlled models both include Repetition control, but Question control doesn't include Specificity control, or vice versa. See Table 8 for exact numbers.CC-BY · From the PDF
Figure 6 Screenshot of the chat UI, talking with the beam search baseline model.
Figure 6 Screenshot of the chat UI, talking with the beam search baseline model.CC-BY · From the PDF
Figure 7 Screenshot of the A/B test UI, comparing a human-human conversation (left) and a Repetition-controlled baseline model (right).
Figure 7 Screenshot of the A/B test UI, comparing a human-human conversation (left) and a Repetition-controlled baseline model (right).CC-BY · From the PDF
Figure 8 Example conversation with (a) Baseline (b) Repetition-controlled baseline (c) Question-controlled CT ( z = 7 ), (d) Specificity-controlled WD (weight = 4 ).
Figure 8 Example conversation with (a) Baseline (b) Repetition-controlled baseline (c) Question-controlled CT ( z = 7 ), (d) Specificity-controlled WD (weight = 4 ).CC-BY · From the PDF
Image 8
CC-BY · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 33 references

Research works printed but not linked: 6

  1. Jiwei Li, Will Monroe, Alan Ritter, Dan Jurafsky, Michel Galley, and Jianfeng Gao. 2016b. Deep reinforcement learning for dialogue generation. In Proceedings of the 2016 Conference on Em- pirical Methods in Natural Language Process- ing, pages 1192-1202, Austin, Texas. Associa- tion for Computational Linguistics.
  2. Jeffrey Pennington, Richard Socher, and Christo- pher Manning. 2014. GloVe: Global vectors for word representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1532- 1543, Doha, Qatar. Association for Computa- tional Linguistics.
  3. Iulian Vlad Serban, Ryan Lowe, Laurent Charlin, and Joelle Pineau. 2016a. Generative deep neu- ral networks for dialogue: A short review. Ad- vances in Neural Information Processing Sys- tems workshop on Learning Methods for Dia- logue.
  4. Iulian Vlad Serban, Alessandro Sordoni, Yoshua Bengio, Aaron C Courville, and Joelle Pineau. 2016b. Building end-to-end dialogue systems using generative hierarchical neural network models. In AAAI, volume 16, pages 3776-3784.
  5. Anu Venkatesh, Chandra Khatri, Ashwin Ram, Fenfei Guo, Raefer Gabriel, Ashish Nagar, Ro- hit Prasad, Ming Cheng, Behnam Hedayatnia, Angeliki Metallinou, et al. 2017. On evaluat- ing and comparing conversational agents. Ad- vances in Neural Information Processing Sys- tems, Conversational AI Workshop.
  6. Oriol Vinyals and Quoc Le. 2015. A neural con- versational model. In Proceedings of the 31st International Conference on Machine Learning, Deep Learning Workshop, Lille, France.

Cited by

See all 279

Metadata

Authors
See, A., Roller, S., Kiela, D., & Weston, J.
Affiliations
Meta (United States) (US)
Venue
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Published
2019
Pages
1702-1723
OpenAlex
W2916772188
Cited by
247
References
33
Citations by year
2026: 31 · 2025: 8 · 2024: 16 · 2023: 50 · 2022: 45 · 2021: 49 · 2020: 38 · 2019: 10
FWCI
13.58
Type
conference paper
Language
en
Open access
Licence
cc-by
Locations
Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) (publishedVersion, cc-by)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
  • Social Sciences › Arts and Humanities › Language and Linguistics › Language, Discourse, Communication Strategies
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
Keywords
conversation quality, human judgment, dialogue quality, chatbots

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: What makes a good conversation? How controllable attributes affect human judgments. https://app.cochat.ai/papers/10.18653/v1/n19-1170
The paper
See, A., Roller, S., Kiela, D., & Weston, J. (2019). What makes a good conversation? How controllable attributes affect human judgments. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). https://doi.org/10.18653/v1/n19-1170

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.