Retrieve and Refine: Improved Sequence Generation Models For Dialogue
Open accessThe DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.
Abstract
Sequence generation models for dialogue are known to have several problems: they tend to produce short, generic sentences that are uninformative and unengaging.Retrieval models on the other hand can surface interesting responses, but are restricted to the given retrieval set leading to erroneous replies that cannot be tuned to the specific context.In this work we develop a model that combines the two approaches to avoid both their deficiencies: first retrieve a response and then refine it -the final sequence generator treating the retrieval as additional context.We show on the recent CON-VAI2 challenge task our approach produces responses superior to both standard retrieval and generation models in human evaluations.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“Firstly, its adaptability to various situations is evidenced by the fine-tuning of 50k dialogues from game characters, enhancing its effectiveness as an NPCs [17].”
From MemoryRepository for AI NPC (2024) · cites this paper as [17]
Experimental — accuracy not yet measured
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
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766
Liu, C.-W., Lowe, R., Serban, I., Noseworthy, M., Charlin, L., & Pineau, J. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1230 · Cited by 1,228
Personalizing Dialogue Agents: I have a dog, do you have pets too?
Zhang, S., Dinan, E., Urbanek, J., Szlam, A., Kiela, D., & Weston, J. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1205 · Cited by 1,177 · cited 4×
“Following the protocol in Zhang et al. (2018), we asked humans to conduct short dialogues with our models (100 dialogues each of 10-20 turns, so 600 dialogues in total), and then measure the engagingness, consistency, and fluency (all scored out of 5) as well as to try to detect the persona that…”
MethodInfluentialSelf-citation(2016) · doi:10.18653/v1/d16-1147 · Cited by 1,035
Self-citationLiu, C., Lowe, R., Serban, I. V., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.08023 · Cited by 603
Generating Sentences by Editing Prototypes
Guu, K., Hashimoto, T. B., Oren, Y., & Liang, P. (2018) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00030 · Cited by 300 · cited 3×
“…(Junczys-Dowmunt and Grundkiewicz, 2017; Niehues et al., 2016; Novak et al., 2016; Xia et al., 2017; Grangier and Auli, 2017) or combining with retrieval (Gu et al., 2017; Cao et al., 2018), as well as for sentence correction or refinement without context (Guu et al., 2017; Schmaltz et al., 2017).”
BackgroundControllable Abstractive Summarization
Fan, A., Grangier, D., & Auli, M. (2018) · Proceedings of the 2nd Workshop on Neural Machine Translation and Generation · doi:10.18653/v1/w18-2706 · Cited by 281 · cited 2×
“(4)Other approaches might also help with this problem such as using an explicit copy mechanism or to use BPE tokenization (Fan et al., 2017), but we leave those for future work.”
BackgroundDeliberation Networks: Sequence Generation Beyond One-Pass Decoding
Xia, Y., Tian, F., Wu, L., Lin, J., Qin, T., Yu, N., & Liu, T. (2017) · neural information processing systems · Cited by 232
Retrieve, Rerank and Rewrite: Soft Template Based Neural Summarization
Cao, Z., Li, W., Li, S., & Wei, F. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1015 · Cited by 202 · cited 2×
“…(Junczys-Dowmunt and Grundkiewicz, 2017; Niehues et al., 2016; Novak et al., 2016; Xia et al., 2017; Grangier and Auli, 2017) or combining with retrieval (Gu et al., 2017; Cao et al., 2018), as well as for sentence correction or refinement without context (Guu et al., 2017; Schmaltz et al., 2017).”
BackgroundPersonalizing Dialogue Agents: I have a dog, do you have pets too?
Zhang, S., Dinan, E., Urbanek, J., Szlam, A., Kiela, D., & Weston, J. (2018) · arXiv · doi:10.48550/arxiv.1801.07243 · Cited by 165
Self-citationAn Information Retrieval Approach to Short Text Conversation
Ji, Z., Lu, Z., & Li, H. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1408.6988 · Cited by 152
Pre-Translation for Neural Machine TranslationPreprint
Niehues, J., Cho, E., Ha, T.-L., & Waibel, A. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1610.05243 · Cited by 87
Exemplar Encoder-Decoder for Neural Conversation Generation
Pandey, G., Contractor, D., Kumar, V., & Joshi, S. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1123 · Cited by 68
Generative Deep Neural Networks for Dialogue: A Short Review
Serban, I. V., Lowe, R., Charlin, L., & Pineau, J. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.06216 · Cited by 63
Adapting Sequence Models for Sentence Correction
Schmaltz, A., Kim, Y., Rush, A. M., & Shieber, S. M. (2017) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d17-1298 · Cited by 59
Search Engine Guided Non-Parametric Neural Machine TranslationPreprint
Gu, J., Wang, Y., Cho, K., & Li, V. O. K. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.07267 · Cited by 32
An Exploration of Neural Sequence-to-Sequence Architectures for Automatic Post-EditingPreprint
Junczys-Dowmunt, M., & Grundkiewicz, R. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.04138 · Cited by 21
Iterative Refinement for Machine Translation
Novak, R., Auli, M., & Grangier, D. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1610.06602 · Cited by 19
QuickEdit: Editing Text & Translations by Crossing Words OutPreprint
Grangier, D., & Auli, M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.04805 · Cited by 14
QuickEdit: Editing Text & Translations via Simple Delete Actions.Preprint
Grangier, D., & Auli, M. (2017) · arXiv (Cornell University) · Cited by 9
Research works printed but not linked: 1
- Alexander Miller, Adam Fisch, Jesse Dodge, AmirHossein Karimi, Antoine Bordes, and Jason Weston. 2016. Key-value memory networks for directly reading documents. arXiv preprint arXiv:1606.03126 . · arXiv
Cited by
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-T., Rocktäschel, T., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.11401 · Cited by 3,101
“Such tasks include open-domain question answering [5, 25], fact checking [50], fact completion [42], long-form question answering [12], Wikipedia article generation [32], dialogue [36, 59, 9, 13], translation [16], and language modeling [17, 23].”
BackgroundJustifying Recommendations using Distantly-Labeled Reviews and Fine-Grained Aspects
Ni, J., Li, J., & McAuley, J. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1018 · Cited by 1,200
Recipes for Building an Open-Domain Chatbot
Roller, S., Dinan, E., Goyal, N., Ju, D., Williamson, M., Liu, Y., Xu, J., Ott, M., Smith, E. M., Boureau, Y.-L., et al. (2021) · Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume · doi:10.18653/v1/2021.eacl-main.24 · Cited by 784
Self-citationRecipes for building an open-domain chatbot
Roller, S., Dinan, E., Goyal, N., Ju, D., Williamson, M., Liu, Y., Xu, J., Ott, M., Shuster, K., Smith, E. M., et al. (2020) · arXiv · doi:10.48550/arxiv.2004.13637 · Cited by 784
“the human utterances they were trained on (Weston et al., 2018).”
BackgroundResultInfluentialSelf-citationWhat Makes Good In-Context Examples for GPT-3?
Liu, J., Shen, D., Zhang, Y., Dolan, B., Carin, L., & Chen, W. (2022) · Proceedings of Deep Learning Inside Out (DeeLIO 2022): The 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures · doi:10.18653/v1/2022.deelio-1.10 · Cited by 563
Metadata
- Authors
- Weston, J., Dinan, E., & Miller, A.
- Affiliations
- Meta (United States) (US)
- Corresponding author
- Dinan, Emily
- Venue
- Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI
- Published
- 2018
- Pages
- 87-92
- OpenAlex
- W2885421725
- Cited by
- 165
- References
- 17
- Citations by year
- 2026: 2 · 2025: 5 · 2024: 13 · 2023: 26 · 2022: 32 · 2021: 33 · 2020: 31 · 2019: 22 · 2018: 1
- FWCI
- 8.84
- Type
- conference paper
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Keywords
- dialogue response generation, retrieval-augmented generation, response retrieval, conversational AI
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
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.