The DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Augmenting Transformers with KNN-Based Composite Memory for Dialog
Abstract
Various machine learning tasks can benefit from access to external information of different modalities, such as text and images. Recent work has focused on learning architectures with large memories capable of storing this knowledge. We propose augmenting generative Transformer neural networks with KNN-based Information Fetching (KIF) modules. Each KIF module learns a read operation to access fixed external knowledge. We apply these modules to generative dialog modeling, a challenging task where information must be flexibly retrieved and incorporated to maintain the topic and flow of conversation. We demonstrate the effectiveness of our approach by identifying relevant knowledge required for knowledgeable but engaging dialog from Wikipedia, images, and human-written dialog utterances, and show that leveraging this retrieved information improves model performance, measured by automatic and human evaluation.
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.
Integrity signals
Registry
Cites
Statistics
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.
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?
In the citing paper
“For visually grounded dialogue, KIF [313] and Maria [314] enhances dialog generation with external knowledge like visual experiences.”
From Retrieval-Augmented Generation for AI-Generated Content: A Survey (2024) · cites this paper as [313]
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
Billion-scale similarity search with GPUs
Johnson, J., Douze, M., & Jegou, H. (2021) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2019.2921572 · Cited by 4,228
Reading Wikipedia to answer open-domain questions
Chen, D., Fisch, A., Weston, J., & Bordes, A. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1171 · Cited by 1,546
Self-citationHierarchical Neural Story Generation
Fan, A., Lewis, M., & Dauphin, Y. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1082 · Cited by 1,266
Self-citationHierarchical Neural Story Generation
Fan, A., Lewis, M., & Dauphin, Y. (2018) · arXiv · doi:10.48550/arxiv.1805.04833 · Cited by 1,242
Self-citationGraves, A., Wayne, G., & Danihelka, I. (2014) · arXiv · doi:10.48550/arxiv.1410.5401 · Cited by 1,058
Neural Machine Translation of Rare Words with Subword Units
Sennrich, R., Haddow, B., & Birch, A. (2015) · arXiv · doi:10.48550/arxiv.1508.07909 · Cited by 950
Controllable 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×
“for both datasets used is available for download from parl.ai as well. We use byte-pair encoding (Sennrich et al.,2016) to represent the text to better handle the rare word problem (Dinan et al.,2018;Fan et al., 2018a). Our generative Transformer models have 8 encoder layers and 8 decoder layers, with FFN size 2048, e…”
Self-citationRetrieve and Refine: Improved Sequence Generation Models For Dialogue
Weston, J., Dinan, E., & Miller, A. (2018) · Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI · doi:10.18653/v1/w18-5713 · Cited by 165
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) · arXiv · doi:10.48550/arxiv.1801.07243 · Cited by 165
Augmenting Self-attention with Persistent Memory
Sukhbaatar, S., Grave, E., Lample, G., Jegou, H., & Joulin, A. (2019) · arXiv · doi:10.48550/arxiv.1907.01470 · Cited by 75
Research works printed but not linked: 42
- Bordes Antoine, 2017, 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24–26, 2017, Conference Track Proceedings
- Cai Deng, 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), 1866
- Chandar Sarath, 2016, CoRR, 1605
- Chen Wenlin, 2016, Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 1975, 10.18653/v1/P16-1186 · DOI
- Dinan Emily, 2018, International Conference on Learning Representations
- Fan Angela, 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), 4177
- Fan Angela, 2018, Proceedings of the 2nd Workshop on Neural Machine Translation and Generation, 45
- Fan Angela, 2018, Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 889
- Grave Edouard, 2017, Proceedings of the 34th International Conference on Machine Learning-Volume 70, 1302
- Grave Edouard, 2017, 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24–26, 2017, Conference Track Proceedings
- Guu Kelvin, 2020, Proceedings of the International Conference on Machine Learning, 5695
- Humeau Samuel, 2019, International Conference on Learning Representations
- Johnson Jeff, 2019, IEEE Transactions on Big Data
- Joulin Armand, 2015, Advances in Neural Information Processing Systems, 190
- Khandelwal Urvashi, 2019, International Conference on Learning Representations
- Kingma Diederik P., 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7–9, 2015, Conference Track Proceedings
- Lample Guillaume, 2019, Advances in Neural Information Processing Systems, 8548
- Li Margaret, 2019, arXiv preprint arXiv:1909.03087 · arXiv
- Lian Rongzhong, 2019, Proceedings of the 28th International Joint Conference on Artificial Intelligence, 5081
- Mahajan Dhruv, 2018, Proceedings of the European Conference on Computer Vision (ECCV), 181
- McCann Bryan, 2017, Advances in Neural Information Processing Systems, 6294
- Alexander Miller, Will Feng, Dhruv Batra, Antoine Bordes, Adam Fisch, Jiasen Lu, Devi Parikh, and Jason Weston. 2017. parl.ai: A dialog research software platform. pages 79–84. https://arxiv.org/abs/1705.06476 , DOI: https://doi.org/10.18653/v1/D17-2014 · DOI · Paper page
- Mnih Andriy, 2009, Advances in Neural Information Processing Systems, 1081
- Petroni Fabio, 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), 2463, 10.18653/v1/D19-1250 · DOI · Paper page
- Plötz Tobias, 2018, Advances in Neural Information Processing Systems, 1087
- Qin Lianhui, 2019, Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 5427
- Rae Jack, 2016, Advances in Neural Information Processing Systems, 3621
- Sennrich Rico, 2016, Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 1715, 10.18653/v1/P16-1162 · DOI · Paper page
- Seo Minjoon, 2019, Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 4430
- Serban Iulian V., 2016, arXiv preprint arXiv:1611.06216 · arXiv
- Serban Iulian V., 2016, Thirtieth AAAI Conference on Artificial Intelligence
- Shuster Kurt, 2020, Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2414, 10.18653/v1/2020.acl-main.219 · DOI
- Shuster Kurt, 2019, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 12516
- Song Haoyu, 2020, arXiv preprint arXiv:2004.07672 · arXiv
- Song Yiping, 2016, arXiv preprint arXiv:1610.07149 · arXiv
- Sukhbaatar Sainbayar, 2015, Advances in Neural Information Processing Systems, 2440
- Thomee Bart, 2016, Communications of the ACM, 59, 64, 10.1145/2812802 · DOI · Paper page
- Vaswani Ashish, 2017, Advances in Neural Information Processing Systems, 5998
- Weston Jason, 2015, 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7–9, 2015, Conference Track Proceedings
- Xie Saining, 2017, Proceedings of the IEEE conference on computer vision and pattern recognition, 1492
- Zhang Saizheng, 2018, Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2204, 10.18653/v1/P18-1205 · DOI · Paper page
- Zhu Yutao, 2020, Information Retrieval Journal, 23, 27, 10.1007/s10791-019-09364-x · DOI
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
Retrieval Augmentation Reduces Hallucination in Conversation
Shuster, K., Poff, S., Chen, M., Kiela, D., & Weston, J. (2021) · Findings of the Association for Computational Linguistics: EMNLP 2021 · doi:10.18653/v1/2021.findings-emnlp.320 · Cited by 575
Retrieval-Augmented Generation for AI-Generated Content: A Survey
Zhao, P., Zhang, H., Yu, Q., Wang, Z., Geng, Y., Fu, F., Yang, L., Zhang, W., Jiang, J., & Cui, B. (2024) · arXiv · doi:10.48550/arxiv.2402.19473 · Cited by 240
Wu, Y., Rabe, M. N., Hutchins, D., & Szegedy, C. (2022) · arXiv · doi:10.48550/arxiv.2203.08913 · Cited by 90
Training language models with memory augmentation
Zhong, Z., Lei, T., & Chen, D. (2022) · Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2022.emnlp-main.382 · Cited by 60
Metadata
- Authors
- Fan, A., Gardent, C., Braud, C., & Bordes, A.
- Affiliations
- Facebook AI Research, Université de Lorraine LORIA.
- CNRS/LORIA.
- CNRS/IRIT.
- Facebook AI Research.
- Venue
- Transactions of the Association for Computational Linguistics
- Publisher
- MIT Press
- Published
- 2021-02
- Volume
- 9
- Pages
- 82-99
- ISSN
- 2307-387X
- Cited by
- 20
- References
- 12
- Language
- en
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: Augmenting Transformers with KNN-Based Composite Memory for Dialog. https://app.cochat.ai/papers/10.1162/tacl_a_00356
- The paper
- Fan, A., Gardent, C., Braud, C., & Bordes, A. (2021). Augmenting Transformers with KNN-Based Composite Memory for Dialog. Transactions of the Association for Computational Linguistics. https://doi.org/10.1162/tacl_a_00356
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.
