--- title: "Key-Value Retrieval Networks for Task-Oriented Dialogue (2017)" description: "The paper addresses a problem of task-oriented dialogue agents. 1 reference, cited by 180 papers here." authors: ["Mihail Eric", "Lakshmi Krishnan", "Francois Charette", "Christopher D. Manning"] year: 2017 venue: "Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue" source: "https://aclanthology.org/W17-5506/" doi: "10.18653/v1/w17-5506" arxiv: "1705.05414" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/eric-2017-key-value-retrieval-networks-task/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/eric-2017-key-value-retrieval-networks-task/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2017](https://md.research.elamur.ai/free/en/papers/2017/) / Key-Value Retrieval Networks for Task-Oriented Dialogue # Key-Value Retrieval Networks for Task-Oriented Dialogue **Authors:** [Mihail Eric](https://md.research.elamur.ai/free/en/authors/mihail-eric/), Lakshmi Krishnan, Francois Charette and [Christopher D. Manning](https://md.research.elamur.ai/free/en/authors/christopher-d-manning/) · **Year:** 2017 · **Venue:** [Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue](https://md.research.elamur.ai/free/en/venues/sigdial/) ([SIGDIAL 2017](https://md.research.elamur.ai/free/en/venues/sigdial/2017/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/W17-5506/) · [PDF](https://aclanthology.org/W17-5506.pdf) · [DOI 10.18653/v1/w17-5506](https://doi.org/10.18653/v1/w17-5506) · [arXiv 1705.05414](https://arxiv.org/abs/1705.05414) · [OpenAlex](https://openalex.org/W2616122292) **Citations:** 388 citations (OpenAlex, 2026-10-14) · [180](https://md.research.elamur.ai/free/en/papers/eric-2017-key-value-retrieval-networks-task/cited-by/) in our library, of the 149,439 papers whose bibliographies we read ## Summary The paper addresses a problem of task-oriented dialogue agents. Such agents find it hard to make natural use of information from a knowledge base (KB) while remaining fully differentiable. Researchers from Stanford and Ford Research propose the Key-Value Retrieval Network. It is an LSTM-based seq2seq model with attention over the encoder states, extended with a separate attention mechanism over the keys of KB entries. Each database entry is decomposed into (subject, relation, object) triples. The key is the sum of the subject and relation embeddings. The attention score for a key becomes the logit for a canonicalized value token, and during generation this token is replaced with the actual value from the database. The model requires no belief tracker or explicit dialogue state modeling and is trained on all domains at once. The authors also released a new corpus of KB-grounded dialogues for an in-car assistant. On BLEU, entity F1 and human evaluations in live conversations, the model outperforms a rule-based system and Copy Net. The work shows that knowledge from a database can be incorporated into neural dialogue without manual state annotation. ## Key points - **Corpus:** 3,031 multi-turn dialogues in three in-car assistant domains: calendar scheduling, weather forecasting, and point-of-interest navigation. Each dialogue has its own KB containing at most 230 normalized triples. The data is freely available on the Stanford NLP website. - **Method:** the output vocabulary is extended to |V| + n canonical KB tokens. The KB attention scores are added to the ordinary logits as a sparse vector. The idea derives from key-value memory networks (Miller et al., 2016). - **Automatic metrics:** the model achieves the highest BLEU and aggregate entity F1. It outperforms the rule-based system by 4.2% in aggregate entity F1, and Copy Net by 2.2 BLEU points and by 11% in entity F1. It falls about 12.7% short of human performance in entity F1, although in BLEU it is roughly on par with humans. - **Ablation:** Attn. Seq2Seq without KB attention has a very low entity F1. The variant without encoder attention is already considerably better, and the best result comes from combining both types of attention. - **Human evaluation:** the experiment covered 120 live chat scenarios with Amazon Mechanical Turk workers, with ratings on a 1–5 scale. KV Ret. Net scored 3.36 for fluency, 3.43 for cooperativeness and 3.09 for humanlikeness. For comparison: rule-based — 3.20/3.39/2.87, Copy Net — 2.33/2.42/2.02, humans — 3.98/3.95/4.04. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* ## Institutions - [Ford Motor Company](https://md.research.elamur.ai/free/en/companies/ford-motor-company/) — Company, Dearborn, United States · 2 works · 613 citations 📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works 🧭 Topics (2): [🗨️ Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · 624 works · [🔍 Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · 473 works 💡 Concepts (1): [💡 Chatbots](https://md.research.elamur.ai/free/en/concepts/chatbot/) · 54 works ## Cite Cite as: Mihail Eric, Lakshmi Krishnan, Francois Charette and Christopher D. Manning. 2017. Key-Value Retrieval Networks for Task-Oriented Dialogue. Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{eric2017key, title = {{Key-Value Retrieval Networks for Task-Oriented Dialogue}}, author = {Mihail Eric, Lakshmi Krishnan, Francois Charette and Christopher D. Manning}, booktitle = {Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue}, year = {2017}, doi = {10.18653/v1/w17-5506}, eprint = {1705.05414}, archivePrefix = {arXiv}, url = {https://doi.org/10.18653/v1/w17-5506} } ``` - [← previous Massive Exploration of Neural Machine Translation Architectures](https://md.research.elamur.ai/free/en/papers/britz-2017-massive-exploration-neural-machine-translation/) - [next → Sentence Simplification with Deep Reinforcement Learning](https://md.research.elamur.ai/free/en/papers/zhang-2017-sentence-simplification-deep-reinforcement-learning/) - [↑ back to papers of 2017](https://md.research.elamur.ai/free/en/papers/2017/) ## References 1 references, 1 of them with a card of ours. ↗ leads to the work. 1. L. El Asri, H. Schulz, S. Sharma, J. Zumer, J. Harris, E. Fine, R. Mehrotra, and K. Suleman. 2017. [Frames: A corpus for adding memory to goal-oriented dialogue systems](https://md.research.elamur.ai/free/en/papers/asri-2017-frames-corpus-adding-memory-goal/). [http://www.maluuba.com/publications/](http://www.maluuba.com/publications/) . *Figure 3: Sample dialogues from our human evaluation, conducted between a Turker and the KV… [↗](http://www.maluuba.com/publications/) *Updated 29 October 2026*