# Entity-Consistent End-to-end Task-Oriented Dialogue System with KB Retriever

arXiv: https://arxiv.org/abs/1909.06762 · HTML: https://mlsanity.com/paper/1909.06762/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Sep 2019.

## Built on by (most cited first, 21 of 21)

- [Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey](https://mlsanity.com/paper/2105.04387/) (2021)
- [Few-Shot Bot: Prompt-Based Learning for Dialogue Systems](https://mlsanity.com/paper/2110.08118/) (2021)
- [BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling](https://mlsanity.com/paper/2106.02787/) (2021)
- [DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue Generation](https://mlsanity.com/paper/2204.09149/) (2022)
- [Don't be Contradicted with Anything! CI-ToD: Towards Benchmarking Consistency for Task-oriented Dialogue System](https://mlsanity.com/paper/2109.11292/) (2021)
- [End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions](https://mlsanity.com/paper/2311.09008/) (2023)
- [Constraint based Knowledge Base Distillation in End-to-End Task Oriented Dialogs](https://mlsanity.com/paper/2109.07396/) (2021)
- [Q-TOD: A Query-driven Task-oriented Dialogue System](https://mlsanity.com/paper/2210.07564/) (2022)
- [Autoregressive Entity Generation for End-to-End Task-Oriented Dialog](https://mlsanity.com/paper/2209.08708/) (2022)
- [Towards Standard Criteria for human evaluation of Chatbots: A Survey](https://mlsanity.com/paper/2105.11197/) (2021)
- [Multi-Grained Knowledge Retrieval for End-to-End Task-Oriented Dialog](https://mlsanity.com/paper/2305.10149/) (2023)
- [A Template-guided Hybrid Pointer Network for Knowledge-basedTask-oriented Dialogue Systems](https://mlsanity.com/paper/2106.05830/) (2021)
- [A Comparative Study on Language Models for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2201.08687/) (2022)
- [Synergizing In-context Learning with Hints for End-to-end Task-oriented Dialog Systems](https://mlsanity.com/paper/2405.15585/) (2024)
- [DESCGEN: A Distantly Supervised Dataset for Generating Abstractive Entity Descriptions](https://mlsanity.com/paper/2106.05365/) (2021)
- [Retrieval-Generation Alignment for End-to-End Task-Oriented Dialogue System](https://mlsanity.com/paper/2310.08877/) (2023)
- [Dual-Feedback Knowledge Retrieval for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2310.14528/) (2023)
- [Prior Lessons of Incremental Dialogue and Robot Action Management for the Age of Language Models](https://mlsanity.com/paper/2501.00953/) (2025)
- [Mind the Knowledge Gap: A Survey of Knowledge-enhanced Dialogue Systems](https://mlsanity.com/paper/2212.09252/) (2022)
- [A Unified Data Augmentation Framework for Low-Resource Multi-Domain Dialogue Generation](https://mlsanity.com/paper/2406.09881/) (2024)
- [Knowledge-driven Answer Generation for Conversational Search](https://mlsanity.com/paper/2104.06892/) (2021)

## Abstract (arXiv)

Querying the knowledge base (KB) has long been a challenge in the end-to-end task-oriented dialogue system. Previous sequence-to-sequence (Seq2Seq) dialogue generation work treats the KB query as an attention over the entire KB, without the guarantee that the generated entities are consistent with each other. In this paper, we propose a novel framework which queries the KB in two steps to improve the consistency of generated entities. In the first step, inspired by the observation that a response can usually be supported by a single KB row, we introduce a KB retrieval component which explicitly returns the most relevant KB row given a dialogue history. The retrieval result is further used to filter the irrelevant entities in a Seq2Seq response generation model to improve the consistency among the output entities. In the second step, we further perform the attention mechanism to address the most correlated KB column. Two methods are proposed to make the training feasible without labeled retrieval data, which include distant supervision and Gumbel-Softmax technique. Experiments on two publicly available task oriented dialog datasets show the effectiveness of our model by outperforming the baseline systems and producing entity-consistent responses.