# DKAF: KB Arbitration for Learning Task-Oriented Dialog Systems with Dialog-KB Inconsistencies

arXiv: https://arxiv.org/abs/2305.16697 · HTML: https://mlsanity.com/paper/2305.16697/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 47 references that are in the map.
- First posted on arXiv 26 May 2023.

## Builds on (most cited first, 21 of 21)

- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [A Simple Language Model for Task-Oriented Dialogue](https://mlsanity.com/paper/2005.00796/) (2020)
- [A Network-based End-to-End Trainable Task-oriented Dialogue System](https://mlsanity.com/paper/1604.04562/) (2016)
- [Key-Value Retrieval Networks for Task-Oriented Dialogue](https://mlsanity.com/paper/1705.05414/) (2017)
- [Dialogue Natural Language Inference](https://mlsanity.com/paper/1811.00671/) (2018)
- [Learning End-to-End Goal-Oriented Dialog](https://mlsanity.com/paper/1605.07683/) (2016)
- [Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems](https://mlsanity.com/paper/1804.08217/) (2018)
- [A Hierarchical Recurrent Encoder-Decoder For Generative Context-Aware Query Suggestion](https://mlsanity.com/paper/1507.02221/) (2015)
- [Dialogue-Based Relation Extraction](https://mlsanity.com/paper/2004.08056/) (2020)
- [I like fish, especially dolphins: Addressing Contradictions in Dialogue Modeling](https://mlsanity.com/paper/2012.13391/) (2020)
- [Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing](https://mlsanity.com/paper/1807.02322/) (2018)
- [BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling](https://mlsanity.com/paper/2106.02787/) (2021)
- [Global-to-local Memory Pointer Networks for Task-Oriented Dialogue](https://mlsanity.com/paper/1901.04713/) (2019)
- [Relation Classification via Recurrent Neural Network](https://mlsanity.com/paper/1508.01006/) (2015)
- [Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog](https://mlsanity.com/paper/2004.11019/) (2020)
- [GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2010.01447/) (2020)
- [Don't be Contradicted with Anything! CI-ToD: Towards Benchmarking Consistency for Task-oriented Dialogue System](https://mlsanity.com/paper/2109.11292/) (2021)
- [Disentangling Language and Knowledge in Task-Oriented Dialogs](https://mlsanity.com/paper/1805.01216/) (2018)
- [Constraint based Knowledge Base Distillation in End-to-End Task Oriented Dialogs](https://mlsanity.com/paper/2109.07396/) (2021)
- [Unsupervised Learning of KB Queries in Task-Oriented Dialogs](https://mlsanity.com/paper/2005.00123/) (2020)

## Abstract (arXiv)

Task-oriented dialog (TOD) agents often ground their responses on external knowledge bases (KBs). These KBs can be dynamic and may be updated frequently. Existing approaches for learning TOD agents assume the KB snapshot contemporary to each individual dialog is available during training. However, in real-world scenarios, only the latest KB snapshot is available during training and as a result, the train dialogs may contain facts conflicting with the latest KB. These dialog-KB inconsistencies in the training data may potentially confuse the TOD agent learning algorithm. In this work, we define the novel problem of learning a TOD agent with dialog-KB inconsistencies in the training data. We propose a Dialog-KB Arbitration Framework (DKAF) which reduces the dialog-KB inconsistencies by predicting the contemporary KB snapshot for each train dialog. These predicted KB snapshots are then used for training downstream TOD agents. As there are no existing datasets with dialog-KB inconsistencies, we systematically introduce inconsistencies in two publicly available dialog datasets. We show that TOD agents trained with DKAF perform better than existing baselines on both these datasets