# Improving Response Selection in Multi-Turn Dialogue Systems by Incorporating Domain Knowledge

arXiv: https://arxiv.org/abs/1809.03194 · HTML: https://mlsanity.com/paper/1809.03194/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Sep 2018.

## Built on by (most cited first, 5 of 5)

- [AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialog](https://mlsanity.com/paper/2209.03632/) (2022)
- [A comprehensive solution to retrieval-based chatbot construction](https://mlsanity.com/paper/2106.06139/) (2021)
- [Mind the Knowledge Gap: A Survey of Knowledge-enhanced Dialogue Systems](https://mlsanity.com/paper/2212.09252/) (2022)
- [Intent-calibrated Self-training for Answer Selection in Open-domain Dialogues](https://mlsanity.com/paper/2307.06703/) (2023)
- [Understanding the Complexity and Its Impact on Testing in ML-Enabled Systems](https://mlsanity.com/paper/2301.03837/) (2023)

## Abstract (arXiv)

Building systems that can communicate with humans is a core problem in Artificial Intelligence. This work proposes a novel neural network architecture for response selection in an end-to-end multi-turn conversational dialogue setting. The architecture applies context level attention and incorporates additional external knowledge provided by descriptions of domain-specific words. It uses a bi-directional Gated Recurrent Unit (GRU) for encoding context and responses and learns to attend over the context words given the latent response representation and vice versa.In addition, it incorporates external domain specific information using another GRU for encoding the domain keyword descriptions. This allows better representation of domain-specific keywords in responses and hence improves the overall performance. Experimental results show that our model outperforms all other state-of-the-art methods for response selection in multi-turn conversations.