# LSTM-based Mixture-of-Experts for Knowledge-Aware Dialogues

arXiv: https://arxiv.org/abs/1605.01652 · HTML: https://mlsanity.com/paper/1605.01652/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 May 2016.

## Built on by (most cited first, 6 of 6)

- [AdaTag: Multi-Attribute Value Extraction from Product Profiles with Adaptive Decoding](https://mlsanity.com/paper/2106.02318/) (2021)
- [Breaking the gridlock in Mixture-of-Experts: Consistent and Efficient Algorithms](https://mlsanity.com/paper/1802.07417/) (2018)
- [Table-based Fact Verification with Self-adaptive Mixture of Experts](https://mlsanity.com/paper/2204.08753/) (2022)
- [Mixtures of Deep Neural Experts for Automated Speech Scoring](https://mlsanity.com/paper/2106.12475/) (2021)
- [Mind the Knowledge Gap: A Survey of Knowledge-enhanced Dialogue Systems](https://mlsanity.com/paper/2212.09252/) (2022)
- [Modular Approach to Machine Reading Comprehension: Mixture of Task-Aware Experts](https://mlsanity.com/paper/2210.01750/) (2022)

## Abstract (arXiv)

We introduce an LSTM-based method for dynamically integrating several word-prediction experts to obtain a conditional language model which can be good simultaneously at several subtasks. We illustrate this general approach with an application to dialogue where we integrate a neural chat model, good at conversational aspects, with a neural question-answering model, good at retrieving precise information from a knowledge-base, and show how the integration combines the strengths of the independent components. We hope that this focused contribution will attract attention on the benefits of using such mixtures of experts in NLP.