# Speaker-Sensitive Dual Memory Networks for Multi-Turn Slot Tagging

arXiv: https://arxiv.org/abs/1711.10705 · HTML: https://mlsanity.com/paper/1711.10705/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Nov 2017.

## Built on by (most cited first, 2 of 2)

- [Prior Omission of Dissimilar Source Domain(s) for Cost-Effective Few-Shot Learning](https://mlsanity.com/paper/2109.05234/) (2021)
- [GASCOM: Graph-based Attentive Semantic Context Modeling for Online Conversation Understanding](https://mlsanity.com/paper/2310.14028/) (2023)

## Abstract (arXiv)

In multi-turn dialogs, natural language understanding models can introduce obvious errors by being blind to contextual information. To incorporate dialog history, we present a neural architecture with Speaker-Sensitive Dual Memory Networks which encode utterances differently depending on the speaker. This addresses the different extents of information available to the system - the system knows only the surface form of user utterances while it has the exact semantics of system output. We performed experiments on real user data from Microsoft Cortana, a commercial personal assistant. The result showed a significant performance improvement over the state-of-the-art slot tagging models using contextual information.