# Effective Incorporation of Speaker Information in Utterance Encoding in Dialog

arXiv: https://arxiv.org/abs/1907.05599 · HTML: https://mlsanity.com/paper/1907.05599/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jul 2019.

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

- [Response-act Guided Reinforced Dialogue Generation for Mental Health Counseling](https://mlsanity.com/paper/2301.12729/) (2023)
- [A Speaker-aware Parallel Hierarchical Attentive Encoder-Decoder Model for Multi-turn Dialogue Generation](https://mlsanity.com/paper/2110.06823/) (2021)

## Abstract (arXiv)

In dialog studies, we often encode a dialog using a hierarchical encoder where each utterance is converted into an utterance vector, and then a sequence of utterance vectors is converted into a dialog vector. Since knowing who produced which utterance is essential to understanding a dialog, conventional methods tried integrating speaker labels into utterance vectors. We found the method problematic in some cases where speaker annotations are inconsistent among different dialogs. A relative speaker modeling method is proposed to address the problem. Experimental evaluations on dialog act recognition and response generation show that the proposed method yields superior and more consistent performances.