Hierarchical Dialogue Understanding with Special Tokens and Turn-level Attention

Xiao Liu, Jian Zhang, Heng Zhang, Fuzhao Xue, Yang You

Keywords: Turn-level Attention, Dialogue Understanding, Natural Language Processing

Abstract: Compared with standard text, understanding dialogue is more challenging for machines as the dynamic and unexpected semantic changes in each turn. To model such inconsistent semantics, we propose a simple but effective Hierarchical Dialogue Understanding model, HiDialog. Specifically, we first insert multiple special tokens into a dialogue and propose the turn-level attention to learn turn embeddings hierarchically. Then, a heterogeneous graph module is leveraged to polish the learned embeddings. We evaluate our model on various dialogue understanding tasks including dialogue relation extraction, dialogue emotion recognition, and dialogue act classification. Results show that our simple approach achieves state-of-the-art performance on all three tasks above. All our source code is publicly available at https://github.com/ShawX825/HiDialog.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/hierarchical-dialogue-understanding-with/code)