Hierarchical Dialogue Understanding with Special Tokens and Turn-level Attention
This work addresses the problem of inconsistent semantics in dialogue for NLP researchers and practitioners, offering an incremental improvement over existing methods.
The authors tackled the challenge of modeling dynamic semantic changes in dialogue by proposing HiDialog, a hierarchical model using special tokens and turn-level attention, which achieved state-of-the-art performance on dialogue relation extraction, emotion recognition, and act classification tasks.
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.