Multi-turn Response Selection using Dialogue Dependency Relations
Qi Jia, Yizhu Liu, Siyu Ren, Kenny Qili Zhu, Haifeng Tang · 2020
Multi-turn response selection is a task designed for developing dialogue agents.The performance on this task has a remarkable improvement with pre-trained language models.However, these models simply concatenate the turns in dialogue history as the input and largely ignore the dependencies between the turns.In this paper, we propose a dialogue extraction algorithm to transform a dialogue history into threads based on their dependency relations.Each thread can be regarded as a self-contained sub-dialogue.We also propose Thread-Encoder model to encode threads and candidates into compact representations by pre-trained Transformers and finally get the matching score through an attention layer.The experiments show that dependency relations are helpful for dialogue context understanding, and our model outperforms the state-of-the-art baselines on both DSTC7 and DSTC8*, with competitive results on UbuntuV2.