Revisiting Conversation Discourse for Dialogue Disentanglement

by   Bobo Li, et al.

Dialogue disentanglement aims to detach the chronologically ordered utterances into several independent sessions. Conversation utterances are essentially organized and described by the underlying discourse, and thus dialogue disentanglement requires the full understanding and harnessing of the intrinsic discourse attribute. In this paper, we propose enhancing dialogue disentanglement by taking full advantage of the dialogue discourse characteristics. First of all, in feature encoding stage, we construct the heterogeneous graph representations to model the various dialogue-specific discourse structural features, including the static speaker-role structures (i.e., speaker-utterance and speaker-mentioning structure) and the dynamic contextual structures (i.e., the utterance-distance and partial-replying structure). We then develop a structure-aware framework to integrate the rich structural features for better modeling the conversational semantic context. Second, in model learning stage, we perform optimization with a hierarchical ranking loss mechanism, which groups dialogue utterances into different discourse levels and carries training covering pair-wise and session-wise levels hierarchically. Third, in inference stage, we devise an easy-first decoding algorithm, which performs utterance pairing under the easy-to-hard manner with a global context, breaking the constraint of traditional sequential decoding order. On two benchmark datasets, our overall system achieves new state-of-the-art performances on all evaluations. In-depth analyses further demonstrate the efficacy of each proposed idea and also reveal how our methods help advance the task. Our work has great potential to facilitate broader multi-party multi-thread dialogue applications.


Discourse-Wizard: Discovering Deep Discourse Structure in your Conversation with RNNs

Spoken language understanding is one of the key factors in a dialogue sy...

Enhanced Speaker-aware Multi-party Multi-turn Dialogue Comprehension

Multi-party multi-turn dialogue comprehension brings unprecedented chall...

Structured Dialogue Discourse Parsing

Dialogue discourse parsing aims to uncover the internal structure of a m...

Discourse-Aware Emotion Cause Extraction in Conversations

Emotion Cause Extraction in Conversations (ECEC) aims to extract the utt...

MedFilter: Improving Extraction of Task-relevant Utterances through Integration of Discourse Structure and Ontological Knowledge

Information extraction from conversational data is particularly challeng...

Time to Transfer: Predicting and Evaluating Machine-Human Chatting Handoff

Is chatbot able to completely replace the human agent? The short answer ...

Incorporating Annotator Uncertainty into Representations of Discourse Relations

Annotation of discourse relations is a known difficult task, especially ...

Please sign up or login with your details

Forgot password? Click here to reset