Revisiting Conversation Discourse for Dialogue Disentanglement
Authors:
- Bobo LiBLBobo Li
- Hao FeiHao Fei
- Fei LiFei Li
- Shengqiong WuSWShengqiong Wu
- Lizi LiaoLLLizi Liao
- Yinwei WeiYWYinwei Wei
- Tat-Seng ChuaTCTat-Seng Chua
- Donghong JiDJDonghong Ji
Preprint
Abstract
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, \textbf{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, \textbf{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, \textbf{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.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language ProcessingACM Computing Surveys, 2023
- Is ChatGPT a General-Purpose Natural Language Processing Task Solver?2023
- Conversation Disentanglement with Bi-Level Contrastive Learning2022
- A Comprehensive Survey on Graph Neural NetworksIEEE Transactions on Neural Networks and Learning Systems, 2020
- Comparing partitionsJournal of Classification, 1985