Unsupervised Mutual Learning of Discourse Parsing and Topic Segmentation in Dialogue

• URL: http://arxiv.org/abs/2405.19799v3
• Date: Mon, 17 Feb 2025 09:22:19 GMT
• Title: Unsupervised Mutual Learning of Discourse Parsing and Topic Segmentation in Dialogue
• Authors: Jiahui Xu, Feng Jiang, Anningzhe Gao, Luis Fernando D'Haro, Haizhou Li,
• Abstract summary: In dialogue systems, discourse plays a crucial role in managing conversational focus and coordinating interactions. It consists of two key structures: rhetorical structure and topic structure. We introduce a unified representation that integrates rhetorical and topic structures, ensuring semantic consistency between them. We propose an unsupervised mutual learning framework (UMLF) that jointly models rhetorical and topic structures, allowing them to mutually reinforce each other without requiring additional annotations.
• Score: 37.618612723025784
• License:
• Abstract: In dialogue systems, discourse plays a crucial role in managing conversational focus and coordinating interactions. It consists of two key structures: rhetorical structure and topic structure. The former captures the logical flow of conversations, while the latter detects transitions between topics. Together, they improve the ability of a dialogue system to track conversation dynamics and generate contextually relevant high-quality responses. These structures are typically identified through discourse parsing and topic segmentation, respectively. However, existing supervised methods rely on costly manual annotations, while unsupervised methods often focus on a single task, overlooking the deep linguistic interplay between rhetorical and topic structures. To address these issues, we first introduce a unified representation that integrates rhetorical and topic structures, ensuring semantic consistency between them. Under the unified representation, we further propose two linguistically grounded hypotheses based on discourse theories: (1) Local Discourse Coupling, where rhetorical cues dynamically enhance topic-aware information flow, and (2) Global Topology Constraint, where topic structure patterns probabilistically constrain rhetorical relation distributions. Building on the unified representation and two hypotheses, we propose an unsupervised mutual learning framework (UMLF) that jointly models rhetorical and topic structures, allowing them to mutually reinforce each other without requiring additional annotations. We evaluate our approach on two rhetorical datasets and three topic segmentation datasets. Experimental results demonstrate that our method surpasses all strong baselines built on pre-trained language models. Furthermore, when applied to LLMs, our framework achieves notable improvements, demonstrating its effectiveness in improving discourse structure modeling.

Related papers

• With a Little Help from my (Linguistic) Friends: Topic Segmentation of Multi-party Casual Conversations [0.565395466029518]
  This paper tries to reach a comparable level of accuracy as recent machine learning based topic segmentation models. The features we identify as meaningful for this task help us understand better the topical structure of a conversation.
  arXiv  Detail & Related papers  (2024-02-05T09:48:07Z)
• Multi-turn Dialogue Comprehension from a Topic-aware Perspective [70.37126956655985]
  This paper proposes to model multi-turn dialogues from a topic-aware perspective. We use a dialogue segmentation algorithm to split a dialogue passage into topic-concentrated fragments in an unsupervised way. We also present a novel model, Topic-Aware Dual-Attention Matching (TADAM) Network, which takes topic segments as processing elements.
  arXiv  Detail & Related papers  (2023-09-18T11:03:55Z)
• Revisiting Conversation Discourse for Dialogue Disentanglement [88.3386821205896]
  We propose enhancing dialogue disentanglement by taking full advantage of the dialogue discourse characteristics. We develop a structure-aware framework to integrate the rich structural features for better modeling the conversational semantic context. Our work has great potential to facilitate broader multi-party multi-thread dialogue applications.
  arXiv  Detail & Related papers  (2023-06-06T19:17:47Z)
• Channel-aware Decoupling Network for Multi-turn Dialogue Comprehension [81.47133615169203]
  We propose compositional learning for holistic interaction across utterances beyond the sequential contextualization from PrLMs. We employ domain-adaptive training strategies to help the model adapt to the dialogue domains. Experimental results show that our method substantially boosts the strong PrLM baselines in four public benchmark datasets.
  arXiv  Detail & Related papers  (2023-01-10T13:18:25Z)
• Speaker-Oriented Latent Structures for Dialogue-Based Relation Extraction [10.381257436462116]
  We introduce SOLS, a novel model which can explicitly induce speaker-oriented latent structures for better DiaRE. Specifically, we learn latent structures to capture the relationships among tokens beyond the utterance boundaries. During the learning process, our speaker-specific regularization method progressively highlights speaker-related key clues and erases the irrelevant ones.
  arXiv  Detail & Related papers  (2021-09-11T04:24:51Z)
• Exploring Discourse Structures for Argument Impact Classification [48.909640432326654]
  This paper empirically shows that the discourse relations between two arguments along the context path are essential factors for identifying the persuasive power of an argument. We propose DisCOC to inject and fuse the sentence-level structural information with contextualized features derived from large-scale language models.
  arXiv  Detail & Related papers  (2021-06-02T06:49:19Z)
• Topic-Aware Multi-turn Dialogue Modeling [91.52820664879432]
  This paper presents a novel solution for multi-turn dialogue modeling, which segments and extracts topic-aware utterances in an unsupervised way. Our topic-aware modeling is implemented by a newly proposed unsupervised topic-aware segmentation algorithm and Topic-Aware Dual-attention Matching (TADAM) Network.
  arXiv  Detail & Related papers  (2020-09-26T08:43:06Z)
• Structured Attention for Unsupervised Dialogue Structure Induction [110.12561786644122]
  We propose to incorporate structured attention layers into a Variational Recurrent Neural Network (VRNN) model with discrete latent states to learn dialogue structure in an unsupervised fashion. Compared to a vanilla VRNN, structured attention enables a model to focus on different parts of the source sentence embeddings while enforcing a structural inductive bias.
  arXiv  Detail & Related papers  (2020-09-17T23:07:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.