paper-with-me

Papers

Unsupervised Dialogue Topic Segmentation with Topic-aware Utterance Representation

2023-05-04 · Haoyu Gao, Rui Wang, Ting-En Lin, Yuchuan Wu, Min Yang, Fei Huang, Yongbin Li

Dialogue Topic Segmentation (DTS) plays an essential role in a variety of dialogue modeling tasks. Previous DTS methods either focus on semantic similarity or dialogue coherence to assess topic similarity for unsupervised dialogue segmentation. However, the topic similarity cannot be fully identified via semantic similarity or dialogue coherence. In addition, the unlabeled dialogue data, which contains useful clues of utterance relationships, remains underexploited. In this paper, we propose a novel unsupervised DTS framework, which learns topic-aware utterance representations from unlabeled dialogue data through neighboring utterance matching and pseudo-segmentation. Extensive experiments on two benchmark datasets (i.e., DialSeg711 and Doc2Dial) demonstrate that our method significantly outperforms the strong baseline methods. For reproducibility, we provide our code and data at:https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/dial-start.

📄 PDF Abstract BibTeX arXiv:2305.02747

Code (1)

alibabaresearch/damo-convai 공식 구현 pytorch

Tasks

SegmentationSemantic SimilaritySemantic Textual Similarity

Similar Papers 제목 키워드 기반

Topic-Aware Multi-turn Dialogue Modeling

2020-09-26 · Yi Xu, Hai Zhao, Zhuosheng Zhang

In the retrieval-based multi-turn dialogue modeling, it remains a challenge to select the most appropriate response according to extracting salient features in context utterances. As a conversation goes on, topic shift a…

Retrieval

Multi-turn Dialogue Comprehension from a Topic-aware Perspective

2023-09-18 · Xinbei Ma, Yi Xu, Hai Zhao, Zhuosheng Zhang

Dialogue related Machine Reading Comprehension requires language models to effectively decouple and model multi-turn dialogue passages. As a dialogue development goes after the intentions of participants, its topic may n…

Machine Reading ComprehensionReading Comprehension

An Unsupervised Dialogue Topic Segmentation Model Based on Utterance Rewriting

2024-09-12 · Xia Hou, QiFeng Li, Tongliang Li

Dialogue topic segmentation plays a crucial role in various types of dialogue modeling tasks. The state-of-the-art unsupervised DTS methods learn topic-aware discourse representations from conversation data through adjac…

Representation LearningSegmentationSemantic SimilaritySemantic Textual Similarity

Improving Unsupervised Dialogue Topic Segmentation with Utterance-Pair Coherence Scoring

2021-06-12 · SIGDIAL (ACL) 2021 7 · Linzi Xing, Giuseppe Carenini

Dialogue topic segmentation is critical in several dialogue modeling problems. However, popular unsupervised approaches only exploit surface features in assessing topical coherence among utterances. In this work, we addr…

Segmentation

Unsupervised Dialogue Topic Segmentation in Hyperdimensional Space

2023-08-21 · Seongmin Park, Jinkyu Seo, Jihwa Lee

We present HyperSeg, a hyperdimensional computing (HDC) approach to unsupervised dialogue topic segmentation. HDC is a class of vector symbolic architectures that leverages the probabilistic orthogonality of randomly dra…

Segmentation