EMNLP Findings2024
Recent Trends in Linear Text Segmentation: A Survey
Abstract
Linear Text Segmentation is the task of automatically tagging text documents with topic shifts, i.e. the places in the text where the topics change. A well-established area of research in Natural Language Processing, drawing from well-understood concepts in linguistic and computational linguistic research, the field has recently seen a lot of interest as a result of the surge of text, video, and audio available on the web, which in turn require ways of summarising and categorizing the mole of content for which linear text segmentation is a fundamental step. In this survey, we provide an extensive overview of current advances in linear text segmentation, describing the state of the art in terms of resources and approaches for the task. Finally, we highlight the limitations of available resources and of the task itself, while indicating ways forward based on the most recent literature and under-explored research directions. 1
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Improving Long Document Topic Segmentation Models With Enhanced Coherence Modeling cites Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic Coherence
- Improving Long Document Topic Segmentation Models With Enhanced Coherence Modeling cites Two-Level Transformer and Auxiliary Coherence Modeling for Improved Text Segmentation
- Improving Long Document Topic Segmentation Models With Enhanced Coherence Modeling cites A Joint Model for Document Segmentation and Segment Labeling
- Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic Coherence cites Two-Level Transformer and Auxiliary Coherence Modeling for Improved Text Segmentation
- Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic Coherence cites A Joint Model for Document Segmentation and Segment Labeling
- TIAGE: A Benchmark for Topic-Shift Aware Dialog Modeling cites Two-Level Transformer and Auxiliary Coherence Modeling for Improved Text Segmentation
Builds on8
- Two-Level Transformer and Auxiliary Coherence Modeling for Improved Text SegmentationGoran Glavas, Swapna SomasundaranAAAI 2020 · 71 citations
- A Joint Model for Document Segmentation and Segment LabelingJoe Barrow, Rajiv Jain, Vlad I. Morariu, Varun Manjunatha et al.ACL 2020 · 47 citations
- Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic CoherenceKelvin Lo, Yuan Jin, Weicong Tan, Ming Liu et al.EMNLP Findings 2021 · 38 citations
- TIAGE: A Benchmark for Topic-Shift Aware Dialog ModelingHuiyuan Xie, Zhenghao Liu, Chenyan Xiong, Zhiyuan Liu et al.EMNLP Findings 2021 · 18 citations
- Improving Long Document Topic Segmentation Models With Enhanced Coherence ModelingHai Yu, Chong Deng, Qinglin Zhang, Jiaqing Liu et al.EMNLP 2023 · 7 citations
Related papers
- The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and ChallengesGenta Indra Winata, Alham Fikri Aji, Zheng Xin Yong, Thamar SolorioACL Findings 2023 · 46 citations
- SegFormer: A Topic Segmentation Model with Controllable Range of AttentionHaitao Bai, Pinghui Wang, Ruofei Zhang, Zhou SuAAAI 2023 · 18 citations
- SuperDialseg: A Large-scale Dataset for Supervised Dialogue SegmentationJunfeng Jiang, Chengzhang Dong, Sadao Kurohashi, Akiko AizawaEMNLP 2023 · 2 citations
- A Reference-free Segmentation Quality Index (SegReFree)Evan Lucas, Dylan Kangas, Timothy C. HavensEMNLP Findings 2023 · 1 citation
- Toward Unifying Text Segmentation and Long Document SummarizationSangwoo Cho, Kaiqiang Song, Xiaoyang Wang, Fei Liu et al.EMNLP 2022 · 19 citations
