Topic Segmentation of Semi-Structured and Unstructured Conversational Datasets using Language Models

• URL: http://arxiv.org/abs/2310.17120v1
• Date: Thu, 26 Oct 2023 03:37:51 GMT
• Title: Topic Segmentation of Semi-Structured and Unstructured Conversational Datasets using Language Models
• Authors: Reshmi Ghosh, Harjeet Singh Kajal, Sharanya Kamath, Dhuri Shrivastava, Samyadeep Basu, Hansi Zeng, Soundararajan Srinivasan
• Abstract summary: Current works on topic segmentation often focus on segmentation of structured texts. We propose Focal Loss function as a robust alternative to Cross-Entropy and re-weighted Cross-Entropy loss function when segmenting unstructured and semi-structured chats.
• Score: 3.7908886926768344
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Breaking down a document or a conversation into multiple contiguous segments based on its semantic structure is an important and challenging problem in NLP, which can assist many downstream tasks. However, current works on topic segmentation often focus on segmentation of structured texts. In this paper, we comprehensively analyze the generalization capabilities of state-of-the-art topic segmentation models on unstructured texts. We find that: (a) Current strategies of pre-training on a large corpus of structured text such as Wiki-727K do not help in transferability to unstructured conversational data. (b) Training from scratch with only a relatively small-sized dataset of the target unstructured domain improves the segmentation results by a significant margin. We stress-test our proposed Topic Segmentation approach by experimenting with multiple loss functions, in order to mitigate effects of imbalance in unstructured conversational datasets. Our empirical evaluation indicates that Focal Loss function is a robust alternative to Cross-Entropy and re-weighted Cross-Entropy loss function when segmenting unstructured and semi-structured chats.

Related papers

• A Bottom-Up Approach to Class-Agnostic Image Segmentation [4.086366531569003]
  We present a novel bottom-up formulation for addressing the class-agnostic segmentation problem. We supervise our network directly on the projective sphere of its feature space. Our bottom-up formulation exhibits exceptional generalization capability, even when trained on datasets designed for class-based segmentation.
  arXiv  Detail & Related papers  (2024-09-20T17:56:02Z)
• Pointer-Guided Pre-Training: Infusing Large Language Models with Paragraph-Level Contextual Awareness [3.2925222641796554]
  "pointer-guided segment ordering" (SO) is a novel pre-training technique aimed at enhancing the contextual understanding of paragraph-level text representations. Our experiments show that pointer-guided pre-training significantly enhances the model's ability to understand complex document structures.
  arXiv  Detail & Related papers  (2024-06-06T15:17:51Z)
• From Text Segmentation to Smart Chaptering: A Novel Benchmark for Structuring Video Transcriptions [63.11097464396147]
  We introduce a novel benchmark YTSeg focusing on spoken content that is inherently more unstructured and both topically and structurally diverse. We also introduce an efficient hierarchical segmentation model MiniSeg, that outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-02-27T15:59:37Z)
• Few-Shot Learning for Annotation-Efficient Nucleus Instance Segmentation [50.407071700154674]
  We propose to formulate annotation-efficient nucleus instance segmentation from the perspective of few-shot learning (FSL) Our work was motivated by that, with the prosperity of computational pathology, an increasing number of fully-annotated datasets are publicly accessible. Extensive experiments on a couple of publicly accessible datasets demonstrate that SGFSIS can outperform other annotation-efficient learning baselines.
  arXiv  Detail & Related papers  (2024-02-26T03:49:18Z)
• How Well Do Text Embedding Models Understand Syntax? [50.440590035493074]
  The ability of text embedding models to generalize across a wide range of syntactic contexts remains under-explored. Our findings reveal that existing text embedding models have not sufficiently addressed these syntactic understanding challenges. We propose strategies to augment the generalization ability of text embedding models in diverse syntactic scenarios.
  arXiv  Detail & Related papers  (2023-11-14T08:51:00Z)
• Topic-driven Distant Supervision Framework for Macro-level Discourse Parsing [72.14449502499535]
  The task of analyzing the internal rhetorical structure of texts is a challenging problem in natural language processing. Despite the recent advances in neural models, the lack of large-scale, high-quality corpora for training remains a major obstacle. Recent studies have attempted to overcome this limitation by using distant supervision.
  arXiv  Detail & Related papers  (2023-05-23T07:13:51Z)
• Boosting Event Extraction with Denoised Structure-to-Text Augmentation [52.21703002404442]
  Event extraction aims to recognize pre-defined event triggers and arguments from texts. Recent data augmentation methods often neglect the problem of grammatical incorrectness. We propose a denoised structure-to-text augmentation framework for event extraction DAEE.
  arXiv  Detail & Related papers  (2023-05-16T16:52:07Z)
• Uncovering the Potential of ChatGPT for Discourse Analysis in Dialogue: An Empirical Study [51.079100495163736]
  This paper systematically inspects ChatGPT's performance in two discourse analysis tasks: topic segmentation and discourse parsing. ChatGPT demonstrates proficiency in identifying topic structures in general-domain conversations yet struggles considerably in specific-domain conversations. Our deeper investigation indicates that ChatGPT can give more reasonable topic structures than human annotations but only linearly parses the hierarchical rhetorical structures.
  arXiv  Detail & Related papers  (2023-05-15T07:14:41Z)
• Topic Segmentation in the Wild: Towards Segmentation of Semi-structured & Unstructured Chats [2.9360071145551068]
  We analyze the capabilities of state-of-the-art topic segmentation models on unstructured texts. We find that pre-training on a large corpus of structured text does not help in transferability to unstructured texts. Training from scratch with only a relatively small-sized dataset of the target unstructured domain improves the segmentation results by a significant margin.
  arXiv  Detail & Related papers  (2022-11-27T22:17:16Z)
• Toward Unifying Text Segmentation and Long Document Summarization [31.084738269628748]
  We study the role that section segmentation plays in extractive summarization of written and spoken documents. Our approach learns robust sentence representations by performing summarization and segmentation simultaneously. Our findings suggest that the model can not only achieve state-of-the-art performance on publicly available benchmarks, but demonstrate better cross-genre transferability.
  arXiv  Detail & Related papers  (2022-10-28T22:07:10Z)
• Two-Level Transformer and Auxiliary Coherence Modeling for Improved Text Segmentation [9.416757363901295]
  We introduce a novel supervised model for text segmentation with simple but explicit coherence modeling. Our model -- a neural architecture consisting of two hierarchically connected Transformer networks -- is a multi-task learning model that couples the sentence-level segmentation objective with the coherence objective that differentiates correct sequences of sentences from corrupt ones.
  arXiv  Detail & Related papers  (2020-01-03T17:06:41Z)

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.