paper-with-me

Papers

ProtoSiTex: Learning Semi-Interpretable Prototypes for Multi-label Text Classification

2025-10-14 · Utsav Kumar Nareti, Suraj Kumar, Soumya Pandey, Soumi Chattopadhyay, Chandranath Adak, Sankha Subhra Mullick arxiv

The rapid growth of user-generated text across digital platforms has intensified the need for interpretable models capable of fine-grained text classification and explanation. Existing prototype-based models offer intuitive explanations but typically operate at coarse granularity (sentence or document level) and fail to address the multi-label nature of real-world text classification. We propose ProtoSiTex, a semi-interpretable framework designed for fine-grained multi-label text classification. ProtoSiTex employs a dual-phase alternate training strategy: an unsupervised prototype discovery phase that learns semantically coherent and diverse prototypes, and a supervised classification phase that maps these prototypes to class labels. A hierarchical loss function enforces consistency across subsentence, sentence, and document levels, enhancing interpretability and alignment. Unlike prior approaches, ProtoSiTex captures overlapping and conflicting semantics using adaptive prototypes and multi-head attention. We also introduce a benchmark dataset of hotel reviews annotated at the subsentence level with multiple labels. Experiments on this dataset and two public benchmarks (binary and multi-class) show that ProtoSiTex achieves state-of-the-art performance while delivering faithful, human-aligned explanations, establishing it as a robust solution for semi-interpretable multi-label text classification.

📄 PDF Abstract BibTeX arXiv:2510.12534

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Label Text Classification

Similar Papers 제목 키워드 기반

Semi-Supervised Object Detection via Multi-Instance Alignment With Global Class Prototypes

2022-01-01 · CVPR 2022 1 · Aoxue Li, Peng Yuan, Zhenguo Li

Semi-Supervised object detection (SSOD) aims to improve the generalization ability of object detectors with large-scale unlabeled images. Current pseudo-labeling-based SSOD methods individually learn from labeled dat…

object-detectionObject DetectionSemi-Supervised Object Detection

Mixed Prototype Consistency Learning for Semi-supervised Medical Image Segmentation

2024-04-16 · Lijian Li

Recently, prototype learning has emerged in semi-supervised medical image segmentation and achieved remarkable performance. However, the scarcity of labeled data limits the expressiveness of prototypes in previous method…

Image SegmentationMedical Image SegmentationSemantic SegmentationSemi-supervised Medical Image Segmentation

ProtoSSL: Interpretable Prototype Learning from Unlabeled Time-Series Data

2026-05-07 · Steven Song, Sahil Sethi, Brett Beaulieu-Jones, Robert L. Grossman arxiv

In time-series domains where both predictive performance and interpretability are essential, deep neural networks achieve strong results but provide limited insight into how their predictions are made. Projection-based p…

Audio Classification

Open-world Semi-supervised Novel Class Discovery

2023-05-22 · Jiaming Liu, Yangqiming Wang, Tongze Zhang, Yulu Fan 외

Traditional semi-supervised learning tasks assume that both labeled and unlabeled data follow the same class distribution, but the realistic open-world scenarios are of more complexity with unknown novel classes mixed in…

Contrastive LearningNovel Class DiscoveryRepresentation Learning

Analyzing the Benefits of Prototypes for Semi-Supervised Category Learning

2024-06-04 · Liyi Zhang, Logan Nelson, Thomas L. Griffiths

Categories can be represented at different levels of abstraction, from prototypes focused on the most typical members to remembering all observed exemplars of the category. These representations have been explored in the…