paper-with-me

Papers

A Multi-Task and Multi-Label Classification Model for Implicit Discourse Relation Recognition

2024-08-16 · Nelson Filipe Costa, Leila Kosseim

We address the inherent ambiguity in Implicit Discourse Relation Recognition (IDRR) by introducing a novel multi-task classification model capable of learning both multi-label and single-label representations of discourse relations. Our model is trained exclusively on the DiscoGeM corpus and evaluated both on the DiscoGeM and the PDTB 3.0 corpus. We establish the first benchmark on multi-label IDRR classification and achieve SOTA results on single-label IDRR classification using the DiscoGeM corpus. Finally, we present the first evaluation on the potential of transfer learning between the DiscoGeM and the PDTB 3.0 corpus on single-label IDRR classification.

📄 PDF Abstract BibTeX arXiv:2408.08971

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATIONRelationTransfer Learning

Similar Papers 제목 키워드 기반

Multi-Label Network Classification via Weighted Personalized Factorizations

2019-02-25 · Ahmed Rashed, Josif Grabocka, Lars Schmidt-Thieme

Multi-label network classification is a well-known task that is being used in a wide variety of web-based and non-web-based domains. It can be formalized as a multi-relational learning task for predicting nodes labels ba…

ClassificationGeneral ClassificationImplicit RelationsRelational Reasoning

Multi-Task Label Embedding for Text Classification

2017-10-17 · EMNLP 2018 10 · Honglun Zhang, Liqiang Xiao, Wenqing Chen, Yongkun Wang 외

Multi-task learning in text classification leverages implicit correlations among related tasks to extract common features and yield performance gains. However, most previous works treat labels of each task as independent…

ClassificationGeneral ClassificationMulti-Task Learningtext-classification+1

PercentMatch: Percentile-based Dynamic Thresholding for Multi-Label Semi-Supervised Classification

2022-08-30 · Junxiang Huang, Alexander Huang, Beatriz C. Guerra, Yen-Yun Yu

While much of recent study in semi-supervised learning (SSL) has achieved strong performance on single-label classification problems, an equally important yet underexplored problem is how to leverage the advantage of unl…

ClassificationMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATION

Learning Image Conditioned Label Space for Multilabel Classification

2018-02-21 · Yi-Nan Li, Mei-Chen Yeh

This work addresses the task of multilabel image classification. Inspired by the great success from deep convolutional neural networks (CNNs) for single-label visual-semantic embedding, we exploit extending these models …

ClassificationGeneral Classificationimage-classificationImage Classification

Label distributions help implicit discourse relation classification

2022-10-01 · COLING (CODI, CRAC) 2022 10 · Frances Yung, Kaveri Anuranjana, Merel Scholman, Vera Demberg

Implicit discourse relations can convey more than one relation sense, but much of the research on discourse relations has focused on single relation senses. Recently, DiscoGeM, a novel multi-domain corpus, which contains…

ClassificationImplicit Discourse Relation ClassificationRelationRelation Classification