paper-with-me

Papers

Text Classification with Negative Supervision

2020-07-01 · ACL 2020 6 · Sora Ohashi, Junya Takayama, Tomoyuki Kajiwara, Chenhui Chu, Yuki Arase

Advanced pre-trained models for text representation have achieved state-of-the-art performance on various text classification tasks. However, the discrepancy between the semantic similarity of texts and labelling standards affects classifiers, i.e. leading to lower performance in cases where classifiers should assign different labels to semantically similar texts. To address this problem, we propose a simple multitask learning model that uses negative supervision. Specifically, our model encourages texts with different labels to have distinct representations. Comprehensive experiments show that our model outperforms the state-of-the-art pre-trained model on both single- and multi-label classifications, sentence and document classifications, and classifications in three different languages.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationGeneral ClassificationSemantic SimilaritySemantic Textual SimilaritySentencetext-classificationText Classification

Similar Papers 제목 키워드 기반

One-class Text Classification with Multi-modal Deep Support Vector Data Description

2021-04-01 · EACL 2021 2 · Chenlong Hu, Yukun Feng, Hidetaka Kamigaito, Hiroya Takamura 외

This work presents multi-modal deep SVDD (mSVDD) for one-class text classification. By extending the uni-modal SVDD to a multiple modal one, we build mSVDD with multiple hyperspheres, that enable us to build a much bette…

text-classificationText Classification

DSReg: Using Distant Supervision as a Regularizer

2019-05-28 · ICLR 2020 1 · Yuxian Meng, Muyu Li, Xiaoya Li, Wei Wu 외

In this paper, we aim at tackling a general issue in NLP tasks where some of the negative examples are highly similar to the positive examples, i.e., hard-negative examples. We propose the distant supervision as a regula…

Multi-Task LearningReading Comprehensiontext-classificationText Classification

On a Guided Nonnegative Matrix Factorization

2020-10-22 · Joshua Vendrow, Jamie Haddock, Elizaveta Rebrova, Deanna Needell

Fully unsupervised topic models have found fantastic success in document clustering and classification. However, these models often suffer from the tendency to learn less-than-meaningful or even redundant topics when the…

ClusteringTopic Models

Hound: Hunting Supervision Signals for Few and Zero Shot Node Classification on Text-attributed Graph

2024-09-01 · Yuxiang Wang, Xiao Yan, Shiyu Jin, Quanqing Xu 외

Text-attributed graph (TAG) is an important type of graph structured data with text descriptions for each node. Few- and zero-shot node classification on TAGs have many applications in fields such as academia and social …

NegationNode ClassificationTAGText Matching

Supervision Adaptation Balancing In-distribution Generalization and Out-of-distribution Detection

2022-06-19 · Zhilin Zhao, Longbing Cao, Kun-Yu Lin

The discrepancy between in-distribution (ID) and out-of-distribution (OOD) samples can lead to \textit{distributional vulnerability} in deep neural networks, which can subsequently lead to high-confidence predictions for…

Out-of-Distribution DetectionOut of Distribution (OOD) Detection