paper-with-me

홈 › Papers

Hierarchical Heterogeneous Graph Representation Learning for Short Text Classification

2021-10-30 · EMNLP 2021 11 · Yaqing Wang, Song Wang, Quanming Yao, Dejing Dou

Short text classification is a fundamental task in natural language processing. It is hard due to the lack of context information and labeled data in practice. In this paper, we propose a new method called SHINE, which is based on graph neural network (GNN), for short text classification. First, we model the short text dataset as a hierarchical heterogeneous graph consisting of word-level component graphs which introduce more semantic and syntactic information. Then, we dynamically learn a short document graph that facilitates effective label propagation among similar short texts. Thus, compared with existing GNN-based methods, SHINE can better exploit interactions between nodes of the same types and capture similarities between short texts. Extensive experiments on various benchmark short text datasets show that SHINE consistently outperforms state-of-the-art methods, especially with fewer labels.

📄 PDF Abstract BibTeX arXiv:2111.00180

Code (1)

tata1661/shine-emnlp21 공식 구현 pytorch

Tasks

ClassificationGraph Neural NetworkGraph Representation LearningRepresentation Learningtext-classificationText Classification

Methods 이 논문이 사용한 방법론

Graph Neural Network 설명 없음

Similar Papers 제목 키워드 기반

Fake News Detection on News-Oriented Heterogeneous Information Networks through Hierarchical Graph Attention

2020-02-05 · Yuxiang Ren, Jiawei Zhang

The viral spread of fake news has caused great social harm, making fake news detection an urgent task. Current fake news detection methods rely heavily on text information by learning the extracted news content or writin…

ArticlesFake News DetectionGraph AttentionGraph Representation Learning+2

Linguistically Informed Graph Model and Semantic Contrastive Learning for Korean Short Text Classification

2026-03-04 · JaeGeon Yoo, Byoungwook Kim, Yeongwook Yang, Hong-Jun Jang arxiv

Short text classification (STC) remains a challenging task due to the scarcity of contextual information and labeled data. However, existing approaches have pre-dominantly focused on English because most benchmark datase…

Contrastive LearningSemantic SimilarityText Classification

Neural Extractive Summarization with Hierarchical Attentive Heterogeneous Graph Network

2020-11-01 · EMNLP 2020 11 · Ruipeng Jia, Yanan Cao, Hengzhu Tang, Fang Fang 외

Sentence-level extractive text summarization is substantially a node classification task of network mining, adhering to the informative components and concise representations. There are lots of redundant phrases between …

Extractive SummarizationExtractive Text SummarizationNode ClassificationSentence+1

HHGT: Hierarchical Heterogeneous Graph Transformer for Heterogeneous Graph Representation Learning

2024-07-18 · Qiuyu Zhu, Liang Zhang, Qianxiong Xu, Kaijun Liu 외

Despite the success of Heterogeneous Graph Neural Networks (HGNNs) in modeling real-world Heterogeneous Information Networks (HINs), challenges such as expressiveness limitations and over-smoothing have prompted research…

Graph Representation LearningNode ClusteringRepresentation Learning

Hierarchical Graph Network for Multi-hop Question Answering

2019-11-09 · EMNLP 2020 11 · Yuwei Fang, Siqi Sun, Zhe Gan, Rohit Pillai 외

In this paper, we present Hierarchical Graph Network (HGN) for multi-hop question answering. To aggregate clues from scattered texts across multiple paragraphs, a hierarchical graph is created by constructing nodes on di…

Multi-hop Question AnsweringQuestion Answering