Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks
Text classification is fundamental in natural language processing (NLP), and Graph Neural Networks (GNN) are recently applied in this task. However, the existing graph-based works can neither capture the contextual word relationships within each document nor fulfil the inductive learning of new words. In this work, to overcome such problems, we propose TextING for inductive text classification via GNN. We first build individual graphs for each document and then use GNN to learn the fine-grained word representations based on their local structures, which can also effectively produce embeddings for unseen words in the new document. Finally, the word nodes are aggregated as the document embedding. Extensive experiments on four benchmark datasets show that our method outperforms state-of-the-art text classification methods.
Code (1)
Tasks
ClassificationDocument EmbeddingGeneral ClassificationInductive Learningtext-classificationText ClassificationSimilar Papers 제목 키워드 기반
How Can Graph Neural Networks Help Document Retrieval: A Case Study on CORD19 with Concept Map Generation
Graph neural networks (GNNs), as a group of powerful tools for representation learning on irregular data, have manifested superiority in various downstream tasks. With unstructured texts represented as concept maps, GNNs…
Representation LearningRetrievalSparse Structure Learning via Graph Neural Networks for Inductive Document Classification
Recently, graph neural networks (GNNs) have been widely used for document classification. However, most existing methods are based on static word co-occurrence graphs without sentence-level information, which poses three…
ClassificationDocument ClassificationInductive LearningSentenceConnecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data
One way to address safety risks from large language models (LLMs) is to censor dangerous knowledge from their training data. While this removes the explicit information, implicit information can remain scattered across v…
In-Context LearningHDT: Hierarchical Document Transformer
In this paper, we propose the Hierarchical Document Transformer (HDT), a novel sparse Transformer architecture tailored for structured hierarchical documents. Such documents are extremely important in numerous domains, i…
Inductive BiasInductive Document Network Embedding with Topic-Word Attention
Document network embedding aims at learning representations for a structured text corpus i.e. when documents are linked to each other. Recent algorithms extend network embedding approaches by incorporating the text conte…
Network Embedding