MEGClass: Extremely Weakly Supervised Text Classification via Mutually-Enhancing Text Granularities
Submission Type: Regular Long Paper
Submission Track: Information Retrieval and Text Mining
Submission Track 2: Semantics: Lexical, Sentence level, Document Level, Textual Inference, etc.
Keywords: text classification, extremely weak supervision, weakly-supervised learning, document representations, representation learning, pseudo-document generation
TL;DR: This paper proposes an extremely weakly-supervised text classification method using mutually-enhancing text granularities (word, sentence, and document-level context).
Abstract: Text classification is essential for organizing unstructured text. Traditional methods rely on human annotations or, more recently, a set of class seed words for supervision, which can be costly, particularly for specialized or emerging domains. To address this, using class surface names alone as extremely weak supervision has been proposed. However, existing approaches treat different levels of text granularity (documents, sentences, or words) independently, disregarding inter-granularity class disagreements and the context identifiable exclusively through joint extraction. In order to tackle these issues, we introduce MEGClass, an extremely weakly-supervised text classification method that leverages Mutually-Enhancing Text Granularities. MEGClass utilizes coarse- and fine-grained context signals obtained by jointly considering a document's most class-indicative words and sentences. This approach enables the learning of a contextualized document representation that captures the most discriminative class indicators. By preserving the heterogeneity of potential classes, MEGClass can select the most informative class-indicative documents as iterative feedback to enhance the initial word-based class representations and ultimately fine-tune a pre-trained text classifier. Extensive experiments on seven benchmark datasets demonstrate that MEGClass outperforms other weakly and extremely weakly supervised methods.
Submission Number: 2304
Loading