Attending to Inter-sentential Features in Neural Text Classification

Billy CHIU, Sunil Kumar SAHU, Neha SENGUPTA, Derek THOMAS, Mohammady MAHDY

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

1 Citation (Scopus)


Text classification requires a deep understanding of the linguistic features in text; in particular, the intra-sentential (local) and inter-sentential features (global). Models that operate on word sequences have been successfully used to capture the local features, yet they are not effective in capturing the global features in long-text. We investigate graph-level extensions to such models and propose a novel architecture for combining alternative text features. It uses an attention mechanism to dynamically decide how much information to use from a sequence- or graph-level component. We evaluated different architectures on a range of text classification datasets, and graph-level extensions were found to improve performance on most benchmarks. In addition, the attention-based architecture, as adaptively-learned from the data, outperforms the generic and fixed-value concatenation ones.
Original languageEnglish
Title of host publicationProceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR ’20)
PublisherAssociation for Computing Machinery (ACM)
ISBN (Print)9781450380164
Publication statusPublished - 25 Jul 2020
Externally publishedYes


Dive into the research topics of 'Attending to Inter-sentential Features in Neural Text Classification'. Together they form a unique fingerprint.

Cite this