Hierarchical Attention Networks for Document Classification

Иерархические сети внимания для классификации документов
Chris Dyer, Eduard Hovy, Alex Smola, Zichao Yang, Xiaodong He, Diyi Yang
2016-01-01
SCID:  54.1/2rjdc5a8 Discuss with AI
Hierarchical Attention Networksattention mechanismdocument classificationhierarchical structure
Abstract (AI)
Zichao Yang, Diyi Yang, Chris Dyer, Xiaodong He, Alex Smola, Eduard Hovy. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2016.
Key Findings
1
Demonstrates improved document classification performance (state-of-the-art at time) on benchmark datasets compared to baseline methods
2
Hierarchical structure preserves document structure and yields better document representations than flat models
3
Introduces hierarchical attention networks that model documents at word and sentence levels for document classification
4
Uses attention mechanisms at both the word and sentence levels to identify informative words and sentences for classification
Research Object

Document classification models based on hierarchical attention networks

Research Subject

Effectiveness of hierarchical attention mechanisms (word- and sentence-level) for improving document classification performance

Publication Details
Publication Date
2016-01-01
Journal
Publisher
ISSN
Cited by
4878
Access Type
Author Information
Authors
Chris Dyer
Eduard Hovy
Alex Smola
Zichao Yang
Xiaodong He
Diyi Yang
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%