A deep network with visual text composition behavior

DOI	Resolve DOI: https://doi.org/10.18653/v1/P17-2059
Author	Search for: Guo, Hongyu¹
Name affiliation	National Research Council of Canada. Information and Communication Technologies
Format	Text, Article
Conference	The 55th Annual Meeting of the Association for Computational Linguistics, July 30 - August 4, 2017, Vancouver, BC., Canada
Abstract	While natural languages are composi- tional, how state-of-the-art neural models achieve compositionality is still unclear. We propose a deep network, which not only achieves competitive accuracy for text classification, but also exhibits compositional behavior. That is, while creating hierarchical representations of a piece of text, such as a sentence, the lower layers of the network distribute their layer-specific attention weights to individual words. In contrast, the higher layers compose meaningful phrases and clauses, whose lengths increase as the networks get deeper until fully composing the sentence.
Publication date	2017-07
Publisher	Association for Computational Linguistics
In	Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. Volume 2: Short Papers: 372–377.
Language	English
Peer reviewed	Yes
NPARC number	23002276
Export citation	Export as RIS
Report a correction	Report a correction (opens in a new tab)
Record identifier	a6bdaa46-5f05-4281-8ccc-bf160e7a5aff
Record created	2017-09-28
Record modified	2022-02-18