Work

Gated-Attention Readers for Text Comprehension

Year: 2017

Type: conference-paper

Abstract: In this paper we study the problem of answering cloze-style questions over documents.Our model, the Gated-Attention (GA) Reader 1 , integrates a multi-hop architecture with a novel attention mechanism, which is based on multiplicative interactions between the query embedding and the intermediate states of a recurrent neural network document reader.This enables the reader to build query-specific representations of tokens in the document for accurate answer selection.The GA Reader obtains state-of-the-art results on three benchmarks for this task-the CNN & Daily Mail news stories and the Who Did What dataset.The effectiveness of multiplicative interaction is demonstrated by an ablation study, and by comparing to alternative compositional operators for implementing the gated-attention.

Source: Proceedings of the conference - Association for Computational Linguistics. Meeting

DOI: 10.18653/v1/p17-1168

Authors: Bhuwan Dhingra, Hanxiao Liu, Zhilin Yang, William Cohen, Ruslan Salakhutdinov

Institutions: Microsoft (United States), Carnegie Mellon University

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: National Science Foundation

Award: SHF: Large: Collaborative Research: Exploiting the Naturalness of Software