Question-Aware Sentence Gating Networks for Question and Answering
This addresses the problem of high-level reasoning in QA for researchers and practitioners, but it is incremental as it builds on existing neural network-based models.
The paper tackles machine comprehension QA by proposing question-aware sentence gating networks to incorporate sentence-level information into word-level encoding, resulting in improved accuracy over baselines on various QA datasets.
Machine comprehension question answering, which finds an answer to the question given a passage, involves high-level reasoning processes of understanding and tracking the relevant contents across various semantic units such as words, phrases, and sentences in a document. This paper proposes the novel question-aware sentence gating networks that directly incorporate the sentence-level information into word-level encoding processes. To this end, our model first learns question-aware sentence representations and then dynamically combines them with word-level representations, resulting in semantically meaningful word representations for QA tasks. Experimental results demonstrate that our approach consistently improves the accuracy over existing baseline approaches on various QA datasets and bears the wide applicability to other neural network-based QA models.