Question-Aware Sentence Gating Networks for Question and Answering
arXiv:1807.07964
Abstract
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.
References in corpus (19)
- Adam: A Method for Stochastic Optimization
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- SQuAD: 100,000+ Questions for Machine Comprehension of Text
- SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents
- Dynamic Coattention Networks For Question Answering
- Machine Comprehension Using Match-LSTM and Answer Pointer
- Neural Machine Translation in Linear Time
- Learning Natural Language Inference using Bidirectional LSTM model and Inner-Attention
- FusionNet: Fusing via Fully-Aware Attention with Application to Machine Comprehension
- Neural Summarization by Extracting Sentences and Words
- AttSum: Joint Learning of Focusing and Summarization with Neural Attention
- Robust Multilingual Named Entity Recognition with Shallow Semi-Supervised Features
- MEMEN: Multi-layer Embedding with Memory Networks for Machine Comprehension
- Natural Language Inference by Tree-Based Convolution and Heuristic Matching
- Words or Characters? Fine-grained Gating for Reading Comprehension
- Gated Word-Character Recurrent Language Model
- Who did What: A Large-Scale Person-Centered Cloze Dataset
- Recurrent Neural Network-Based Sentence Encoder with Gated Attention for Natural Language Inference
- Phase Conductor on Multi-layered Attentions for Machine Comprehension