S-Net: From Answer Extraction to Answer Generation for Machine Reading Comprehension

Abstract

In this paper, we present a novel approach to machine reading comprehension for the MS-MARCO dataset. Unlike the SQuAD dataset that aims to answer a question with exact text spans in a passage, the MS-MARCO dataset defines the task as answering a question from multiple passages and the words in the answer are not necessary in the passages. We therefore develop an extraction-then-synthesis framework to synthesize answers from extraction results. Specifically, the answer extraction model is first employed to predict the most important sub-spans from the passage as evidence, and the answer synthesis model takes the evidence as additional features along with the question and passage to further elaborate the final answers. We build the answer extraction model with state-of-the-art neural networks for single passage reading comprehension, and propose an additional task of passage ranking to help answer extraction in multiple passages. The answer synthesis model is based on the sequence-to-sequence neural networks with extracted evidences as features. Experiments show that our extraction-then-synthesis method outperforms state-of-the-art methods.

AAAI18

References in corpus (10)

• ADADELTA: An Adaptive Learning Rate Method
• SQuAD: 100,000+ Questions for Machine Comprehension of Text
• Effective Approaches to Attention-based Neural Machine Translation
• Dynamic Coattention Networks For Question Answering
• Machine Comprehension Using Match-LSTM and Answer Pointer
• Grammar as a Foreign Language
• Selective Encoding for Abstractive Sentence Summarization
• Learning Recurrent Span Representations for Extractive Question Answering
• End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension
• Making Neural QA as Simple as Possible but not Simpler

Cited by in corpus (17)

• Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering
• A Unified Query-based Generative Model for Question Generation and Question Answering
• Entity-Relation Extraction as Multi-Turn Question Answering
• The price of debiasing automatic metrics in natural language evaluation
• Focused Hierarchical RNNs for Conditional Sequence Processing
• PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation
• Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives
• Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification
• Meaningful Answer Generation of E-Commerce Question-Answering
• HAS-QA: Hierarchical Answer Spans Model for Open-domain Question Answering
• Product-Aware Answer Generation in E-Commerce Question-Answering
• Conversational Answer Generation and Factuality for Reading Comprehension Question-Answering
• GenNet : Reading Comprehension with Multiple Choice Questions using Generation and Selection model
• A Study of the Tasks and Models in Machine Reading Comprehension
• A3Net: Adversarial-and-Attention Network for Machine Reading Comprehension
• Tag and Correct: Question aware Open Information Extraction with Two-stage Decoding
• Bi-directional Cognitive Thinking Network for Machine Reading Comprehension