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

TL;DR

This paper introduces S-Net, a novel extraction-then-synthesis framework for machine reading comprehension on MS-MARCO, combining passage ranking, evidence extraction, and answer generation to improve performance over existing methods.

Contribution

The paper proposes a new extraction-then-synthesis approach that effectively synthesizes answers from multiple passages, advancing beyond traditional span-based extraction methods.

Findings

Outperforms state-of-the-art methods on MS-MARCO dataset

Integrates passage ranking with evidence extraction and answer synthesis

Demonstrates effectiveness of sequence-to-sequence models for answer generation

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.