S-Net: From Answer Extraction to Answer Generation for Machine Reading Comprehension
This addresses the problem of generating answers from multiple passages for machine reading comprehension, representing an incremental improvement over existing methods.
The paper tackles machine reading comprehension on the MS-MARCO dataset, where answers are not necessarily exact text spans, by proposing an extraction-then-synthesis framework that first extracts evidence from passages and then generates answers, achieving state-of-the-art performance.
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.