Joint Training of Candidate Extraction and Answer Selection for Reading Comprehension
arXiv:1805.06145
Abstract
While sophisticated neural-based techniques have been developed in reading comprehension, most approaches model the answer in an independent manner, ignoring its relations with other answer candidates. This problem can be even worse in open-domain scenarios, where candidates from multiple passages should be combined to answer a single question. In this paper, we formulate reading comprehension as an extract-then-select two-stage procedure. We first extract answer candidates from passages, then select the final answer by combining information from all the candidates. Furthermore, we regard candidate extraction as a latent variable and train the two-stage process jointly with reinforcement learning. As a result, our approach has improved the state-of-the-art performance significantly on two challenging open-domain reading comprehension datasets. Further analysis demonstrates the effectiveness of our model components, especially the information fusion of all the candidates and the joint training of the extract-then-select procedure.
arXiv comment10 pages, Accepted by ACL 2018
References in corpus (14)
- Teaching Machines to Read and Comprehend
- Sequence Level Training with Recurrent Neural Networks
- SQuAD: 100,000+ Questions for Machine Comprehension of Text
- The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations
- Machine Comprehension Using Match-LSTM and Answer Pointer
- SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
- ReasoNet: Learning to Stop Reading in Machine Comprehension
- Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering
- Quasar: Datasets for Question Answering by Search and Reading
- Ask the Right Questions: Active Question Reformulation with Reinforcement Learning
- Learning Recurrent Span Representations for Extractive Question Answering
- R: Reinforced Reader-Ranker for Open-Domain Question Answering
- Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering
- DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications