# Joint Training of Candidate Extraction and Answer Selection for Reading Comprehension

arXiv: https://arxiv.org/abs/1805.06145 · HTML: https://mlsanity.com/paper/1805.06145/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 May 2018.

## Built on by (most cited first, 4 of 4)

- [A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methods](https://mlsanity.com/paper/2204.03508/) (2022)
- [Check It Again: Progressive Visual Question Answering via Visual Entailment](https://mlsanity.com/paper/2106.04605/) (2021)
- [Deep Understanding based Multi-Document Machine Reading Comprehension](https://mlsanity.com/paper/2204.03494/) (2022)
- [An Understanding-Oriented Robust Machine Reading Comprehension Model](https://mlsanity.com/paper/2207.00187/) (2022)

## Abstract (arXiv)

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.