Modeling Extractive Question Answering Using Encoder-Decoder Models with Constrained Decoding and Evaluation-Based Reinforcement Learning

Shaobo Li, Chengjie Sun (), Bingquan Liu, Yuanchao Liu and Zhenzhou Ji
Additional contact information
Shaobo Li: School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China
Chengjie Sun: School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China
Bingquan Liu: School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China
Yuanchao Liu: School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China
Zhenzhou Ji: School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China

Mathematics, 2023, vol. 11, issue 7, 1-16

Abstract: Extractive Question Answering, also known as machine reading comprehension, can be used to evaluate how well a computer comprehends human language. It is a valuable topic with many applications, such as in chatbots and personal assistants. End-to-end neural-network-based models have achieved remarkable performance on these tasks. The most frequently used approach to extract answers with neural networks is to predict the answer’s start and end positions in the document, independently or jointly. In this paper, we propose another approach that considers all words in an answer jointly. We introduce an encoder-decoder model to learn from all words in the answer. This differs from previous works. which usually focused on the start and end and ignored the words in the middle. To help the encoder-decoder model to perform this task better, we employ evaluation-based reinforcement learning with different reward functions. The results of an experiment on the SQuAD dataset show that the proposed method can outperform the baseline in terms of F1 scores, offering another potential approach to solve the extractive QA task.

Keywords: natural language processing; question answering; encoder-decoder models; reinforcement learning; neural network; machine learning (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2023
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/11/7/1624/pdf (application/pdf)
https://www.mdpi.com/2227-7390/11/7/1624/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:11:y:2023:i:7:p:1624-:d:1108909

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().