A short survey on end-to-end simple question answering systems
- PDF / 1,924,629 Bytes
- 25 Pages / 439.37 x 666.142 pts Page_size
- 26 Downloads / 198 Views
A short survey on end‑to‑end simple question answering systems José Wellington Franco da Silva1 · Amanda Drielly Pires Venceslau1 · Juliano Efson Sales2 · José Gilvan Rodrigues Maia3 · Vládia Célia Monteiro Pinheiro4 · Vânia Maria Ponte Vidal3
© Springer Nature B.V. 2020
Abstract Searching for a specific and meaningful piece of information in the humongous textual data volumes found on the internet and knowledge repositories is a very challenging task. This problem is usually constrained to answering simple, factoid questions by resorting to a question answering (QA) system built on top of complex approaches such as heuristics, information retrieval, and machine learning. More precisely, deep learning methods became into sharp focus of this research field because such purposes can realize the benefits of the vast amounts of data to boost the practical results of QA systems. In this paper, we present a systematic survey on deep learning-based QA systems concerning factoid questions, with particular focus on how each existing system addresses their critical features in terms of learning end-to-end models. We also detail the evaluation process carried out on these systems and discuss how each approach differs from the others in terms of the challenges tackled and the strategies employed. Finally, we present the most prominent research problems still open in the field.
* José Wellington Franco da Silva [email protected] Amanda Drielly Pires Venceslau [email protected] Juliano Efson Sales juliano‑sales@uni‑passau.de José Gilvan Rodrigues Maia [email protected] Vládia Célia Monteiro Pinheiro [email protected] Vânia Maria Ponte Vidal [email protected] 1
Universidade Federal do Ceará, Crateús, Brazil
2
University of Passau, Germany, Passau, Germany
3
Universidade Federal do Ceará, Campus do Pici, Fortaleza, Ceará, Brazil
4
University of Fortaleza, Fortaleza, Ceará, Brazil
13
Vol.:(0123456789)
J. W. F. da Silva et al.
Keywords Survey · Neural networks · Simple question answering · Deep learning
1 Introduction Question answering (QA) systems is a reasonably old research field of Computer Science if we consider text documents and information retrieval as crucial aspects of QA (Abualigah 2019). According to Diefenbach et al. (2018), the first QA systems were developed to mediate access to information found in the database in the latter 60s and the beginning of the 70s. The challenge concerns the translation of a user’s specific information necessity into a format that can be adequately evaluated using standard query processing methods or inferences from the Semantic Web. The main idea behind a QA system operating over a knowledge base consists of finding the information requested from users’ expressing themselves using natural language. Traditionally, the process of answering a question can be divided into five steps corresponding to question analysis, phrase mapping, disambiguation, query construction and querying distributed knowledge (Diefenbach et al. 2018). However, g
Data Loading...
