| Full text | |
| Author(s): |
Pirozelli, Paulo
;
Brandao, Anarosa A. F.
;
Peres, Sarajane M.
;
Cozman, Fabio G.
;
Xavier-Junior, JC
;
Rios, RA
Total Authors: 6
|
| Document type: | Journal article |
| Source: | INTELLIGENT SYSTEMS, PT II; v. 13654, p. 15-pg., 2022-01-01. |
| Abstract | |
Question answering (QA) systems are usually structured as strict conditional generators, which return an answer for every input question. Sometimes, however, the policy of always responding to questions may prove itself harmful, given the possibility of giving inaccurate answers, particularly for ambiguous or sensitive questions; instead, it may be better for a QA system to decide which questions should be answered or not. In this paper, we explore dual system architectures that filter unanswerable or meaningless questions, thus answering only a subset of the questions raised. Two experiments are performed in order to evaluate this modular approach: a classification on SQuAD 2.0 for unanswerable questions, and a regression on Pir ' a for question meaningfulness. Despite the difficulties involved in the tasks, we show that filtering questions may contribute to improve the quality of the answers generated by QA systems. By using classification and regression models to filter questions, we can get better control over the accuracy of the answers produced by the answerer systems. (AU) | |
| FAPESP's process: | 19/07665-4 - Center for Artificial Intelligence |
| Grantee: | Fabio Gagliardi Cozman |
| Support Opportunities: | Research Grants - Research Program in eScience and Data Science - Research Centers in Engineering Program |