Abstract
Software with natural-language user interfaces has an ever-increasing importance. However, the quality of the included Question Answering (QA) functionality is still not sufficient regarding the number of questions that are answered correctly. In our work, we address the research problem of how the QA quality of a given system can be improved just by evaluating the natural-language input (i.e., the user's question) and output (i.e., the system's answer). Our main contribution is an approach capable of identifying wrong answers provided by a QA system. Hence, filtering incorrect answers from a list of answer candidates is leading to a highly improved QA quality. In particular, our approach has shown its potential while removing in many cases the majority of incorrect answers, which increases the QA quality significantly in comparison to the non-filtered output of a system.
Abstract (translated)
URL
https://arxiv.org/abs/2112.05452
