Answers are grounded in this paper and cite their sources.
Question answering promises a means of efficiently searching web-based content repositories such as Wikipedia. However, the systems of this type most prevalent today merely conduct their learning once in an offline training phase while, afterwards, all parameters remain static. Thus, the possibility of improvement over time is precluded. As a consequence of this shortcoming, question answering is not currently taking advantage of the wealth of feedback mechanisms that have become prominent on the web (e. g., buttons for liking, voting, or sharing).
No takes yet. Share an insight, caveat, or question.
Kratzwald et al. (2019) studied this question.