SeMantic AnsweR Type prediction task (SMART) at ISWC 2020 Semantic Web Challenge

Question Answering (QA) is a popular task in Natural Language Processing and Information Retrieval, in which the goal is to answer a natural language question (going beyond the document retrieval). There are further sub-tasks, for instance, reading comprehension, in which the expected answers can be either a segment of text or span, from the corresponding reading passage of text. The Stanford Question Answering Dataset (SQuAD) [Rajpurkar et al., 2018] is an example of this task. Similarly, another task is Question Answering over Knowledge Bases, in which the expected answer can either be a set of entities in the knowledge base or an answer derived from an aggregation of them. Question Answering over Linked Data (QALD) [Usbeck et al., 2018] and Large Scale Complex Question Answering Dataset (LC-QuAD) [Dubey et al., 2019] are two examples for this task Question or answer type classification plays a key role in question answering [Harabagiu et al., 2000, Allam and Haggag, 2012].