TY - JOUR AU - Khot, Tushar AU - Clark, Peter AU - Guerquin, Michal AU - Jansen, Peter AU - Sabharwal, Ashish PY - 2020/04/03 Y2 - 2024/03/28 TI - QASC: A Dataset for Question Answering via Sentence Composition JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 34 IS - 05 SE - AAAI Technical Track: Natural Language Processing DO - 10.1609/aaai.v34i05.6319 UR - https://ojs.aaai.org/index.php/AAAI/article/view/6319 SP - 8082-8090 AB - <p>Composing knowledge from multiple pieces of texts is a key challenge in multi-hop question answering. We present a multi-hop reasoning dataset, <strong>Q</strong>uestion <strong>A</strong>nswering via <strong>S</strong>entence <strong>C</strong>omposition (QASC), that requires retrieving facts from a large corpus and composing them to answer a multiple-choice question. QASC is the first dataset to offer two desirable properties: (a) the facts to be composed are annotated in a large corpus, and (b) the decomposition into these facts is not evident from the question itself. The latter makes retrieval challenging as the system must introduce new concepts or relations in order to discover potential decompositions. Further, the reasoning model must then learn to identify valid compositions of these retrieved facts using common-sense reasoning. To help address these challenges, we provide annotation for supporting facts as well as their composition. Guided by these annotations, we present a two-step approach to mitigate the retrieval challenges. We use other multiple-choice datasets as additional training data to strengthen the reasoning model. Our proposed approach improves over current state-of-the-art language models by 11% (absolute). The reasoning and retrieval problems, however, remain unsolved as this model still lags by 20% behind human performance.</p> ER -