Causal Question Answering with Reinforcement Learning

arXiv:2311.02760v2 Announce Type: replace-cross
Abstract: Causal questions inquire about causal relationships between different events or phenomena. They are important for a variety of use cases, including virtual assistants and search engines. However, many current approaches to causal question answering cannot provide explanations or evidence for their answers. Hence, in this paper, we aim to answer causal questions with a causality graph, a large-scale dataset of causal relations between noun phrases along with the relations' provenance data. Inspired by recent, successful …

abstract aim arxiv assistants cases causal cs.ai cs.lg current events evidence however paper question question answering questions reinforcement reinforcement learning relationships search type use cases virtual virtual assistants