论文标题
为可解释的多跳问题回答生成后续问题
Generating Followup Questions for Interpretable Multi-hop Question Answering
论文作者
论文摘要
我们提出了一个框架，用于回答开放型域的多跳问题，其中读取部分信息并用于生成后续问题，最终通过预验证的单跳答答提取器来回答。该框架使每个跳跃都可以解释，并使得与以后的啤酒花相关联，以便于第一次跳跃。作为该框架的第一个实例化，我们训练一个指针生成网络，以根据问题和部分信息来预测后续问题。这提供了神经问题生成网络的新颖应用，该网络可用于根据最终答案及其支持事实提供弱地面真相的后续问题。学会生成后续问题，以选择相关答案跨越下游支持事实，同时避免分心的前提，这对文本生成构成了令人兴奋的语义挑战。我们使用HOTPOTQA的两跳桥问题进行了评估。
We propose a framework for answering open domain multi-hop questions in which partial information is read and used to generate followup questions, to finally be answered by a pretrained single-hop answer extractor. This framework makes each hop interpretable, and makes the retrieval associated with later hops as flexible and specific as for the first hop. As a first instantiation of this framework, we train a pointer-generator network to predict followup questions based on the question and partial information. This provides a novel application of a neural question generation network, which is applied to give weak ground truth single-hop followup questions based on the final answers and their supporting facts. Learning to generate followup questions that select the relevant answer spans against downstream supporting facts, while avoiding distracting premises, poses an exciting semantic challenge for text generation. We present an evaluation using the two-hop bridge questions of HotpotQA.
