论文标题
多跳问题答案的语义句子组成推理
Semantic Sentence Composition Reasoning for Multi-Hop Question Answering
论文作者
论文摘要
由于缺乏数据不足，现有的多跳开放域问答系统需要根据每个问题有效地找出相关的支持事实。为了减轻语义事实句子检索和多跳上下文扩展的挑战，我们为多跳的问题答案任务提供了一种语义句子构成推理方法，该任务由两个关键模块组成：多阶段语义匹配模块（MSSM）和事实句子组成模块（FSC）。通过事实句子和多阶段语义检索的结合，我们的方法可以为模型培训和推理提供更全面的上下文信息。实验结果表明，我们的模型能够合并现有的预训练的语言模型，并在QASC任务上胜过现有的SOTA方法，并提高了约9％。
Due to the lack of insufficient data, existing multi-hop open domain question answering systems require to effectively find out relevant supporting facts according to each question. To alleviate the challenges of semantic factual sentences retrieval and multi-hop context expansion, we present a semantic sentence composition reasoning approach for a multi-hop question answering task, which consists of two key modules: a multi-stage semantic matching module (MSSM) and a factual sentence composition module (FSC). With the combination of factual sentences and multi-stage semantic retrieval, our approach can provide more comprehensive contextual information for model training and reasoning. Experimental results demonstrate our model is able to incorporate existing pre-trained language models and outperform the existing SOTA method on the QASC task with an improvement of about 9%.
