Deng Yang, Zhang Wenxuan, Xu Weiwen, Shen Ying, Lam Wai
IEEE Trans Neural Netw Learn Syst. 2024 Aug;35(8):11231-11245. doi: 10.1109/TNNLS.2023.3258413. Epub 2024 Aug 5.
Nonfactoid question answering (QA) is one of the most extensive yet challenging applications and research areas in natural language processing (NLP). Existing methods fall short of handling the long-distance and complex semantic relations between the question and the document sentences. In this work, we propose a novel query-focused summarization method, namely a graph-enhanced multihop query-focused summarizer (GMQS), to tackle the nonfactoid QA problem. Specifically, we leverage graph-enhanced reasoning techniques to elaborate the multihop inference process in nonfactoid QA. Three types of graphs with different semantic relations, namely semantic relevance, topical coherence, and coreference linking, are constructed for explicitly capturing the question-document and sentence-sentence interrelationships. Relational graph attention network (RGAT) is then developed to aggregate the multirelational information accordingly. In addition, the proposed method can be adapted to both extractive and abstractive applications as well as be mutually enhanced by joint learning. Experimental results show that the proposed method consistently outperforms both existing extractive and abstractive methods on two nonfactoid QA datasets, WikiHow and PubMedQA, and possesses the capability of performing explainable multihop reasoning.
非事实性问答（QA）是自然语言处理（NLP）中应用最为广泛但也最具挑战性的领域之一。现有方法在处理问题与文档句子之间的长距离和复杂语义关系方面存在不足。在这项工作中，我们提出了一种新颖的以查询为中心的摘要方法，即图增强多跳以查询为中心的摘要器（GMQS），以解决非事实性问答问题。具体而言，我们利用图增强推理技术来阐述非事实性问答中的多跳推理过程。构建了具有不同语义关系的三种类型的图，即语义相关性、主题连贯性和指代链接，以明确捕捉问题与文档以及句子与句子之间的相互关系。然后开发关系图注意力网络（RGAT）来相应地聚合多关系信息。此外，所提出的方法既可以适用于抽取式和抽象式应用，也可以通过联合学习相互增强。实验结果表明，所提出的方法在两个非事实性问答数据集WikiHow和PubMedQA上始终优于现有的抽取式和抽象式方法，并且具有执行可解释多跳推理的能力。
