PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text
Haitian Sun Tania Bedrax-Weiss William W. Cohen Google AI Language
Abstract
We consider open-domain queston answering (QA) where answers are drawn from either a corpus, a knowledge base (KB), or a combination of both of these. We focus on a setting in which a corpus is supplemented with a large but incomplete KB, and on questions that require non-trivial (e.g., “multi-hop”) reasoning. We describe PullNet, an integrated framework for (1) learning what to retrieve (from the KB and/or corpus) and (2) reasoning with this heterogeneous information to find the best answer. PullNet uses an iterative process to construct a question-specific subgraph that contains information relevant to the question. In each iteration, a graph convolutional network (graph CNN) is used to identify subgraph nodes that should be expanded using retrieval (or “pull”) operations on the corpus and/or KB. After the subgraph is complete, a similar graph CNN is used to extract the answer from the subgraph. This retrieve-and-reason process allows us to answer multi-hop questions using large KBs and corpora. PullNet is weakly supervised, requiring question-answer pairs but not gold inference paths. Experimentally PullNet improves over the prior state-of-the art, and in the setting where a cor
中文速览
开放域问答系统需要同时利用知识库（Knowledge Base, KB）和文本语料库才能回答复杂的多跳推理问题，但现有方法要么依赖启发式规则构建子图导致召回率低、图规模臃肿，要么无法有效融合两类异构知识。PullNet提出了一套迭代式"拉取-推理"框架：从问题中的实体出发，每轮迭代用图卷积网络（Graph Convolutional Network, GCN）判断哪些节点需要进一步扩展，再按需从知识库或语料库中拉取相关事实和文本句子，直到子图包含足够信息后再提取最终答案；整个过程仅需问题-答案对作为弱监督信号，无需标注推理路径。实验表明，PullNet在多个多跳问答基准上刷新了最优成绩，尤其在知识库不完整、需结合文本补全的场景下提升幅度显著——例如在MetaQA三跳问题上命中率从62.5%跃升至91.4%，在知识库一半数据缺失时仍能达到85.2%。这项工作的重要意义在于，它为如何自适应地、按需检索异构知识以支撑多步推理提供了一个可学习的端到端解决方案。
原文 arXiv:1904.09537;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1904.09537v1