Complex Factoid Question Answering with a Free-Text Knowledge Graph
Complex Factoid Question Answering with a Free-Text Knowledge Graph
复制标题
DOI：
10.1145/3366423.3380197
复制
发表时间：
2020-04
期刊：
影响因子：
--
通讯作者：
Chen Zhao
中科院分区：
文献类型：
--
作者：
Chen Zhao
我们介绍了德尔夫特，一个事实问答系统，它结合了知识图问答方法的细微差别和深度与自由文本的更广泛的覆盖面。德尔夫特从维基百科构建了一个自由文本知识图，其中实体作为节点，实体共同出现的句子作为边。对于每个问题，德尔夫特使用文本句子作为边，找到将问题实体节点连接到候选者的子图，从而创建密集且高覆盖率的语义图。一种新颖的图神经网络通过自由文本图的推理-通过沿着边的信息组合节点上的证据-来选择最终答案。在三个问答数据集上的实验表明，德尔夫特能比基于机器阅读的模型、基于bert的答案排序和记忆网络更好地回答实体丰富的问题。德尔夫特的优势来自于它的自由文本知识图的高覆盖率是dbpedia关系的两倍多以及新颖的图神经网络，它可以在丰富但嘈杂的自由文本证据上进行推理。
We introduce delft, a factoid question answering system which combines the nuance and depth of knowledge graph question answering approaches with the broader coverage of free-text. delft builds a free-text knowledge graph from Wikipedia, with entities as nodes and sentences in which entities co-occur as edges. For each question, delft finds the subgraph linking question entity nodes to candidates using text sentences as edges, creating a dense and high coverage semantic graph. A novel graph neural network reasons over the free-text graph—combining evidence on the nodes via information along edge sentences—to select a final answer. Experiments on three question answering datasets show delft can answer entity-rich questions better than machine reading based models, bert-based answer ranking and memory networks. delft’s advantage comes from both the high coverage of its free-text knowledge graph—more than double that of dbpedia relations—and the novel graph neural network which reasons on the rich but noisy free-text evidence.