International Joint Conference on Artificial Intelligence · 2016 · 24 citations · 5 references
ComputingComputer ScienceKnowledge RepresentationMachine LearningNatural Language ProcessingKnowledge Base DesignNatural Language UnderstandingQuestion AnsweringFactoid Question AnsweringKnowledge-based Question AnsweringQuestion Answering CorporaQuestion Answering SystemsSubstructure FormationTemplate-based Question Answering
Question answering (QA) has become a popular way for humans to access billion-scale knowledge bases. QA systems over knowledge bases produce accurate and concise answers. The key of QA over knowledge bases is to map the question to a certain substructure in the knowledge base. To do this, KBQA (Question Answering over Knowledge Bases) uses a new kind of question representation: templates, learned from a million scale QA corpora. For example, for questions about a city's population, KBQA learns templates such as What's the population of $city?, How many people are there in $city?. It learns overall 1171303 templates for 4690 relations. Based on these templates, KBQA effectively and efficiently supports binary factoid questions or complex questions.
5
Wentao Wu, Hongsong Li, Haixun Wang et al. · 2012 · 782 citations
Short text conceptualization using a probabilistic knowledgebase
Yangqiu Song, Haixun Wang, Zhongyuan Wang et al. · 2011 · 209 citations