A General FOFE-net Framework for Simple and Effective Question Answering over Knowledge Bases
This work addresses the problem of complex and heuristic-heavy methods in knowledge base question answering for NLP researchers, offering a simpler alternative with competitive performance.
The authors tackled question answering over knowledge bases by proposing a simple neural model called FOFE-net, which achieved strong results on entity discovery, linking, and relation detection across datasets like SimpleQuestions, WebQSP, and FreebaseQA.
Question answering over knowledge base (KB-QA) has recently become a popular research topic in NLP. One popular way to solve the KB-QA problem is to make use of a pipeline of several NLP modules, including entity discovery and linking (EDL) and relation detection. Recent success on KB-QA task usually involves complex network structures with sophisticated heuristics. Inspired by a previous work that builds a strong KB-QA baseline, we propose a simple but general neural model composed of fixed-size ordinally forgetting encoding (FOFE) and deep neural networks, called FOFE-net to solve KB-QA problem at different stages. For evaluation, we use two popular KB-QA datasets, SimpleQuestions and WebQSP, and a newly created dataset, FreebaseQA. The experimental results show that FOFE-net performs well on KB-QA subtasks, entity discovery and linking (EDL) and relation detection, and in turn pushing overall KB-QA system to achieve strong results on all datasets.