作者: Tianrui Li , Yu Shi , Huaishao Luo , Linjun Shou , Ming Gong
DOI:
关键词: Context (language use) 、 Artificial intelligence 、 Computer science 、 Question answering 、 Matrix (mathematics) 、 Probability vector 、 Sampling (statistics) 、 Stochastic matrix 、 Machine learning 、 Position (vector) 、 Span (engineering)
摘要: Span extraction is an essential problem in machine reading comprehension. Most of the existing algorithms predict the start and end positions of an answer span in the given …