Unsupervised learning of linguistic structure is a difficult problem. A common approach is to define a generative model and maximize the probability of the hidden structure give...
Many sequence labeling tasks in NLP require solving a cascade of segmentation and tagging subtasks, such as Chinese POS tagging, named entity recognition, and so on. Traditional p...
Gesture and speech are co-expressive and complementary channels of a single human language system. While speech carries the major load of symbolic presentation, gesture provides th...
Information extraction (IE) holds the promise of generating a large-scale knowledge base from the Web’s natural language text. Knowledge-based weak supervision, using structured...
Raphael Hoffmann, Congle Zhang, Xiao Ling, Luke S....
Previous information extraction (IE) systems are typically organized as a pipeline architecture of separated stages which make independent local decisions. When the data grows bey...
Qi Li, Sam Anzaroot, Wen-Pin Lin, Xiang Li, Heng J...