We present a probabilistic generative model for learning semantic parsers from ambiguous supervision. Our approach learns from natural language sentences paired with world states ...
One challenge in text processing is the treatment of case insensitive documents such as speech recognition results. The traditional approach is to re-train a language model exclud...
Cheng Niu, Wei Li 0003, Jihong Ding, Rohini K. Sri...
This paper addresses the training of classification trees for weakly labelled data. We call ”weakly labelled data”, a training set such as the prior labelling information pro...
Current semi-supervised incremental learning approaches select unlabeled examples with predicted high confidence for model re-training. We show that for many applications this dat...
Word sense disambiguation is the task to identify the intended meaning of an ambiguous word in a certain context, one of the central problems in natural language processing. This p...