This paper presents a method for learning a semantic parser from ambiguous supervision. Training data consists of natural language sentences annotated with multiple potential mean...
Compositional question answering begins by mapping questions to logical forms, but training a semantic parser to perform this mapping typically requires the costly annotation of t...
Unsupervised over-segmentation of an image into superpixels is a common preprocessing step for image parsing algorithms. Ideally, every pixel within each superpixel region will be...
Alastair P. Moore, Simon Prince, Jonathan Warrell,...
We study unsupervised methods for learning refinements of the nonterminals in a treebank. Following Matsuzaki et al. (2005) and Prescher (2005), we may for example split NP withou...
Unsupervised grammar induction is one of the most difficult works of language processing. Its goal is to extract a grammar representing the language structure using texts without a...