The lexicon of any natural language encodes a huge number of distinct word meanings. Just
to understand this article, you will need to know what thousands of words mean. The space …

Frame semantics is a linguistic theory that has been instantiated for English in the FrameNet
lexicon. We solve the problem of frame-semantic parsing using a two-stage statistical model …

This paper introduces the task of questionanswer driven semantic role labeling (QA-SRL),
where question-answer pairs are used to represent predicate-argument structure. For …

We present two latent variable models for learning character types, or personas, in film, in
which a persona is defined as a set of mixtures over latent lexical classes. These lexical …

We propose a framework for abstractive summarization of multi-documents, which aims to
select contents of summary not from the source document sentences but from the semantic …

There is provided a system including a non-transitory memory storing a media library
including an ordered plurality of media contents, each including a plurality of attribute tags …

Spoken dialogue systems typically use predefined semantic slots to parse users' natural
language inputs into unified semantic representations. To define the slots, domain experts …

Most existing systems for subcategorization frame (SCF) acquisition rely on supervised
parsing and infer SCF distributions at type, rather than instance level. These systems suffer …

We present the first unsupervised approach for semantic parsing that rivals the accuracy of
supervised approaches in translating natural-language questions to database queries. Our …

We introduce a scalable Bayesian preference learning method for identifying convincing
arguments in the absence of gold-standard ratings or rankings. In contrast to previous work …