Dependency grammar is a descriptive and theoretical tradition in linguistics that can be
traced back to antiquity. It has long been influential in the European linguistics tradition and …

We present a simple and effective scheme for dependency parsing which is based on
bidirectional-LSTMs (BiLSTMs). Each sentence token is associated with a BiLSTM vector …

Dual decomposition, and more generally Lagrangian relaxation, is a classical method for
combinatorial optimization; it has recently been applied to several inference problems in …

We present a novel abstractive summarization framework that draws on the recent
development of a treebank for the Abstract Meaning Representation (AMR). In this …

Abstract Abstract Meaning Representation (AMR) is a semantic formalism for which a
growing set of annotated examples is available. We introduce the first approach to parse …

We assume that the tokenization of a sentence is fixed and known at parsing time. That is to
say that dependency parsers will always operate on a pre-tokenized input and are not …

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 …

Abstract Machine reading calls for programs that read and understand text, but most current
work only attempts to extract facts from redundant web-scale corpora. In this paper, we focus …

We describe a new dependency parser for English tweets, TWEEBOPARSER. The parser
builds on several contributions: new syntactic annotations for a corpus of tweets …

Over the past decades, numerous loss functions have been been proposed for a variety of
supervised learning tasks, including regression, classification, ranking, and more generally …