This contribution reviews (some of) the history of analysis by synthesis, an approach to
perception and comprehension articulated in the 1950s. Whereas much research has …

Multiword expressions (MWEs) are a class of linguistic forms spanning conventional word
boundaries that are both idiosyncratic and pervasive across different languages. The …

Many tasks involve predicting a large number of variables that depend on each other as well
as on other observed variables. Structured prediction methods are essentially a combination …

The Handbook of Natural Language Processing, Second Edition presents practical tools
and techniques for implementing natural language processing in computer systems. Along …

Conditional random fields for sequence labeling offer advantages over both generative
models like HMMs and classifiers applied at each sequence position. Among sequence …

Conditional random fields (CRFs) combine the modeling flexibility of graphical models with
the ability to use rich, nonindependent features of the input. In this tutorial, we review …

Discriminative reranking is one method for constructing high-performance statistical parsers
(Collins, 2000). A discriminative reranker requires a source of candidate parses for each …

We present an effective training algorithm for linearly-scored dependency parsers that
implements online largemargin multi-class training (Crammer and Singer, 2003; Crammer et …

Dependency parsing has been a topic of active research in natural language processing
during the last several years. The CoNLL-2006 shared task (Buchholz and Marsi, 2006) …

This paper reports on the TIGER Treebank, a corpus of currently 35.000 syntactically
annotated German newspaper sentences. We describe what kind of information is encoded …