Paragraph Vectors has been recently proposed as an unsupervised method for learning distributed representations for pieces of texts. In their work, the authors showed that the method can learn an embedding of movie review texts which can be leveraged for sentiment analysis. That proof of concept, while encouraging, was rather narrow. Here we consider tasks other than sentiment analysis, provide...

“please ensure that the abstract present in the manuscript matches exactly what is in the submission system” Response: Checked. Tables. “...include the tables within the text.... Move landscape orientated tables to the additional files and renumber tables accordingly...” Response: Modified as suggested. Three additional files are provided with an additional files section added in the manuscript...

Many of the processing steps in natural language engineering can be performed using nite state transducers An optimal way to create such transducers is to compile them from regular expressions This paper is an introduction to the regular expression calculus extended with certain operators that have proved very useful in natural language appli cations ranging from tokenization to light parsing T...

The proposed ISO standard Enhancements to LOTOS (E-LOTOS) is used to describe the leader election protocol of the IEEE 1394 serial multimedia bus (``FireWire''). The E-LOTOS language facilitates descriptions at several levels of abstraction, therefore a broad understanding of the protocol at an abstract level can be gained before adding more complexity and concrete detail. A secondary aim is to...

• On page 2, Materials and Methods, right column, first full paragraph, second sentence, “serum creatinine [mt] 2.8 mg/dL” has been corrected to “serum creatinine >2.8 mg/dL”. The same correction was done in the sixth full paragraph, first sentence. • On page 4, Results, right column, first full paragraph “Knox” has been corrected to “NOx”. The same correction was done on page 5, left column, f...

In this paper we propose a machinelearning approach to paragraph boundary identification which utilizes linguistically motivated features. We investigate the relation between paragraph boundaries and discourse cues, pronominalization and information structure. We test our algorithm on German data and report improvements over three baselines including a reimplementation of Sporleder & Lapata’s (...