Assigning semantic roles to the constituents of a natural language sentence is an important first step in translating natural language into a logical form for further processing. I present a statistical classifier which can perform this task using minimal syntactic cues. I use the syntactic and the semantic head of each constituent as the only features and present simple rules for extracting th...

Millipedes (Diplopoda), with a few notable exceptions, are poor dispersers, showing a very high degree of endemicity, not the least in mountains. The first samplings of the Mesovoid Shallow Substratum (MSS) of the higher altitudes of the Sierra Nevada Mountains (Baetic System, Southern Spain) have led to the discovery of a high number of millipedes, each of the species present showing a differe...

In this paper we examine the influence of dimensionality on natural language route directions in dialogue. Specifically, we show that giving route instructions in a quasi-3d environment leads to experiential descriptive accounts, as manifested by a higher proportion of location descriptions, lack of chunking, use of 1st person singular personal pronouns, and more frequent use of temporal and sp...

This paper describes the approach of the system that we built as part of the participation in ‘PAN 2015 Source Retrieval’ task. Chunking of documents based on paragraphs and efficient download filtering improved the overall performance of the system. Source Retrieval is an important task of a Plagiarism Detection system

Our approach for unsupervised extraction of prosodic structure in spontaneous speech consists of the four steps: chunking into interpausal units, syllable nucleus extraction, prosodic boundary detection, and pitch accent detection. The extraction is based on acoustic features derived from F0 parameterization, and on energy and segment duration features. Phrase boundaries and accents are detecte...

Significant amount of work has been devoted recently to develop learning techniques that can be used to generate partial (shallow) analysis of natural language sentences rather than a full parse. In this work we set out to evaluate whether this direction is worthwhile by comparing a learned shallow parser to one of the best learned full parsers on tasks both can perform — identifying phrases in...

The Indian Ocean tsunami of 26 December 2004 was one of the greatest natural disasters; it was also the first internet-mediated natural disaster. Despite the presumed ubiquity and power of advanced technologies including satellites and the internet, no advance warning was given to the affected coastal populations by their governments or others. This article examines the conditions for the suppl...