Web search engines work well for finding crawlable pages, but not for finding datasets hidden behind Web search forms. We describe a novel technique for detecting search forms, ...
We present a novel approach to recognizing Textual nt. Structural features are constructed from abstract tree descriptions, which are automatically extracted from syntactic depend...
We propose a new approach to characterizing the timeline of a text: temporal dependency structures, where all the events of a narrative are linked via partial ordering relations l...
Oleksandr Kolomiyets, Steven Bethard, Marie-Franci...
Verb suffixes and verb complexes of morphologically rich languages carry a lot of information. We show that this information if harnessed for the task of shallow parsing can lead ...
Harshada Gune, Mugdha Bapat, Mitesh M. Khapra, Pus...
This paper shows that it is very often possible to identify the source language of medium-length speeches in the EUROPARL corpus on the basis of frequency counts of word n-grams (...