NAACL
2007
14 years 1 months ago
2007
This paper addresses the task of providing extended responses to questions regarding specialized topics. This task is an amalgam of information retrieval, topical summarization, a...
NAACL
2007
14 years 1 months ago
2007
A twin-model is proposed for coreference resolution: a link component, modeling the coreferential relationship between an anaphor and a candidate antecedent, and a creation compon...
NAACL
2007
14 years 1 months ago
2007
Standard pairwise coreference resolution systems are subject to errors resulting from their performing anaphora identification as an implicit part of coreference resolution. In t...
NAACL
2007
14 years 1 months ago
2007
PropBank has been widely used as training data for Semantic Role Labeling. However, because this training data is taken from the WSJ, the resulting machine learning models tend to...
NAACL
2007
14 years 1 months ago
2007
This paper reports experiments in which pCRU — a generation framework that combines probabilistic generation methodology with a comprehensive model of the generation space — i...
NAACL
2007
14 years 1 months ago
2007
An open issue in data-driven dependency parsing is how to handle non-projective dependencies, which seem to be required by linguistically adequate representations, but which pose ...
NAACL
2007
14 years 1 months ago
2007
Traditional noun phrase coreference resolution systems represent features only of pairs of noun phrases. In this paper, we propose a machine learning method that enables features ...
NAACL
2007
14 years 1 months ago
2007
We compare two pivot strategies for phrase-based statistical machine translation (SMT), namely phrase translation and sentence translation. The phrase translation strategy means t...
NAACL
2007
14 years 1 months ago
2007
An intelligent thesaurus assists a writer with alternative choices of words and orders them by their suitability in the writing context. In this paper we focus on methods for auto...
NAACL
2007
14 years 1 months ago
2007
This work evaluates a system that uses interpolated predictions of reading difficulty that are based on both vocabulary and grammatical features. The combined approach is compared...