Sciweavers

EMNLP
2006
13 years 6 months ago
Multilingual Deep Lexical Acquisition for HPSGs via Supertagging
We propose a conditional random fieldbased method for supertagging, and apply it to the task of learning new lexical items for HPSG-based precision grammars of English and Japanes...
Phil Blunsom, Timothy Baldwin
EMNLP
2006
13 years 6 months ago
Automatic Construction of Predicate-argument Structure Patterns for Biomedical Information Extraction
This paper presents a method of automatically constructing information extraction patterns on predicate-argument structures (PASs) obtained by full parsing from a smaller training...
Akane Yakushiji, Yusuke Miyao, Tomoko Ohta, Yuka T...
EMNLP
2006
13 years 6 months ago
Statistical Ranking in Tactical Generation
In this paper we describe and evaluate several statistical models for the task of realization ranking, i.e. the problem of discriminating between competing surface realizations ge...
Erik Velldal, Stephan Oepen
EMNLP
2006
13 years 6 months ago
Short Text Authorship Attribution via Sequence Kernels, Markov Chains and Author Unmasking: An Investigation
We present an investigation of recently proposed character and word sequence kernels for the task of authorship attribution based on relatively short texts. Performance is compare...
Conrad Sanderson, Simon Günter
EMNLP
2006
13 years 6 months ago
Is it Really that Difficult to Parse German?
This paper presents a comparative study of probabilistic treebank parsing of German, using the Negra and T
Sandra Kübler, Erhard W. Hinrichs, Wolfgang M...
EMNLP
2006
13 years 6 months ago
Exploiting Discourse Structure for Spoken Dialogue Performance Analysis
In this paper we study the utility of discourse structure for spoken dialogue performance modeling. We experiment with various ways of exploiting the discourse structure: in isola...
Mihai Rotaru, Diane J. Litman
EMNLP
2006
13 years 6 months ago
Sentence ordering with manifold-based classification in multi-document summarization
In this paper, we propose a sentence ordering algorithm using a semi-supervised sentence classification and historical ordering strategy. The classification is based on the manifo...
Paul D. Ji, Stephen G. Pulman
EMNLP
2006
13 years 6 months ago
Better Informed Training of Latent Syntactic Features
We study unsupervised methods for learning refinements of the nonterminals in a treebank. Following Matsuzaki et al. (2005) and Prescher (2005), we may for example split NP withou...
Markus Dreyer, Jason Eisner