Sciweavers

154
Voted
EMNLP
2010
15 years 6 days ago
Training Continuous Space Language Models: Some Practical Issues
Using multi-layer neural networks to estimate the probabilities of word sequences is a promising research area in statistical language modeling, with applications in speech recogn...
Hai Son Le, Alexandre Allauzen, Guillaume Wisniews...
EMNLP
2010
15 years 6 days ago
Constraints Based Taxonomic Relation Classification
Determining whether two terms in text have an ancestor relation (e.g. Toyota and car) or a sibling relation (e.g. Toyota and Honda) is an essential component of textual inference ...
Quang Do, Dan Roth
111
Voted
EMNLP
2010
15 years 6 days ago
Utilizing Extra-Sentential Context for Parsing
Syntactic consistency is the preference to reuse a syntactic construction shortly after its appearance in a discourse. We present an analysis of the WSJ portion of the Penn Treeba...
Jackie Chi Kit Cheung, Gerald Penn
EMNLP
2010
15 years 6 days ago
Practical Linguistic Steganography Using Contextual Synonym Substitution and Vertex Colour Coding
Linguistic Steganography is concerned with hiding information in natural language text. One of the major transformations used in Linguistic Steganography is synonym substitution. ...
Ching-Yun Chang, Stephen Clark
144
Voted
EMNLP
2010
15 years 6 days ago
A New Approach to Lexical Disambiguation of Arabic Text
We describe a model for the lexical analysis of Arabic text, using the lists of alternatives supplied by a broad-coverage morphological analyzer, SAMA, which include stable lemma ...
Rushin Shah, Paramveer S. Dhillon, Mark Liberman, ...
109
Voted
EMNLP
2010
15 years 6 days ago
A Semi-Supervised Method to Learn and Construct Taxonomies Using the Web
Although many algorithms have been developed to harvest lexical resources, few organize the mined terms into taxonomies. We propose (1) a semi-supervised algorithm that uses a roo...
Zornitsa Kozareva, Eduard H. Hovy
114
Voted
EMNLP
2010
15 years 6 days ago
Exploiting Conversation Structure in Unsupervised Topic Segmentation for Emails
This work concerns automatic topic segmentation of email conversations. We present a corpus of email threads manually annotated with topics, and evaluate annotator reliability. To...
Shafiq R. Joty, Giuseppe Carenini, Gabriel Murray,...
88
Voted
EMNLP
2010
15 years 6 days ago
Modeling Perspective Using Adaptor Grammars
Strong indications of perspective can often come from collocations of arbitrary length; for example, someone writing get the government out of my X is typically expressing a conse...
Eric Hardisty, Jordan L. Boyd-Graber, Philip Resni...
111
Voted
EMNLP
2010
15 years 6 days ago
SCFG Decoding Without Binarization
Conventional wisdom dictates that synchronous context-free grammars (SCFGs) must be converted to Chomsky Normal Form (CNF) to ensure cubic time decoding. For arbitrary SCFGs, this...
Mark Hopkins, Greg Langmead
102
Voted
EMNLP
2010
15 years 6 days ago
A Latent Variable Model for Geographic Lexical Variation
The rapid growth of geotagged social media raises new computational possibilities for investigating geographic linguistic variation. In this paper, we present a multi-level genera...
Jacob Eisenstein, Brendan O'Connor, Noah A. Smith,...