EMNLP
2008
13 years 6 months ago
2008
We propose a new graph-based semisupervised learning (SSL) algorithm and demonstrate its application to document categorization. Each document is represented by a vertex within a ...
EMNLP
2008
13 years 6 months ago
2008
Regular expressions have served as the dominant workhorse of practical information extraction for several years. However, there has been little work on reducing the manual effort ...
EMNLP
2008
13 years 6 months ago
2008
EMNLP
2008
13 years 6 months ago
2008
Machine learning approaches to coreference resolution are typically supervised, and require expensive labeled data. Some unsupervised approaches have been proposed (e.g., Haghighi...
EMNLP
2008
13 years 6 months ago
2008
Bootstrapping has a tendency, called semantic drift, to select instances unrelated to the seed instances as the iteration proceeds. We demonstrate the semantic drift of bootstrapp...
EMNLP
2008
13 years 6 months ago
2008
Having seen a news title "Alba denies wedding reports", how do we infer that it is primarily about Jessica Alba, rather than about weddings or reports? We probably reali...
EMNLP
2008
13 years 6 months ago
2008
We present a PropBank semantic role labeling system for English that is integrated with a dependency parser. To tackle the problem of joint syntactic
EMNLP
2008
13 years 6 months ago
2008
In this paper, we present a novel method based on CRFs in response to the two special characteristics of "contextual dependency" and "label redundancy" in sent...
EMNLP
2008
13 years 6 months ago
2008
There is growing interest in applying Bayesian techniques to NLP problems. There are a number of different estimators for Bayesian models, and it is useful to know what kinds of t...
EMNLP
2008
13 years 6 months ago
2008
We improve the quality of paraphrases extracted from parallel corpora by requiring that phrases and their paraphrases be the same syntactic type. This is achieved by parsing the E...