Sciweavers

ACL
2006
13 years 11 months ago
On-Demand Information Extraction
At present, adapting an Information Extraction system to new topics is an expensive and slow process, requiring some knowledge engineering for each new topic. We propose a new par...
Satoshi Sekine
ACL
2006
13 years 11 months ago
Continuous Space Language Models for Statistical Machine Translation
Holger Schwenk, Daniel Dechelotte, Jean-Luc Gauvai...
ACL
2006
13 years 11 months ago
K-QARD: A Practical Korean Question Answering Framework for Restricted Domain
We present a Korean question answering framework for restricted domains, called K-QARD. K-QARD is developed to achieve domain portability and robustness, and the framework is succ...
Young-In Song, Hoo-Jung Chung, Kyoung-Soo Han, Joo...
ACL
2006
13 years 11 months ago
Semantic Taxonomy Induction from Heterogenous Evidence
We propose a novel algorithm for inducing semantic taxonomies. Previous algorithms for taxonomy induction have typically focused on independent classifiers for discovering new sin...
Rion Snow, Daniel Jurafsky, Andrew Y. Ng
ACL
2006
13 years 11 months ago
Unsupervised Induction of Modern Standard Arabic Verb Classes Using Syntactic Frames and LSA
We exploit the resources in the Arabic Treebank (ATB) and Arabic Gigaword (AG) to determine the best features for the novel task of automatically creating lexical semantic verb cl...
Neal Snider, Mona T. Diab
ACL
2006
13 years 11 months ago
Minimum Risk Annealing for Training Log-Linear Models
When training the parameters for a natural language system, one would prefer to minimize 1-best loss (error) on an evaluation set. Since the error surface for many natural languag...
David A. Smith, Jason Eisner
ACL
2006
13 years 11 months ago
Annealing Structural Bias in Multilingual Weighted Grammar Induction
We first show how a structural locality bias can improve the accuracy of state-of-the-art dependency grammar induction models trained by EM from unannotated examples (Klein and Ma...
Noah A. Smith, Jason Eisner
ACL
2006
13 years 11 months ago
Trace Prediction and Recovery with Unlexicalized PCFGs and Slash Features
This paper describes a parser which generates parse trees with empty elements in which traces and fillers are co-indexed. The parser is an unlexicalized PCFG parser which is guara...
Helmut Schmid
ACL
2006
13 years 11 months ago
Morphological Richness Offsets Resource Demand - Experiences in Constructing a POS Tagger for Hindi
In this paper we report our work on building a POS tagger for a morphologically rich language- Hindi. The theme of the research is to vindicate the stand that- if morphology is st...
Smriti Singh, Kuhoo Gupta, Manish Shrivastava, Pus...
ACL
2006
13 years 11 months ago
Compiling a Lexicon of Cooking Actions for Animation Generation
This paper describes a system which generates animations for cooking actions in recipes, to help people understand recipes written in Japanese. The major goal of this research is ...
Kiyoaki Shirai, Hiroshi Ookawa