Sciweavers

627 search results - page 95 / 126
» Contextual Grammars as Generative Models of Natural Language...
Sort
View
ACL
2006
13 years 10 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
SEMWEB
2004
Springer
14 years 2 months ago
Working with Multiple Ontologies on the Semantic Web
The standardization of the second generation Web Ontology Language, OWL, leaves a crucial issue for Web-based ontologies unsatisfactorily resolved: how to represent and reason with...
Bernardo Cuenca Grau, Bijan Parsia, Evren Sirin
EMNLP
2010
13 years 6 months ago
Lessons Learned in Part-of-Speech Tagging of Conversational Speech
This paper examines tagging models for spontaneous English speech transcripts. We analyze the performance of state-of-the-art tagging models, either generative or discriminative, ...
Vladimir Eidelman, Zhongqiang Huang, Mary P. Harpe...
AAAI
2010
13 years 10 months ago
A Two-Dimensional Topic-Aspect Model for Discovering Multi-Faceted Topics
This paper presents the Topic-Aspect Model (TAM), a Bayesian mixture model which jointly discovers topics and aspects. We broadly define an aspect of a document as a characteristi...
Michael Paul, Roxana Girju
EMNLP
2009
13 years 6 months ago
Unsupervised morphological segmentation and clustering with document boundaries
Many approaches to unsupervised morphology acquisition incorporate the frequency of character sequences with respect to each other to identify word stems and affixes. This typical...
Taesun Moon, Katrin Erk, Jason Baldridge