Sciweavers

NAACL
2010
14 years 10 months ago
Classification of Prosodic Events using Quantized Contour Modeling
We present Quantized Contour Modeling (QCM), a Bayesian approach to the classification of acoustic contours. We evaluate the performance of this technique in the classification of...
Andrew Rosenberg
98
Voted
NAACL
2010
14 years 10 months ago
Bayesian Inference for Finite-State Transducers
We describe a Bayesian inference algorithm that can be used to train any cascade of weighted finite-state transducers on end-toend data. We also investigate the problem of automat...
David Chiang, Jonathan Graehl, Kevin Knight, Adam ...
NAACL
2010
14 years 10 months ago
Utility Evaluation of Cross-document Information Extraction
We describe a utility evaluation to determine whether cross-document information extraction (IE) techniques measurably improve user performance in news summary writing. Two groups...
Heng Ji, Zheng Chen, Jonathan Feldman, Antonio Gon...
NAACL
2010
14 years 10 months ago
A Hybrid Morphologically Decomposed Factored Language Models for Arabic LVCSR
In this work, we try a hybrid methodology for language modeling where both morphological decomposition and factored language modeling (FLM) are exploited to deal with the complex ...
Amr El-Desoky, Ralf Schlüter, Hermann Ney
NAACL
2010
14 years 10 months ago
Quantifying the Limits and Success of Extractive Summarization Systems Across Domains
This paper analyzes the topic identification stage of single-document automatic text summarization across four different domains, consisting of newswire, literary, scientific and ...
Hakan Ceylan, Rada Mihalcea, Umut O'zertem, Elena ...
NAACL
2010
14 years 10 months ago
Automatic Generation of Personalized Annotation Tags for Twitter Users
This paper introduces a system designed for automatically generating personalized annotation tags to label Twitter user's interests and concerns. We applied TFIDF ranking and...
Wei Wu, Bin Zhang, Mari Ostendorf
101
Voted
NAACL
2010
14 years 10 months ago
Evaluation Metrics for the Lexical Substitution Task
We identify some problems of the evaluation metrics used for the English Lexical Substitution Task of SemEval-2007, and propose alternative metrics that avoid these problems, whic...
Sanaz Jabbari, Mark Hepple, Louise Guthrie
110
Voted
NAACL
2010
14 years 10 months ago
Topic Models for Image Annotation and Text Illustration
Image annotation, the task of automatically generating description words for a picture, is a key component in various image search and retrieval applications. Creating image datab...
Yansong Feng, Mirella Lapata
NAACL
2010
14 years 10 months ago
Improving the Multilingual User Experience of Wikipedia Using Cross-Language Name Search
Although Wikipedia has emerged as a powerful collaborative Encyclopedia on the Web, it is only partially multilingual as most of the content is in English and a small number of ot...
Raghavendra Udupa, Mitesh M. Khapra
98
Voted
NAACL
2010
14 years 10 months ago
Unsupervised Model Adaptation using Information-Theoretic Criterion
In this paper we propose a novel general framework for unsupervised model adaptation. Our method is based on entropy which has been used previously as a regularizer in semi-superv...
Ariya Rastrow, Frederick Jelinek, Abhinav Sethy, B...