Long-Range Language Model Doug Beeferman, Adam Berger, and John Lafferty...  Home/Search
Context
Related
| cmu.edu/project/link/pub/...distance.ps Cached: PS.gz PS PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
Image Update HelpPS.gz PS PDF From: cmu.edu/project/link/pub/www/p... (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: This paper introduces new techniques based on exponential families for modeling the correlations between words in text and speech. The motivation for this work is to build improved statistical language models by treating a static trigram model as a default distribution, and adding sufficient statistics, or "features," to a family of conditional exponential distributions in order to model the nonstationary characteristics of language. We focus on features based on pairs of mutually... (Update)
Similar documents (at the sentence level):
43.2%: A Model of Lexical Attraction and Repulsion - Beeferman, Berger, Lafferty (1997) (Correct)
Active bibliography (related documents): More All
0.3: Logistic Regression, AdaBoost and Bregman Distances - Collins, al. (2000) (Correct)
0.1: Improving N-Gram Modeling Using Distance-Related Unit.. - Zhang, Singer, Wu.. (Correct)
0.1: Analyzing And Improving Statistical Language Models For Speech.. - Ueberla (1994) (Correct)
Similar documents based on text:
0.0: Unknown - (Correct)
BibTeX entry: (Update)
@misc{ model-accounting,
author = "Long-Range Language Model",
title = "Accounting for Distance in a",
url = "citeseer.ist.psu.edu/765899.html" }
Citations (may not include all citations):2528 Maximum likelihood from incomplete data via the EM algorithm (context) - Dempster, Laird et al. - 1977
2319 Elements of Information Theory (context) - Cover, Thomas - 1991
524 Queueing Systems (context) - Kleinrock - 1975
261 Bayesian Data Analysis (context) - Gelman, Carlin et al. - 1995
213 A maximum entropy approach to natural language processing - Berger, Pietra et al. - 1996
151 SWITCHBOARD: Telephone speech corpus for research and develo.. (context) - Holliman, Godfrey et al. - 1992
76 A maximum entropy approach to adaptive statistical language .. - Rosenfeld - 1996
68 A cache-based natural language model for speech recognition (context) - Kuhn, de Mori - 1990
47 On structuring probabilistic dependencies in stochastic lang.. (context) - Ney, Essen et al. - 1994
45 Estimation of probabilities from sparse data for the langaug.. - Katz - 1987
29 A dynamic language model for speech recognition (context) - Jelinek, Merialdo et al. - 1991
27 Adaptive language modeling using the maximum entropy princip.. (context) - Lau, Rosenfeld et al. - 1993
9 on Pattern Analysis and Machine Intelligence (context) - Pietra, Pietra et al. - 1997
3 and information theory (context) - Csisz'ar, mathematics - 1996
Documents on the same site (http://www.cs.cmu.edu/afs/cs.cmu.edu/project/link/pub/www/papers/ps/):
Statistical Language Modeling Using Grammatical Information - Grinberg (1995) (Correct)
A Model of Lexical Attraction and Repulsion - Doug Beeferman Adam (Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC