Publication View

Dynamic nonlocal language modeling via hierarchical topic-based adaptation (1999)

Abstract

This paper presents a novel method of generating and applying hierarchical, dynamic topic-based lan-guage models. It proposes and evaluates new clus-ter generation, hierarchical smoothing and adaptive topic-probability estimation techniques. These com-bined models help capture long-distance lexical de-pendencies. °Experiments on the Broadcast News corpus show significant improvement in perplexity (10.5 % overall and 33.5 % on target vocabulary). 1

Publication details

Download	http://citeseerx.ist.psu.edu/viewdoc/summary?doi=?doi=10.1.1.13.903
Source	http://acl.ldc.upenn.edu/P/P99/P99-1022.pdf
Contributors	CiteSeerX
Repository	CiteSeerX - Scientific Literature Digital Library and Search Engine (United States)
Type	text
Language	English
Relation	10.1.1.129.7219, 10.1.1.13.8568, 10.1.1.16.4886, 10.1.1.52.4206, 10.1.1.99.7558, 10.1.1.36.8221, 10.1.1.42.2666, 10.1.1.34.8794, 10.1.1.27.7825, 10.1.1.100.3893, 10.1.1.19.5240, 10.1.1.57.2164, 10.1.1.68.2505, 10.1.1.24.9889, 10.1.1.46.3386, 10.1.1.72.9857, 10.1.1.10.7323, 10.1.1.14.8678, 10.1.1.32.366, 10.1.1.34.8552, 10.1.1.21.2109, 10.1.1.127.9747, 10.1.1.71.2797, 10.1.1.72.9476, 10.1.1.87.1331, 10.1.1.113.204, 10.1.1.137.6742