Dynamic Nonlocal Language Modeling via Hierarchical Topic-Based Adaptation

Simple item page
dc.creatorFlorian, Radu
dc.creatorYarowsky, David
dc.date2001-04-27
dc.date.accessioned2026-07-07T03:17:06Z
dc.date.available2026-07-07T03:17:06Z
dc.descriptionThis paper presents a novel method of generating and applying hierarchical, dynamic topic-based language models. It proposes and evaluates new cluster generation, hierarchical smoothing and adaptive topic-probability estimation techniques. These combined models help capture long-distance lexical dependencies. Experiments on the Broadcast News corpus show significant improvement in perplexity (10.5% overall and 33.5% on target vocabulary).
dc.description8 pages, 29 figures, presented at ACL99, College Park, Maryland
dc.identifierhttps://arxiv.org/abs/cs/0104019
dc.identifierhttp://arxiv.org/abs/cs/0104019
dc.identifierProceedings of the 37th Annual Meeting of the ACL, pages 167-174, College Park, Maryland
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/30594
dc.subjectComputation and Language
dc.subjectI.2.7
dc.titleDynamic Nonlocal Language Modeling via Hierarchical Topic-Based Adaptation
dc.typetext

Files

Collections

arXiv