Computer Science – Computation and Language
Scientific paper
2001-04-27
Proceedings of the 37th Annual Meeting of the ACL, pages 167-174, College Park, Maryland
Computer Science
Computation and Language
8 pages, 29 figures, presented at ACL99, College Park, Maryland
Scientific paper
This 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).
Florian Radu
Yarowsky David
No associations
LandOfFree
Dynamic Nonlocal Language Modeling via Hierarchical Topic-Based Adaptation does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Dynamic Nonlocal Language Modeling via Hierarchical Topic-Based Adaptation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Dynamic Nonlocal Language Modeling via Hierarchical Topic-Based Adaptation will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-298211