arXivDaily arXiv每日学术速递 周一至周五更新
arXiv cs/0104019cs.CL
收藏

基于层次主题自适应的动态非局部语言建模

Dynamic Nonlocal Language Modeling via Hierarchical Topic-Based Adaptation

Radu Florian, David Yarowsky

摘要:

本文提出了一种新的生成和应用层次化、动态的基于主题的语言模型的方法。它提出并评估新的聚类生成,分层平滑和自适应主题概率估计技术。这些组合模型有助于捕获长距离词汇依赖。在广播新闻语料库上的实验表明,困惑度有了显著的改善(总体改善10.5%,目标词汇改善33.5%)。

英文摘要:

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).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑