arXivDaily arXiv每日学术速递 周一至周五更新
arXiv cs/9811025cs.CL
收藏

一种结构化的语言模型

A Structured Language Model

Ciprian Chelba

摘要:

本文提出了一种语言模型,开发句法结构,并使用它来提取有意义的信息,从单词的历史,从而使使用长距离的依赖关系。该模型为每个带有中心词注释的词-二进制-解析-结构的联合序列分配概率。该模型,它的概率参数化,和一组实验,以评估其预测能力。

英文摘要:

The paper presents a language model that develops syntactic structure and uses it to extract meaningful information from the word history, thus enabling the use of long distance dependencies. The model assigns probability to every joint sequence of words - binary-parse-structure with headword annotation. The model, its probabilistic parametrization, and a set of experiments meant to evaluate its predictive power are presented.

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。

↑