找回密码
 To register

QQ登录

只需一步,快速开始

扫一扫,访问微社区

Titlebook: ;

[复制链接]
楼主: APL
发表于 2025-3-23 10:03:00 | 显示全部楼层
Inducing probabilistic grammars by Bayesian model merging, between a close fit to the data and a default preference for simpler models (‘Occam‘s Razor’). The general scheme is illustrated using three types of probabilistic grammars: Hidden Markov models, class-based .-grams, and stochastic context-free grammars.
发表于 2025-3-23 16:51:01 | 显示全部楼层
发表于 2025-3-23 21:26:56 | 显示全部楼层
发表于 2025-3-24 00:52:00 | 显示全部楼层
Inference and estimation of a long-range trigram model, This results in significant savings in computation time, and is applicable to the training of a general probabilistic link grammar. Results of preliminary experiments carried out for this class of models are presented.
发表于 2025-3-24 04:13:48 | 显示全部楼层
发表于 2025-3-24 09:42:45 | 显示全部楼层
What is the search space of the regular inference?,l properties of the search space are studied and generalization criteria are discussed. In this framework, the concept of . is introduced, that is the set of the most general solutions excluding a negative sample. Finally, the complexity of regular language identification from both a theoritical and a practical point of view is discussed.
发表于 2025-3-24 13:52:59 | 显示全部楼层
Application of OSTIA to machine translation tasks,d English-to-German translations have been generated, and exhaustive experiments have been carried out to test the ability of OSTIA to learn these translations. The success of the results show the usefulness of formal learning techniques in limited-domain Machine Translation tasks.
发表于 2025-3-24 14:52:06 | 显示全部楼层
A comparison of syntactic and statistical techniques for off-line OCR,very simplistic and idiosyncratic input coding, the syntactic method performs slightly better than any of the other methods. Furthermore, it is likely that the syntactic method could significantly outperform the other methods given a less idiosyncratic input coding.
发表于 2025-3-24 20:29:53 | 显示全部楼层
发表于 2025-3-25 01:48:17 | 显示全部楼层
 关于派博传思  派博传思旗下网站  友情链接
派博传思介绍 公司地理位置 论文服务流程 影响因子官网 SITEMAP 大讲堂 北京大学 Oxford Uni. Harvard Uni.
发展历史沿革 期刊点评 投稿经验总结 SCIENCEGARD IMPACTFACTOR 派博系数 清华大学 Yale Uni. Stanford Uni.
|Archiver|手机版|小黑屋| 派博传思国际 ( 京公网安备110108008328) GMT+8, 2025-5-19 06:44
Copyright © 2001-2015 派博传思   京公网安备110108008328 版权所有 All rights reserved
快速回复 返回顶部 返回列表