arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1206.0042cs.CL
收藏

计算机语言习得

Language Acquisition in Computers

Megan Belzner, Sean Colin-Ellerin, Jorge H. Roman

摘要:

这个项目探讨了计算机语言习得的本质,并以类似于儿童语言习得的技术为指导。虽然现有的自然语言处理方法在范围和理解上是有限的,但我们的系统旨在从第一原理获得对语言的理解,从而最小化初始输入。我们的系统的第一部分是在Java中实现的,重点是使用bigram来理解语言的形态。我们使用频率分布和它们之间的差异来定义和区分语言。对英语和法语文本进行了分析,以确定在文本被认为是不同语言之前的差异阈值为55,并使用西班牙语文本验证了该阈值。我们系统的第二部分侧重于使用递归方法来理解语言的语法。该程序使用两种可能的方法之一来分析给定的句子,无论是基于句型或周围的话。这两种方法都是用C++实现的。该程序能够理解简单句子的结构并学习新单词。此外,我们还就未来的工作和现有计划的潜在扩展提出了一些建议。

英文摘要:

This project explores the nature of language acquisition in computers, guided by techniques similar to those used in children. While existing natural language processing methods are limited in scope and understanding, our system aims to gain an understanding of language from first principles and hence minimal initial input. The first portion of our system was implemented in Java and is focused on understanding the morphology of language using bigrams. We use frequency distributions and differences between them to define and distinguish languages. English and French texts were analyzed to determine a difference threshold of 55 before the texts are considered to be in different languages, and this threshold was verified using Spanish texts. The second portion of our system focuses on gaining an understanding of the syntax of a language using a recursive method. The program uses one of two possible methods to analyze given sentences based on either sentence patterns or surrounding words. Both methods have been implemented in C++. The program is able to understand the structure of simple sentences and learn new words. In addition, we have provided some suggestions regarding future work and potential extensions of the existing program.

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。

↑