arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 0801.4716cs.CL
收藏

将语言模型与单词预测组件的语义信息集成的方法

Methods to integrate a language model with semantic information for a word prediction component

Université François Rabelais de Tours(图尔弗朗索瓦·拉伯雷大学);Laboratoire d’Informatique (LI)(计算机实验室(LI))

Tonio Wandmacher, Jean-Yves Antoine

摘要:

目前的词预测系统大多使用n元语言模型(LM)来估计短语中后续词的概率。在过去的几年中,已经有许多尝试来用进一步的句法或语义信息来丰富这样的语言模型。我们想探索潜在语义分析(LSA)的预测能力,这种方法已被证明可以提供有关上下文中单词之间长距离语义依赖关系的可靠信息。我们在这里提出并评估几种方法,集成基于LSA的信息与标准的语言模型:语义缓存,部分重新排序,和不同形式的插值。我们发现,与4-gram基线相比,所有方法都显示出显着的改进,其中大多数方法也适用于简单的缓存模型。

英文摘要:

Most current word prediction systems make use of n-gram language models (LM) to estimate the probability of the following word in a phrase. In the past years there have been many attempts to enrich such language models with further syntactic or semantic information. We want to explore the predictive powers of Latent Semantic Analysis (LSA), a method that has been shown to provide reliable information on long-distance semantic dependencies between words in a context. We present and evaluate here several methods that integrate LSA-based information with a standard language model: a semantic cache, partial reranking, and different forms of interpolation. We found that all methods show significant improvements, compared to the 4-gram baseline, and most of them to a simple cache model as well.

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。

↑