arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1107.4573cs.AIcs.CLcs.LG
收藏

类比知觉应用于七个单词理解测试

Analogy perception applied to seven tests of word comprehension

Institute for Information Technology(信息技术研究所);National Research Council of Canada(加拿大国家研究委员会)

Peter D. Turney

摘要:

类比是认知的核心,这一观点一直被争论不休。在人工智能研究中,类比算法通常受到需要手工编码的高级表示作为输入的限制。另一种方法是使用高级感知,其中从原始数据自动生成高级表示。类比知觉是运用高级知觉对类比进行再认识的过程。我们提出了PairClass,类比感知算法,识别词汇比例类比使用表示自动生成的原始文本数据的大型语料库。比例类比是A:B::C:D形式的类比,意思是“A对B就像C对D一样”。词汇比例类比是与单词的比例类比,如carpenter:wood::mason:stone。PairClass使用高维特征向量来表示两个词之间的语义关系,其中的元素基于语料库中模式的频率。PairClass通过将标准监督机器学习技术应用于特征向量来识别类比。我们展示了如何七种不同的测试的单词理解可以被框定为类比知觉的问题,然后我们应用PairClass的七个类比知觉问题。我们在所有七项测试中都取得了有竞争力的结果。这是第一次用统一的方法处理如此广泛的单词理解测试。

英文摘要:

It has been argued that analogy is the core of cognition. In AI research, algorithms for analogy are often limited by the need for hand-coded high-level representations as input. An alternative approach is to use high-level perception, in which high-level representations are automatically generated from raw data. Analogy perception is the process of recognizing analogies using high-level perception. We present PairClass, an algorithm for analogy perception that recognizes lexical proportional analogies using representations that are automatically generated from a large corpus of raw textual data. A proportional analogy is an analogy of the form A:B::C:D, meaning "A is to B as C is to D". A lexical proportional analogy is a proportional analogy with words, such as carpenter:wood::mason:stone. PairClass represents the semantic relations between two words using a high-dimensional feature vector, in which the elements are based on frequencies of patterns in the corpus. PairClass recognizes analogies by applying standard supervised machine learning techniques to the feature vectors. We show how seven different tests of word comprehension can be framed as problems of analogy perception and we then apply PairClass to the seven resulting sets of analogy perception problems. We achieve competitive results on all seven tests. This is the first time a uniform approach has handled such a range of tests of word comprehension.

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。

↑