Spicy Adjectives and Nominal Donkeys: Capturing Semantic Deviance Using Compositionality in Distributional Spaces

Spicy Adjectives and Nominal Donkeys: Capturing Semantic Deviance Using Compositionality in Distributional Spaces
复制标题

辣形容词和名义驴:利用分布空间中的组合性捕获语义偏差

DOI:
--
复制
发表时间:
2017
期刊:
Cognitive Sciences
影响因子:
--
通讯作者:
Marco Baroni
Marco Baroni
中科院分区:
--
文献类型:
--
作者:
Eva Maria Vecchi;M. Marelli;Roberto Zamparelli;Marco Baroni

文献摘要

参考文献

被引文献

相似文献

老练的参议员和立法洋葱。不管你是否听说过这些事情,我们都有一些直觉,其中一个比另一个更没有意义。在本文中,我们介绍了一个大型的数据集的人类判断的新的形容词-名词短语。我们使用这些数据来测试的方法,语义偏差的基础上的短语表示与成分分布的语义方法,即方法,从上下文信息中获得词义,并结合词义近似短语的含义。我们提出了几个简单的措施提取的单词和短语的分布表示,我们表明,他们有一个显着的影响,预测新的形容词-名词短语的可接受性,即使当一些替代措施经典的复合处理和bigram可接受性的研究考虑。我们的研究结果表明,在何种程度上一个属性形容词改变了名词的分布表示是最重要的因素,在建模可接受的和偏差的短语之间的区别。我们的研究扩展了目前的应用组合分布语义方法的语言和认知有趣的问题,它提供了一个新的,定量精确的方法来预测人类何时会发现新的语言表达可接受的挑战,当他们不会。
Sophisticated senator and legislative onion. Whether or not you have ever heard of these things, we all have some intuition that one of them makes much less sense than the other. In this paper, we introduce a large dataset of human judgments about novel adjective-noun phrases. We use these data to test an approach to semantic deviance based on phrase representations derived with compositional distributional semantic methods, that is, methods that derive word meanings from contextual information, and approximate phrase meanings by combining word meanings. We present several simple measures extracted from distributional representations of words and phrases, and we show that they have a significant impact on predicting the acceptability of novel adjective-noun phrases even when a number of alternative measures classically employed in studies of compound processing and bigram plausibility are taken into account. Our results show that the extent to which an attributive adjective alters the distributional representation of the noun is the most significant factor in modeling the distinction between acceptable and deviant phrases. Our study extends current applications of compositional distributional semantic methods to linguistically and cognitively interesting problems, and it offers a new, quantitatively precise approach to the challenge of predicting when humans will find novel linguistic expressions acceptable and when they will not.
DOI: --
发表时间: 2010-03
期刊: ArXiv
影响因子: --
作者:
B. Coecke;M. Sadrzadeh;S. Clark
通讯作者: B. Coecke;M. Sadrzadeh;S. Clark
DOI: 10.48550/arxiv.1106.4058
发表时间: 2011
期刊: --
影响因子: --
作者:
Grefenstette E
通讯作者: Grefenstette E
DOI: 10.1037/0096-1523.26.2.820
发表时间: 2000-04-01
影响因子: 2.1
作者:
Pollatsek, A;Hyönä, J;Bertram, R
通讯作者: Bertram, R
DOI: 10.1016/j.jml.2007.11.007
发表时间: 2008-11
影响因子: 4.3
作者:
Jaeger, T. Florian
通讯作者: Jaeger, T. Florian