Oxymoron generation using an association word corpus and a large-scale N-gram corpus
Oxymoron generation using an association word corpus and a large-scale N-gram corpus
复制标题
使用关联词语料库和大规模 N-gram 语料库生成矛盾词
DOI：
10.1007/s00500-014-1430-6
复制
发表时间：
2015
期刊：
影响因子：
4.1
通讯作者：
Hiroaki Yamane and Masafumi Hagiwara
中科院分区：
文献类型：
--
作者：
Tomoki Kurikawa;Takashi Handa and Tomoki Fukai;Tomoki Kurikawa and Kunihiko Kaneko;Tomoki Kurikawa and Kunihiko Kaneko;Taku Suzuki;Taku Suzuki;鈴木 拓;鈴木 拓;Taku Suzuki;鈴木 拓;鈴木 拓;鈴木 拓;鈴木 拓;鈴木 拓;Taku Suzuki;Hiroaki Yamane and Masafumi Hagiwara
矛盾修饰法是矛盾或不协调的词的组合，通常用于吸引读者对文本的注意力。提出了一种利用关联词语料库和大规模语法语料库生成矛盾修饰法的方法。首先，形容词作为输入被馈送到所提出的系统。然后，反义词对提取的gram语料库。利用反义词对和联想词语料库，产生候选词。候选人根据其是否合适和是否有吸引力而最终确定或淘汰。为了确定适合性，使用逐点互信息（PMI）来排除语法不自然的表达式。为了确定吸引力，PMI，矛盾修饰候选人的频率差距，和WordNet。生成的矛盾修饰法的组合表明所提出的方法的潜在有效性。
Oxymorons are combinations of contradictory or incongruous words and are typically used to draw readers’ attention to a text. This paper proposes a method to generate oxymorons using an association word corpus and a large-scale-gram corpus. First, adjectives are fed as input into the proposed system. Then, antonym pairs are extracted from the-gram corpus. Using the antonym pairs and the association word corpus, candidates are generated. Candidates are finalized or eliminated according to their suitability and attractiveness. To determine suitability, pointwise mutual information (PMI) is employed to exclude grammatically unnatural expressions. To determine attractiveness, PMI, gap of frequency of the oxymoron candidates, and WordNet are used. The generated combinations of oxymorons indicate the potential effectiveness of the proposed method.