Visual Denotations for Recognizing Textual Entailment
Visual Denotations for Recognizing Textual Entailment
复制标题
DOI：
10.18653/v1/d17-1305
复制
发表时间：
2017-09
期刊：
影响因子：
--
通讯作者：
D. Han;Pascual Martínez-Gómez;K. Mineshima
中科院分区：
文献类型：
--
作者：
D. Han;Pascual Martínez-Gómez;K. Mineshima
在文本蕴涵识别的逻辑方法中，短语间语义关系的识别是一个尚未解决的问题。资源，如释义数据库提供有限的覆盖范围，尽管他们的大规模，而无监督的意义分布模型往往无法识别短语蕴涵。我们建议将短语映射到它们的视觉表示，并根据它们的图像比较它们的含义。我们表明，我们的方法是有效的识别文本蕴涵的任务时，结合特定的语言和逻辑功能。
In the logic approach to Recognizing Textual Entailment, identifying phrase-to-phrase semantic relations is still an unsolved problem. Resources such as the Paraphrase Database offer limited coverage despite their large size whereas unsupervised distributional models of meaning often fail to recognize phrasal entailments. We propose to map phrases to their visual denotations and compare their meaning in terms of their images. We show that our approach is effective in the task of Recognizing Textual Entailment when combined with specific linguistic and logic features.