| 摘要: |
| 作为自然语言处理中的普遍现象,隐喻若不得到解决,将成为制约自然语言处理和机器翻译的瓶颈问题.结合相关的隐喻理论基础,从隐喻识别和隐喻解释这两个隐喻计算的子任务出发,介绍了现有的隐喻计算模型以及隐喻语料资源,并对这些隐喻模型的优缺点和适用范围进行了比较. |
| 关键词: 隐喻计算模型 隐喻识别 隐喻解释 语料库 |
| DOI：10.13328/j.cnki.jos.004669 |
| 分类号: |
| 基金项目:国家自然科学基金(61075058) |
|
| Computational Metaphor Processing |
|
TIAN Jia1, SU Chang1, CHEN Yi-Jiang2
|
|
1.Department of Cognitive Science, Xiamen University, Xiamen 361005, China;2.Department of Computer Science, Xiamen University, Xiamen 361005, China
|
| Abstract: |
| As a traditional form in NLP, the identification and comprehension of metaphor is a bottle-neck problem in NLP and machine translation. In this paper, based on the basic theory, current computational models for metaphor are reviewed. According to the methods, models are divided into metaphor identification and comprehension. The advantages of every model are also analyzed. At last, the paper introduces the current resources of metaphor processing. |
| Key words: computational metaphor model metaphor identification metaphor comprehension corpus resources |
