Word Embedding and WordNet Based Metaphor Identification and Interpretation
Word Embedding and WordNet Based Metaphor Identification and Interpretation
复制标题
DOI：
10.18653/v1/p18-1113
复制
发表时间：
2018-07
期刊：
影响因子：
--
通讯作者：
Rui Mao;Chenghua Lin;Frank Guerin
中科院分区：
文献类型：
--
作者：
Rui Mao;Chenghua Lin;Frank Guerin
隐喻在自然语言中广泛存在，给机器翻译等自然语言处理任务带来了巨大的挑战。现有的基于词嵌入的隐喻识别模型不能准确识别句子中的隐喻词。在本文中，我们提出了一种无监督的学习方法，识别和解释隐喻在单词级别没有任何预处理，在隐喻识别任务中表现优于强基线。我们的模型扩展到解释所识别的隐喻，将它们解释为字面对应物，以便机器可以更好地翻译它们。我们用两个流行的英汉翻译系统对此进行了评估，结果表明我们的模型显着改善了系统。
Metaphoric expressions are widespread in natural language, posing a significant challenge for various natural language processing tasks such as Machine Translation. Current word embedding based metaphor identification models cannot identify the exact metaphorical words within a sentence. In this paper, we propose an unsupervised learning method that identifies and interprets metaphors at word-level without any preprocessing, outperforming strong baselines in the metaphor identification task. Our model extends to interpret the identified metaphors, paraphrasing them into their literal counterparts, so that they can be better translated by machines. We evaluated this with two popular translation systems for English to Chinese, showing that our model improved the systems significantly.