MERMAID：隐喻的符号生成和识别解码
MERMAID: Metaphor Generation with Symbolism and Discriminative Decoding
摘要：
隐喻的生成是一项具有挑战性的任务，因为它需要正确理解抽象概念，在不相关的概念之间建立联系，并偏离字面意义。在本文中，我们的目标是生成一个隐喻句子的字面表达，通过替换相关的动词。基于隐喻和符号之间的理论联系，我们提出了一种方法，通过使用掩蔽语言建模的最新进展以及常识推理，将古腾堡诗歌语料库（Jacobs，2018）中的大量隐喻句子转换为它们的字面对应物，自动构建平行语料库。对于生成任务，我们引入了一个隐喻模型来指导序列到序列模型的解码，该模型在我们的并行数据上进行了微调，以生成高质量的隐喻。对一组独立的文字陈述测试集的人类评估表明，我们最好的模型生成的隐喻平均比三个精心制作的基线好66%。一个基于任务的评估表明，人类写的诗歌增强了我们的模型提出的隐喻是首选的68%的时间相比，诗歌没有隐喻。
英文摘要：
Generating metaphors is a challenging task as it requires a proper understanding of abstract concepts, making connections between unrelated concepts, and deviating from the literal meaning. In this paper, we aim to generate a metaphoric sentence given a literal expression by replacing relevant verbs. Based on a theoretically-grounded connection between metaphors and symbols, we propose a method to automatically construct a parallel corpus by transforming a large number of metaphorical sentences from the Gutenberg Poetry corpus (Jacobs, 2018) to their literal counterpart using recent advances in masked language modeling coupled with commonsense inference. For the generation task, we incorporate a metaphor discriminator to guide the decoding of a sequence to sequence model fine-tuned on our parallel data to generate high-quality metaphors. Human evaluation on an independent test set of literal statements shows that our best model generates metaphors better than three well-crafted baselines 66% of the time on average. A task-based evaluation shows that human-written poems enhanced with metaphors proposed by our model are preferred 68% of the time compared to poems without metaphors.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
