arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2102.01826cs.CL
收藏

一个俚语生成的计算框架

A Computational Framework for Slang Generation

University of Toronto(多伦多大学);Vector Institute for Artificial Intelligence(向量人工智能研究所)

Zhewei Sun, Richard Zemel, Yang Xu

摘要:

俚语是一种常见的非正式语言,但其灵活性和数据资源的缺乏对现有的自然语言系统提出了挑战。我们采取的第一步机器生成俚语开发一个框架,模型扬声器的俚语语境中的单词选择。我们的框架编码新的俚语意义相关的传统和俚语意义的一个词,同时将句法和语境知识的俚语用法。我们使用概率推理和神经对比学习的组合来构建框架。我们对三个俚语词典进行了严格的评估,结果表明,我们的方法不仅优于最先进的语言模型,而且更好地预测了从20世纪60年代到21世纪初俚语用法的历史出现。我们解释了提出的模型,发现对比学习的语义空间是敏感的俚语和传统意义的词之间的相似性。我们的工作为非正式语言的自动生成和解释创造了机会。

英文摘要:

Slang is a common type of informal language, but its flexible nature and paucity of data resources present challenges for existing natural language systems. We take an initial step toward machine generation of slang by developing a framework that models the speaker's word choice in slang context. Our framework encodes novel slang meaning by relating the conventional and slang senses of a word while incorporating syntactic and contextual knowledge in slang usage. We construct the framework using a combination of probabilistic inference and neural contrastive learning. We perform rigorous evaluations on three slang dictionaries and show that our approach not only outperforms state-of-the-art language models, but also better predicts the historical emergence of slang word usages from 1960s to 2000s. We interpret the proposed models and find that the contrastively learned semantic space is sensitive to the similarities between slang and conventional senses of words. Our work creates opportunities for the automated generation and interpretation of informal language.

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。

↑