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 2005.12533cs.CLcs.AI
收藏

基于转换器的序列概率指导符号自然语言语法归纳

Guiding Symbolic Natural Language Grammar Induction via Transformer-Based Sequence Probabilities

SingularityNET Foundation(奇点网基金会);The Hong Kong Polytechnic University(香港理工大学)

Ben Goertzel, Andres Suarez Madrigal, Gino Yu

摘要:

提出了一种基于Transformer神经网络语言模型分配给句子(以及可能更长的单词序列)的概率来指导聚类和规则归纳等符号学习过程的自然语言句法规则自动学习的新方法。这种方法利用Transformers学习的语言知识,没有任何参考他们的内部表示,因此,该技术很容易适应更强大的语言模型的连续出现。我们展示了我们所提出的技术的概念验证示例,使用它来指导从我们先前的研究中得出的无监督符号链接语法归纳方法。

英文摘要:

A novel approach to automated learning of syntactic rules governing natural languages is proposed, based on using probabilities assigned to sentences (and potentially longer word sequences) by transformer neural network language models to guide symbolic learning processes like clustering and rule induction. This method exploits the learned linguistic knowledge in transformers, without any reference to their inner representations; hence, the technique is readily adaptable to the continuous appearance of more powerful language models. We show a proof-of-concept example of our proposed technique, using it to guide unsupervised symbolic link-grammar induction methods drawn from our prior research.

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。

↑