arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.04147cs.CLquant-ph
收藏

基于近期量子计算机的量子自然语言处理

Quantum Natural Language Processing on Near-Term Quantum Computers

Cambridge Quantum Computing(剑桥量子计算公司);University of Oxford(牛津大学);Hashberg

Konstantinos Meichanetzidis, Stefano Gogioso, Giovanni de Felice, Nicolò Chiappori, Alexis Toumi, Bob Coecke

摘要:

在这项工作中,我们描述了一个全栈管道自然语言处理的近期量子计算机,又名QNLP。我们采用的语言建模框架是组成的分布语义(DiscoCat),它扩展和补充了前组语法的组成结构。在这个模型中,一个句子的语法简化被解释为一个图表,根据语法对单词的特定交互进行编码。正是这种相互作用,加上特定的词嵌入选择,实现了一个句子的意义(或“语义”)。建立在这种相互作用的正式量子性质,我们提出了一种方法,用于映射的DiscoCat图量子电路。我们的方法与NISQ设备和已建立的量子机器学习技术兼容,为量子技术在自然语言处理中的短期应用铺平了道路。

英文摘要:

In this work, we describe a full-stack pipeline for natural language processing on near-term quantum computers, aka QNLP. The language-modelling framework we employ is that of compositional distributional semantics (DisCoCat), which extends and complements the compositional structure of pregroup grammars. Within this model, the grammatical reduction of a sentence is interpreted as a diagram, encoding a specific interaction of words according to the grammar. It is this interaction which, together with a specific choice of word embedding, realises the meaning (or "semantics") of a sentence. Building on the formal quantum-like nature of such interactions, we present a method for mapping DisCoCat diagrams to quantum circuits. Our methodology is compatible both with NISQ devices and with established Quantum Machine Learning techniques, paving the way to near-term applications of quantum technology to natural language processing.

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。

↑