A Quantum Expectation Value Based Language Model with Application to Question Answering.
A Quantum Expectation Value Based Language Model with Application to Question Answering.
复制标题
基于量子期望值的语言模型及其在问答中的应用
DOI：
10.3390/e22050533
复制
发表时间：
2020-05-09
期刊：
影响因子：
--
通讯作者：
Xu R
中科院分区：
文献类型：
--
作者：
Zhao Q;Hou C;Liu C;Zhang P;Xu R
量子语言模型由于其透明性和可解释性而被引入到信息检索中。虽然取得了令人振奋的进展，但目前的研究主要是探讨语义希尔伯特空间中不同句子子空间的密度矩阵之间的关系。希尔伯特空间作为一个整体，具有独特的密度矩阵，缺乏探索。本文提出了一种基于量子期望值的语言模型（QEV-LM）。构造了语义希尔伯特空间的唯一共享密度矩阵。在这个量子模型中，单词和句子被视为不同的可观察对象。在此背景下，描述一对问答之间相似性的匹配分数自然被解释为联合问答可观测值的量子期望值。除了理论合理性外，在TREC-QA和WIKIQA数据集上的实验结果也证明了我们提出的模型的计算效率，具有优异的性能和较低的耗时。
Quantum-inspired language models have been introduced to Information Retrieval due to their transparency and interpretability. While exciting progresses have been made, current studies mainly investigate the relationship between density matrices of difference sentence subspaces of a semantic Hilbert space. The Hilbert space as a whole which has a unique density matrix is lack of exploration. In this paper, we propose a novel Quantum Expectation Value based Language Model (QEV-LM). A unique shared density matrix is constructed for the Semantic Hilbert Space. Words and sentences are viewed as different observables in this quantum model. Under this background, a matching score describing the similarity between a question-answer pair is naturally explained as the quantum expectation value of a joint question-answer observable. In addition to the theoretical soundness, experiment results on the TREC-QA and WIKIQA datasets demonstrate the computational efficiency of our proposed model with excellent performance and low time consumption.