A gentle introduction to Quantum Natural Language Processing
It provides an introductory guide for NLP engineers and quantum computing practitioners to understand a recent application of quantum computing to language processing.
The thesis introduces Quantum Natural Language Processing (QNLP) by explaining how it represents sentence meanings as vectors in quantum computers using the DisCoCat model, which composes word vectors via syntactic structures with tensor products, and demonstrates its efficiency in quantum circuits compared to classical inefficiency.
The main goal of this master's thesis is to introduce Quantum Natural Language Processing (QNLP) in a way understandable by both the NLP engineer and the quantum computing practitioner. QNLP is a recent application of quantum computing that aims at representing sentences' meaning as vectors encoded into quantum computers. To achieve this, the distributional meaning of words is extended by the compositional meaning of sentences (DisCoCat model) : the vectors representing words' meanings are composed through the syntactic structure of the sentence. This is done using an algorithm based on tensor products. We see that this algorithm is inefficient on classical computers but scales well using quantum circuits. After exposing the practical details of its implementation, we go through three use-cases.