Cambridge Quantum (CQ) Open-Sources ‘lambeq’: A Python Library For Experimental Quantum Natural Language Processing (QNLP)

4841
Source: https://medium.com/cambridge-quantum-computing/quantum-natural-language-processing-ii-6b6a44b319b2

Cambridge Quantum (“CQ”) announced the release of the world’s first toolkit and an open-source library for Quantum Natural Language Processing (QNLP), called ‘lambeq’.

Speaking in simple words, ‘lambeq’ is the toolkit for QNLP (Quantum Natural Language Processing) to convert sentences into a quantum circuit. It can be used to accelerate development in practical, real-world applications such as automated dialogue systems and text mining, among other things.

‘lambeq’ has been released on a fully open-sourced basis for the benefit of all quantum computing researchers and developers. Lambeq seamlessly integrates with CQ’s (Cambridge Quantum) TKET, the world’s leading and fastest-growing quantum software development platform that is also fully open-sourced. The open-sourcing of this technology provides QNLP developers with an even broader range for their work.

‘lambeq’ enables and automates the design of NLP experiments, compositional-distributional (DisCo) type, that scientists have previously described. This means moving from Syntax/Grammar Diagrams, which stand for text’s structure classically (tensor networks), to either quantum circuits implemented with TKET or even more complex structures like Neural Nets capable of learning at machine-learning tasks such as classification. ‘lambeq’ is the future of architecture. It’s modular and customizable with interchangeable components, so you can perfectly create something that fits your needs.

Source: https://arxiv.org/pdf/2110.04236.pdf

Eliminating barriers to entry for AI and human-machine interactions is potentially one of the most significant applications of ‘lambeq’. TKET is a ground-breaking toolkit for quantum computing that aims to engage users with AI applications. ‘lambeq’ has the potential to be one of those most important markets in artificial intelligence, and it’s up at-bat as well. The use of QNLP has been confirmed to be applicable in the analysis for symbol sequences that arise from genomics and those found within proteomic experiments.

Paper:https://arxiv.org/abs/2110.04236

Github: https://github.com/CQCL/lambeq

Documentation: https://cqcl.github.io/lambeq/

CQ Blog: https://medium.com/cambridge-quantum-computing/quantum-natural-language-processing-ii-6b6a44b319b2

Source: https://www.blackhillsfox.com/prnewswire/2021/10/13/cambridge-quantum-releases-worlds-first-quantum-natural-language-processing-toolkit-library/