Quantinuum updates natural language processing toolkit
Quantinuum released an update to its open source natural language processing (NLP) Python library and toolkit, lambeq, which turns natural language sentences into quantum circuits. The move comes about six months after lambeq was unveiled by Cambridge Quantum Computing, which shortly after was merged with Honeywell Quantum Solutions to create Quantinuum.
The new release has been designed for a growing community of researchers, developers and users versed in quantum natural language processing (QNLP) and natural language processing (NLP), Quantinuum said, adding that the update will support the growth of QNLP and potential future applications such as automated dialogue, text mining, language translation, text-to-speech, language generation and bioinformatics.
Quantinuum also said lambeq’s new neural-based CCG parser, Bobcat, is trained on a large human-annotated corpus of syntactic derivations. It is fully integrated with the toolkit, simplifying the installation process, and greatly improves performance. The previous parser remains part of the toolkit, and for the benefit of the community, Bobcat will also be released eventually as a separate stand-alone open source tool, the company said.
The new update also is equipped with command-line interface functionality, making it easier to use for users with no programming knowledge. It also contains a new supervised training module designed to simplify the process of training parameterised quantum circuits and tensor networks in a machine learning setup.