Quantinuum Updates Its Iambeq Quantum Natural Language Processing Toolkit
The quantum natural language processing team at Quantinuum has released a major update to its open-source Python library and toolkit, lambeq.
lambeq converts any natural language sentence into a quantum circuit, ready to be realized on a quantum computer.
The update will support the growth of quantum natural language processing (QNLP) and potential future applications such as automated dialogue, text mining, language translation, text-to-speech, language generation, and bioinformatics.
Additionally, 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 and presents improved parsing performance. The previous parser remains part of the toolkit, and Bobcat will also be released as a separate stand-alone open-source tool.
The new update is equipped with a command-line interface and contains a new supervised training module designed to simplify the process of training parameterized quantum circuits and tensor networks in a machine learning setup.
With this update, lambeq becomes more flexible in providing users with more options on the quantum circuits it can generate. It allows manipulation of syntax diagrams and makes it simpler to define the quantum circuits from the syntactic structure.
The visualisation of lambeq's output has also been improved, and documentation has been expanded with numerous examples to remove the barrier to entry for general users.
"Since we launched lambeq, we have received valuable feedback from a rapidly growing community of users, and many of the new features available today reflect this. The new version of lambeq now comes, for example, with a native state-of-the-art parser that has been fully integrated with the toolkit. Additionally, the toolkit is now equipped with a training package that supports popular supervised learning libraries, such as PyTorch, to help users efficiently train NLP tasks using the quantum circuits and tensor networks that lambeq generates. This update is all about accessibility nd crucially, reducing the time it takes to achieve results," said Quantinuum's head of applied quantum NLP research, Dimitrios Kartsaklis, in a statement.