Poster 143: Quantum Natural Language Processing

Authors: Lee James O'Riordan (Irish Centre for High‑End Computing (ICHEC), National University of Ireland Galway (NUIG)), Myles Doyle (Irish Centre for High‑End Computing (ICHEC), National University of Ireland Galway (NUIG)), Venkatesh Kannan (Irish Centre for High‑End Computing (ICHEC), National University of Ireland Galway (NUIG)), Fabio Baruffa (Intel Corporation)

Abstract: Natural language processing (NLP) algorithms that operate over strings of words are limited since they analyse meanings of the component words in a corpus without information about grammatical rules of the language. Consequently, they often produce unsatisfactory results with increase in problem complexity.

The "distributed compositional semantics" (DisCo) model incorporates grammatical structure of sentences into the algorithms, and offers significant improvements to the quality of results. However, their main challenge is the need for large classical computational resources. The DisCo model presents two quantum algorithms which lower storage and compute requirements compared to a classic HPC implementation.

In this project, we implement the two DisCo model quantum algorithms on the Intel Quantum Simulator deployed on the Irish national supercomputer. We target corpuses with ~1000 most-common words using up to 36 qubits simulation. The solution will be able to compute the meanings of two sentences and decide if their meanings match.

Best Poster Finalist (BP): no

Poster: PDF
Poster summary: PDF


Back to Poster Archive Listing