Research pick: A deep dive for meaning - "Application of quantum optimisation osprey algorithm in English translation quality improvement model"

Research in the International Journal of Information and Communication Technology has taken inspiration from the hunting behaviour of the fish-eating bird of prey, the osprey, and combined this with inspiration from quantum computing to improve machine translation, particularly for long sentences and technical texts between Chinese and English.

Ospreys scan large areas of the water before making precise dives on their piscine targets. This strategy has been modelled and adapted into an algorithm that balances broad exploration with focused searches for promising solutions. The result in this work is the Quantum-Optimised Osprey Optimisation Algorithm (QOOA). The team explains that QOOA uses qubits, the mathematical units of quantum information, to explore a wider range of possible solutions. It also incorporates a quantum rotation mechanism that shifts from broad exploration to targeted refinement as the search progresses.

The team tested the new model on the WMT2018 English-Chinese translation benchmark, which contains almost 177,000 training examples. Compared with a baseline neural machine translation system, QOOA scored 3.2 percentage points higher and reduced the number of post-translation edits needed by 12.7 per cent. In addition, the team reports that their approach was particularly effective for lengthy and technical texts, where previous translation systems have been prone to errors and ambiguity.

Wang, L. (2026) ‘Application of quantum optimisation osprey algorithm in English translation quality improvement model’, Int. J. Information and Communication Technology, Vol. 27, No. 49, pp.1–18.