Quantum-Inspired Representation for Long-Tail Senses of Word Sense Disambiguation

Abstract

Data imbalance, also known as the long-tail distribution of data, is an important challenge for data-driven models. In the Word Sense Disambiguation (WSD) task, the long-tail phenomenon of word sense distribution is more common, making it difficult to effectively represent and identify Long-Tail Senses (LTSs). Therefore exploring representation methods that do not rely heavily on the training sample size is an important way to combat LTSs. Considering that many new states, namely superposition states, can be constructed from several known states in quantum mechanics, superposition states provide the possibility to obtain more accurate representations from inferior representations learned from a small sample size. Inspired by quantum superposition states, a representation method in Hilbert space is proposed to reduce the dependence on large sample sizes and thus combat LTSs. We theoretically prove the correctness of the method, and verify its effectiveness under the standard WSD evaluation framework and obtain state-of-the-art performance. Furthermore, we also test on the constructed LTS and the latest cross-lingual datasets, and achieve promising results.

Quantum Interference Model for Semantic Biases of Glosses in Word Sense Disambiguation

“…Accurate and easy-to-distinguish word sense representations can improve the performance of WSD systems (Bevilacqua et al 2021;Blevins and Zettlemoyer 2020). However, limited by the scarcity of word sense annotations (namely glosses) in dictionaries, obtaining highquality word sense representations is an important challenge for the WSD task (Scarlini, Pasini, and Navigli 2020b;Kumar et al 2019;Zhang, He, and Guo 2023;.…”