Unsupervised Tokenization Learning
This addresses tokenization for natural language processing, offering an unsupervised method that can match or exceed lexicon-based approaches, though it is incremental as it builds on existing metrics.
The paper tackled unsupervised tokenization by proposing a 'transition freedom' metric that outperforms statistical metrics like mutual information, achieving F-measure scores from 0.71 to 1.0 across multilingual corpora.
In the presented study, we discover that the so-called "transition freedom" metric appears superior for unsupervised tokenization purposes in comparison to statistical metrics such as mutual information and conditional probability, providing F-measure scores in range from 0.71 to 1.0 across explored multilingual corpora. We find that different languages require different offshoots of that metric (such as derivative, variance, and "peak values") for successful tokenization. Larger training corpora do not necessarily result in better tokenization quality, while compressing the models by eliminating statistically weak evidence tends to improve performance. The proposed unsupervised tokenization technique provides quality better than or comparable to lexicon-based ones, depending on the language.