For mathematical models of language, their potential, limitations, and ways of improvement are investigated in terms of whether they reproduce the complex properties of language. The nature of linguistic structure is studied in terms of its relation to scaling properties of language.
References
- Shuntaro Takahashi, Kumiko Tanaka-Ishii. Evaluating computational language models with scaling properties of natural language. Computational Linguistics, 2019, 45.3: 481-513. [link]
- Shuntaro Takahashi, Kumiko Tanaka-Ishii. Do neural nets learn statistical laws behind natural language? . PLOS One, 2017, 12.12: e0189326. [link]