Semantic shift (drift) is defined as ‘innovations which change the lexical meaning rather than the grammatical function of a form’ (Bloomfield, 1933)[1]

Using random indexing: Jurgens and Stevens (2009)[2]

Temporal random indexing (?): Basile et al. (2015)[3]

Using neural embeddings: Kim et al. (2014)[4], Kulkarni et al. (2015)[5]

References Edit

  1. Leonard Bloomfield. 1933. Language. Allen & Unwin.
  2. David Jurgens and Keith Stevens. 2009. Event detection in blogs using temporal ran- dom indexing. In Proceedings of the Workshop on Events in Emerging Text Types, pages 9–16, Borovets, Bulgaria.
  3. Basile, Pierpaolo, Annalina Caputo, and Giovanni Semeraro. "Temporal random indexing: A system for analysing word meaning over time." In IJCoL vol. 1, n. 1 december 2015: Emerging Topics at the First Italian Conference on Computational Linguistics, p. 55. Accademia University Press, 2015.
  4. Yoon Kim, Yi-I Chiu, Kentaro Hanaki, Darshan Hegde, and Slav Petrov. 2014. Temporal analysis of language through neural language models. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, page 61, Baltimore, USA. 
  5. Vivek Kulkarni, Rami Al-Rfou, Bryan Perozzi, and Steven Skiena. 2015. Statistically signif- icant detection of linguistic change. In Proceedings of the 24th International Conference on World Wide Web, pages 625–635, Florence, Italy.