RT Book,_Section
T1 Measuring language distance among historical varieties using perplexity. Application to European Portuguese
A1 Pichel, José Ramom
A1 Gamallo Otero, Pablo
A1 Alegria Loinaz, Iñaki
K1 Language Distance
K1 Historical Linguistics
AB The objective of this work is to quantify, with a simple and robust measure, the distance between historical varieties of a language. The measure will be inferred from text corpora corresponding to historical periods. Different approaches have been proposed for similar aims: Language Identification, Phylogenetics, Historical Linguistics or Dialectology. In our approach, we used a perplexity-based measure to calculate language distance between all the historical periods of a specific language: European Portuguese. Perplexity has also proven to be a robust metric to calculate distance between languages. However, this measure has not been tested yet to identify diachronic periods within the historical evolution of a specific language. For this purpose, a historical Portuguese corpus has been constructed from different open sources containing texts with close original spelling. The results of our experiments show that Portuguese keeps an important degree of homogeneity over time. We anticipate this metric to be a starting point to be applied to other languages.
PB Association for Computational Linguistics
YR 2018
FD 2018-08-20
LK https://hdl.handle.net/10347/45128
UL https://hdl.handle.net/10347/45128
LA eng
NO Jose Ramom Pichel Campos, Pablo Gamallo, and Iñaki Alegria. 2018. Measuring language distance among historical varieties using perplexity. Application to European Portuguese.. In Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018), pages 145–155, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
NO BBVA Foundation Grant for Researchers and Cultural Creators
NO TelePares
NO TADeep
NO Consellería de Cultura, Educación e Ordenación Universitaria
NO European Regional Development Fund
NO imaxin software
DS Minerva
RD 28 abr 2026