Modeling language evolution with codes that utilize context and phonetic features

Javad Nouri, Roman Yangarber

Tutkimustuotos: Artikkeli kirjassa/raportissa/konferenssijulkaisussaKonferenssiartikkeliTieteellinenvertaisarvioitu

Abstrakti

We present methods for investigating processes of evolution in a language family by modeling relationships among the observed languages.

The models aim to find regularities---regular correspondences in lexical data. We present an algorithm which codes the data using phonetic features of sounds, and learns long-range contextual rules that condition recurrent sound correspondences between languages. This gives us a measure of model quality: better models find more regularity in the data. We also present a procedure for imputing unseen data, which provides another method of model comparison. Our experiments demonstrate improvements in performance compared to prior work.
Alkuperäiskielienglanti
OtsikkoThe 20th SIGNLL Conference on Computational Natural Language Learning (CoNLL) : Proceedings of the Conference
Sivumäärä10
JulkaisupaikkaStroudsburg, PA
KustantajaThe Association for Computational Linguistics
Julkaisupäivä2016
Sivut136-145
ISBN (painettu)978-1-945626-19-7
TilaJulkaistu - 2016
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaConference on Computational Natural Language Learning - Berlin, Saksa
Kesto: 11 elok. 201612 elok. 2016
Konferenssinumero: 20

Lisätietoja

CoNLL 2016

Tieteenalat

  • 113 Tietojenkäsittely- ja informaatiotieteet

Siteeraa tätä