Differentia compositionem facit. A Slower-Paced and Reliable Parser for Latin

Marco Carlo Passarotti, Edoardo Maria Ponti

Risultato della ricerca: Contributo in libroContributo a convegno

4 Citazioni (Scopus)

Abstract

The Index Thomisticus Treebank is the largest available treebank for Latin; it contains Medieval Latin texts by Thomas Aquinas. After experimenting on its data with a number of dependency parsers based on different supervised machine learning techniques, we found that DeSR with a multilayer perceptron algorithm, a right-to-left transition, and a tailor-made feature model is the parser providing the highest accuracy rates. We improved the results further by using a technique that combines the output parses of DeSR with those provided by other parsers, outperforming the previous state of the art in parsing the Index Thomisticus Treebank. The key idea behind such improvement is to ensure a sufficient diversity and accuracy of the outputs to be combined; for this reason, we performed an in-depth evaluation of the results provided by the different parsers that we combined. Finally, we assessed that, although the general architecture of the parser is portable to Classical Latin, yet the model trained on Medieval Latin is inadequate for such purpose.
Lingua originaleEnglish
Titolo della pubblicazione ospiteProceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)
Pagine683-688
Numero di pagine6
Stato di pubblicazionePubblicato - 2016
EventoTenth International Conference on Language Resources and Evaluation (LREC 2016) - Portorož
Durata: 23 mag 201628 mag 2016

Convegno

ConvegnoTenth International Conference on Language Resources and Evaluation (LREC 2016)
CittàPortorož
Periodo23/5/1628/5/16

Keywords

  • Latin
  • Parsing

Fingerprint Entra nei temi di ricerca di 'Differentia compositionem facit. A Slower-Paced and Reliable Parser for Latin'. Insieme formano una fingerprint unica.

Cita questo