@inproceedings{0cbdd6fd7a294fe99e2516cde6ed41d6,
title = "Evaluation of TnT Tagger for Spanish",
abstract = "Part of speech (POS) tagger is a necessary module in many natural language text processing tasks. A POS tagger is a program that accepts an unprepared raw text in input and to each word adds a tag specifying its grammatical properties, such as part of speech, number, person, etc. One of popular POS taggers - TnT tagger - has been extensively tested for English and some other languages. This paper reports on its evaluation for Spanish language. Error analysis is reported, explaining how some specific features of Spanish language affect tagger performance. It is reported that on Spanish texts TnT shows overall tagging accuracy between 92.5% and 95.84%, specifically, between 95.47% and 98.56% on known words and between 75.57% and 83.49% on unknown words. Results show that TnT has reached a good level of maturity and is helpful enough for NLP tasks.",
keywords = "Character recognition, Error analysis, Mood, Natural languages, Speech processing, Speech recognition, Tagging, Testing, Text processing, Text recognition",
author = "Carrasco, {R. M.} and A. Gelbukh",
note = "Publisher Copyright: {\textcopyright} 2003 IEEE.; 4th Mexican International Conference on Computer Science, ENC 2003 ; Conference date: 08-09-2003 Through 12-09-2003",
year = "2003",
doi = "10.1109/ENC.2003.1232869",
language = "Ingl{\'e}s",
series = "Proceedings of the Mexican International Conference on Computer Science",
publisher = "IEEE Computer Society",
pages = "18--25",
editor = "Edgar Chavez and Jesus Favela and Alberto Oliart and Marcelo Mejia",
booktitle = "Proceedings of the 4th Mexican International Conference on Computer Science, ENC 2003",
address = "Estados Unidos",
}