TY - CHAP

T1 - Portuguese part-of-speech tagging with large margin structure learning

AU - Fernandes, Eraldo Rezende

AU - Rodrigues, Irving Muller

AU - Milidiú, Ruy Luiz

N1 - Conference code: 3

PY - 2014/12/12

Y1 - 2014/12/12

N2 - Part-of-Speech Tagging is a fundamental task on many Natural Language Processing systems. This task consists in identifying the syntactic category, i.e. the part of speech, of each word in a sentence. Despite the fact that the current state-of-the-art accuracy for this task is around 97%, any improvement has an immediate impact on more complex tasks, like Parsing, Semantic Role Labeling and Information Extraction. Thus, it is still relevant to explore this task. In this paper, we introduce a part-of-speech tagger based on the Structure Learning framework that reduces the smallest known error on the Portuguese Mac-Morpho corpus by 7.8%. We also apply our tagger to a recently revised version of Mac-Morpho. Our system accuracy on this latter version is competitive with a semi-supervised Neural Network trained on Mac-Morpho plus a very large non-annotated corpus. Additionally, our system is simpler than previous systems and uses a very limited feature set. Our system employs a Large Margin training criteria to derive a structure predictor that is more robust on unseen data.

AB - Part-of-Speech Tagging is a fundamental task on many Natural Language Processing systems. This task consists in identifying the syntactic category, i.e. the part of speech, of each word in a sentence. Despite the fact that the current state-of-the-art accuracy for this task is around 97%, any improvement has an immediate impact on more complex tasks, like Parsing, Semantic Role Labeling and Information Extraction. Thus, it is still relevant to explore this task. In this paper, we introduce a part-of-speech tagger based on the Structure Learning framework that reduces the smallest known error on the Portuguese Mac-Morpho corpus by 7.8%. We also apply our tagger to a recently revised version of Mac-Morpho. Our system accuracy on this latter version is competitive with a semi-supervised Neural Network trained on Mac-Morpho plus a very large non-annotated corpus. Additionally, our system is simpler than previous systems and uses a very limited feature set. Our system employs a Large Margin training criteria to derive a structure predictor that is more robust on unseen data.

KW - Machine Learning

KW - Natural Language Processing

KW - POS Tagging

KW - Structure Learning

KW - Informatics

KW - Business informatics

UR - http://www.scopus.com/inward/record.url?scp=84922535000&partnerID=8YFLogxK

U2 - 10.1109/BRACIS.2014.16

DO - 10.1109/BRACIS.2014.16

M3 - Article in conference proceedings

AN - SCOPUS:84922535000

SN - 978-1-4799-7859-5

SP - 25

EP - 30

BT - BRACIS 2014

PB - Institute of Electrical and Electronics Engineers Inc.

CY - Piscataway

T2 - Brazilian Conference on Intelligent Systems - BRACIS 2014

Y2 - 18 October 2014 through 23 October 2014

ER -