TY - JOUR
T1 - Cic-IPN@INLi2018
T2 - 10th Working Notes of FIRE - Forum for Information Retrieval Evaluation, FIRE-WN 2018
AU - Markov, Ilia
AU - Sidorov, Grigori
N1 - Publisher Copyright:
© 2018 CEUR-WS. All Rights Reserved.
PY - 2018
Y1 - 2018
N2 - In this paper, we describe the CIC-IPN submissions to the shared task on Indian Native Language Identification (INLI 2018). We use the Support Vector Machines algorithm trained on numerous feature types: word, character, part-of-speech tag, and punctuation mark n-grams, as well as character n-grams from misspelled words and emotion-based features. The features are weighted using log-entropy scheme. Our team achieved 41.8% accuracy on the test set 1 and 34.5% accuracy on the test set 2, ranking 3rd in the official INLI shared task scoring.
AB - In this paper, we describe the CIC-IPN submissions to the shared task on Indian Native Language Identification (INLI 2018). We use the Support Vector Machines algorithm trained on numerous feature types: word, character, part-of-speech tag, and punctuation mark n-grams, as well as character n-grams from misspelled words and emotion-based features. The features are weighted using log-entropy scheme. Our team achieved 41.8% accuracy on the test set 1 and 34.5% accuracy on the test set 2, ranking 3rd in the official INLI shared task scoring.
KW - Feature engineering
KW - Indian languages
KW - Machine learning
KW - Native Language Identification
KW - Social media
UR - http://www.scopus.com/inward/record.url?scp=85058662261&partnerID=8YFLogxK
M3 - Artículo de la conferencia
AN - SCOPUS:85058662261
SN - 1613-0073
VL - 2266
SP - 82
EP - 88
JO - CEUR Workshop Proceedings
JF - CEUR Workshop Proceedings
Y2 - 6 December 2018 through 9 December 2018
ER -