TY - GEN
T1 - Convolutional sentence kernel from word embeddings for short text categorization
AU - Kim, Jonghoon
AU - Rousseau, François
AU - Vazirgiannis, Michalis
N1 - Publisher Copyright:
© 2015 Association for Computational Linguistics.
PY - 2015/1/1
Y1 - 2015/1/1
N2 - This paper introduces a convolutional sentence kernel based on word embeddings. Our kernel overcomes the sparsity issue that arises when classifying short documents or in case of little training data. Experiments on six sentence datasets showed statistically significant higher accuracy over the standard linear kernel with ngram features and other proposed models.
AB - This paper introduces a convolutional sentence kernel based on word embeddings. Our kernel overcomes the sparsity issue that arises when classifying short documents or in case of little training data. Experiments on six sentence datasets showed statistically significant higher accuracy over the standard linear kernel with ngram features and other proposed models.
UR - https://www.scopus.com/pages/publications/84959921442
U2 - 10.18653/v1/d15-1089
DO - 10.18653/v1/d15-1089
M3 - Conference contribution
AN - SCOPUS:84959921442
T3 - Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing
SP - 775
EP - 780
BT - Conference Proceedings - EMNLP 2015
PB - Association for Computational Linguistics (ACL)
T2 - Conference on Empirical Methods in Natural Language Processing, EMNLP 2015
Y2 - 17 September 2015 through 21 September 2015
ER -