@inproceedings{ff9fc25662494d7c9806b4f88af84d05,
title = "Classification over Clustering: Augmenting Text Representation with Clusters Helps!",
abstract = "Considering that words with different characteristic in the text have different importance for classification, grouping them together separately can strengthen the semantic expression of each part. Thus we propose a new text representation scheme by clustering words according to their latent semantics and composing them together to get a set of cluster vectors, which are then concatenated as the final text representation. Evaluation on five classification benchmarks proves the effectiveness of our method. We further conduct visualization analysis showing statistical clustering results and verifying the validity of our motivation.",
keywords = "Classification, Clustering, Semantic, Visualization",
author = "Xiaoye Tan and Rui Yan and Chongyang Tao and Mingrui Wu",
note = "Publisher Copyright: {\textcopyright} 2019, Springer Nature Switzerland AG.; 8th CCF International Conference on Natural Language Processing and Chinese Computing, NLPCC 2019 ; Conference date: 09-10-2019 Through 14-10-2019",
year = "2019",
doi = "10.1007/978-3-030-32236-6\_3",
language = "英语",
isbn = "9783030322359",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer",
pages = "28--40",
editor = "Jie Tang and Min-Yen Kan and Dongyan Zhao and Sujian Li and Hongying Zan",
booktitle = "Natural Language Processing and Chinese Computing - 8th CCF International Conference, NLPCC 2019, Proceedings",
address = "德国",
}