NNEMBs at SemEval-2017 Task 4: Neural Twitter Sentiment Classification: a Simple Ensemble Method with Different Embeddings

Yichun Yin, Yangqiu Song, Ming Zhang


Abstract
Recently, neural twitter sentiment classification has become one of state-of-thearts, which relies less feature engineering work compared with traditional methods. In this paper, we propose a simple and effective ensemble method to further boost the performances of neural models. We collect several word embedding sets which are publicly released (often are learned on different corpus) or constructed by running Skip-gram on released large-scale corpus. We make an assumption that different word embeddings cover different words and encode different semantic knowledge, thus using them together can improve the generalizations and performances of neural models. In the SemEval 2017, our method ranks 1st in Accuracy, 5th in AverageR. Meanwhile, the additional comparisons demonstrate the superiority of our model over these ones based on only one word embedding set. We release our code for the method duplicability.
Anthology ID:
S17-2102
Volume:
Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)
Month:
August
Year:
2017
Address:
Vancouver, Canada
Venue:
*SEMEVAL
SIGs:
SIGLEX | SIGSEM
Publisher:
Association for Computational Linguistics
Note:
Pages:
621–625
Language:
URL:
https://www.aclweb.org/anthology/S17-2102
DOI:
10.18653/v1/S17-2102
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/S17-2102.pdf