Emotion detection from user-generated contents is growing in importance in the area of natural language processing. The approach we proposed for the EmoContext task is based on the combination of a CNN and an LSTM using a concatenation of word embeddings. A stack of convolutional neural networks (CNN) is used for capturing the hierarchical hidden relations among embedding features. Meanwhile, a long short-term memory network (LSTM) is used for capturing information shared among words of the sentence. Each conversation has been formalized as a list of word embeddings, in particular during experimental runs pre-trained Glove and Google word embeddings have been evaluated. Surface lexical features have been also considered, but they have been demonstrated to be not usefully for the classification in this specific task. The final system configuration achieved a micro F1 score of 0.7089. The python code of the system is fully available at https://github.com/marcopoli/EmoContext2019.
CITATION STYLE
Polignano, M., de Gemmis, M., & Semeraro, G. (2019). SWAP at SemEval-2019 task 3: Emotion detection in conversations through Tweets, CNN and LSTM deep neural networks. In NAACL HLT 2019 - International Workshop on Semantic Evaluation, SemEval 2019, Proceedings of the 13th Workshop (pp. 324–329). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/s19-2056
Mendeley helps you to discover research relevant for your work.