Emo2Vec: Learning Generalized Emotion Representation by Multi-task Training
TL
TL;DR
Emo2Vec is proposed which encodes emotional semantics into vectors and outperforms existing affect-related representations, such as Sentiment-Specific Word Embedding and DeepMoji embeddings with much smaller training corpora.
Abstract
In this paper, we propose Emo2Vec which encodes emotional semantics into vectors. We train Emo2Vec by multi-task learning six different emotion-related tasks, including emotion/sentiment analysis, sarcasm classification, stress detection, abusive language classification, insult detection, and personality recognition. Our evaluation of Emo2Vec shows that it outperforms existing affect-related representations, such as Sentiment-Specific Word Embedding and DeepMoji embeddings with much smaller training corpora. When concatenated with GloVe, Emo2Vec achieves competitive performances to state-of-the-art results on several tasks using a simple logistic regression classifier.
References42 items
1
Attention-Based LSTM for Psychological Stress Detection from Spoken Language Using Distant Supervision
2
Assessing State-of-the-Art Sentiment Models on State-of-the-Art Sentiment Datasets
3
Refining Word Embeddings for Sentiment Analysis
4
Recurrent Attention Network on Memory for Aspect Sentiment Analysis
5