Abstract | ||
---|---|---|
In this paper, through multi-task ensemble framework we address three problems of and sentiment analysis i.e. classification u0026 intensity, valence, arousal u0026 dominance for emotion and valence u0026 arousal} for sentiment. The underlying problems cover two granularities (i.e. coarse-grained and fine-grained) and a diverse range of domains (i.e. tweets, Facebook posts, news headlines, blogs, letters etc.). The ensemble model aims to leverage the learned representations of three deep learning models (i.e. CNN, LSTM and GRU) and a hand-crafted feature representation for the predictions. Experimental results on the benchmark datasets show the efficacy of our proposed multi-task ensemble frameworks. We obtain the performance improvement of 2-3 points on an average over single-task systems for most of the problems and domains. |
Year | Venue | Field |
---|---|---|
2018 | arXiv: Computation and Language | Arousal,Ensemble forecasting,Sentiment analysis,Computer science,Emotion classification,Natural language processing,Artificial intelligence,Deep learning,Machine learning,Performance improvement |
DocType | Volume | Citations |
Journal | abs/1808.01216 | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
md shad akhtar | 1 | 50 | 11.75 |
Deepanway Ghosal | 2 | 3 | 2.47 |
Asif Ekbal | 3 | 737 | 119.31 |
Pushpak Bhattacharyya | 4 | 795 | 186.21 |