Multi-Task Learning in Deep Neural Network for Sentiment Polarity and Irony classification

We study the impact of a new multi-task learning approach in deep neural network for polarity and irony detection in Italian Twitter posts. We compare this approach with traditional single-task learning models. The different behavior of the two approaches shows the effectiveness of the proposed method that is able to combine the information from the two tasks improving the accuracy in both tasks. This is particularly true on edge cases in which knowledge about the two tasks is needed to classify a tweet, this is the case, for example, when the literal polarity of a tweet is inverted by irony.

[1]  Felice Dell'Orletta,et al.  Building the state-of-the-art in POS tagging of Italian Tweets , 2016, CLiC-it/EVALITA.

[2]  Anders Søgaard,et al.  Deep multi-task learning with low level tasks supervised at lower layers , 2016, ACL.

[3]  Kuldip K. Paliwal,et al.  Bidirectional recurrent neural networks , 1997, IEEE Trans. Signal Process..

[4]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[5]  Chiara Alzetta,et al.  Convolutional Neural Networks for Sentiment Analysis on Italian Tweets , 2016, CLiC-it/EVALITA.

[6]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[7]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[8]  Mark Cieliebak,et al.  Sentiment Analysis using Convolutional Neural Networks with Multi-Task Training and Distant Supervision on Italian Tweets , 2019 .

[9]  Joachim Bingel,et al.  Sluice networks: Learning what to share between loosely related tasks , 2017, ArXiv.

[10]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[11]  Gary Marcus,et al.  Deep Learning: A Critical Appraisal , 2018, ArXiv.

[12]  Isa Maks,et al.  Generating Polarity Lexicons with WordNet propagation in 5 languages , 2014, LREC.

[13]  Silvia Bernardini,et al.  The WaCky wide web: a collection of very large linguistically processed web-crawled corpora , 2009, Lang. Resour. Evaluation.

[14]  Malvina Nissim,et al.  Overview of the Evalita 2016 SENTIment POLarity Classification Task , 2014, CLiC-it/EVALITA.