A Neural Approach to Irony Generation

Ironies can not only express stronger emotions but also show a sense of humor. With the development of social media, ironies are widely used in public. Although many prior research studies have been conducted in irony detection, few studies focus on irony generation. The main challenges for irony generation are the lack of large-scale irony dataset and difficulties in modeling the ironic pattern. In this work, we first systematically define irony generation based on style transfer task. To address the lack of data, we make use of twitter and build a large-scale dataset. We also design a combination of rewards for reinforcement learning to control the generation of ironic sentences. Experimental results demonstrate the effectiveness of our model in terms of irony accuracy, sentiment preservation, and content preservation.

[1]  Yulia Tsvetkov,et al.  Style Transfer Through Multilingual and Feedback-Based Back-Translation , 2018, ArXiv.

[2]  Dongyan Zhao,et al.  Style Transfer in Text: Exploration and Evaluation , 2017, AAAI.

[3]  Samy Bengio,et al.  Content preserving text generation with attribute controls , 2018, NeurIPS.

[4]  Richard Evans,et al.  WLV at SemEval-2018 Task 3: Dissecting Tweets in Search of Irony , 2018, *SEMEVAL.

[5]  Rico Sennrich,et al.  Improving Neural Machine Translation Models with Monolingual Data , 2015, ACL.

[6]  Guillaume Lample,et al.  Multiple-Attribute Text Rewriting , 2018, ICLR.

[7]  Preslav Nakov,et al.  SemEval-2014 Task 9: Sentiment Analysis in Twitter , 2014, *SEMEVAL.

[8]  Jie Zhou,et al.  A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer , 2019, IJCAI.

[9]  Mário J. Silva,et al.  Automatic creation of a reference corpus for political opinion mining in user-generated content , 2009, TSA@CIKM.

[10]  Paolo Rosso,et al.  SemEval-2015 Task 11: Sentiment Analysis of Figurative Language in Twitter , 2015, *SEMEVAL.

[11]  R. J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[12]  Shrikanth Narayanan,et al.  NTUA-SLP at SemEval-2018 Task 1: Predicting Affective Content in Tweets with Deep Attentive RNNs and Transfer Learning , 2018, *SEMEVAL.

[13]  Percy Liang,et al.  Delete, Retrieve, Generate: a Simple Approach to Sentiment and Style Transfer , 2018, NAACL.

[14]  Nathalie Aussenac-Gilles,et al.  Exploring the Impact of Pragmatic Phenomena on Irony Detection in Tweets: A Multilingual Corpus Study , 2017, EACL.

[15]  Lillian Lee,et al.  Opinion Mining and Sentiment Analysis , 2008, Found. Trends Inf. Retr..

[16]  Chuhan Wu,et al.  THU_NGN at SemEval-2018 Task 3: Tweet Irony Detection with Densely connected LSTM and Multi-task Learning , 2018, *SEMEVAL.

[17]  Salim Roukos,et al.  Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[18]  Eric P. Xing,et al.  Toward Controlled Generation of Text , 2017, ICML.

[19]  Regina Barzilay,et al.  Style Transfer from Non-Parallel Text by Cross-Alignment , 2017, NIPS.

[20]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[21]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[22]  Véronique Hoste,et al.  SemEval-2018 Task 3: Irony Detection in English Tweets , 2018, *SEMEVAL.

[23]  Tony Veale,et al.  IronyMagnet at SemEval-2018 Task 3: A Siamese network for Irony detection in Social media , 2018, *SEMEVAL.

[24]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

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

[26]  Houfeng Wang,et al.  Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach , 2018, ACL.