Sarcasm Detection with Self-matching Networks and Low-rank Bilinear Pooling

Sarcasm is sophisticated linguistic expression and is commonly observed on social media and e-commerce platforms. Failure to detect sarcastic expressions in natural language processing tasks, such as opinion mining and sentiment analysis, leads to poor model performance. Traditional approaches rely heavily on discrete handcrafted features and will incur enormous human costs. It was not until recent that scholars began to employ neural networks to address these limitations and have achieved new state-of-the-art performance. In this work, we propose a novel self-matching network to capture sentence ”incongruity” information by exploring word-to-word interactions. In particular, we calculate the joint information in each word-to-word pair in the input sentence to build a self-matching attention vector, based on which we attend the sentence and build its representation vector. Such a network allows sentence to match within itself word by word and cater to the words of conflict sentiments. In addition, we incorporate a bi-directional LSTM network into our proposed network to retain compositional information. We concatenate incongruity information and compositional information through a Low-rank Bilinear Pooling method to control for potential information redundancy without losing discriminative power. Experiment results on publicly available datasets demonstrate that our model significantly outperforms extant baselines on standard evaluation metrics including precision, recall, F1 score and accuracy.

[1]  Tony Veale,et al.  Fracking Sarcasm using Neural Network , 2016, WASSA@NAACL-HLT.

[2]  A. Katz,et al.  Are There Necessary Conditions for Inducing a Sense of Sarcastic Irony? , 2012 .

[3]  Pushpak Bhattacharyya,et al.  Are Word Embedding-based Features Useful for Sarcasm Detection? , 2016, EMNLP.

[4]  Ari Rappoport,et al.  Semi-Supervised Recognition of Sarcasm in Twitter and Amazon , 2010, CoNLL.

[5]  Pushpak Bhattacharyya,et al.  Automatic Sarcasm Detection: A Survey , 2016 .

[6]  Jun Hong,et al.  Sarcasm Detection on Czech and English Twitter , 2014, COLING.

[7]  Diana Maynard,et al.  Who cares about Sarcastic Tweets? Investigating the Impact of Sarcasm on Sentiment Analysis. , 2014, LREC.

[8]  Byron C. Wallace,et al.  Sparse, Contextually Informed Models for Irony Detection: Exploiting User Communities, Entities and Sentiment , 2015, ACL.

[9]  Pushpak Bhattacharyya,et al.  Harnessing Context Incongruity for Sarcasm Detection , 2015, ACL.

[10]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[11]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[12]  Pushpak Bhattacharyya,et al.  Harnessing Sequence Labeling for Sarcasm Detection in Dialogue from TV Series ‘Friends’ , 2016, CoNLL.

[13]  Jiasen Lu,et al.  Hierarchical Question-Image Co-Attention for Visual Question Answering , 2016, NIPS.

[14]  Marilyn A. Walker,et al.  Really? Well. Apparently Bootstrapping Improves the Performance of Sarcasm and Nastiness Classifiers for Online Dialogue , 2013, ArXiv.

[15]  Penny M. Pexman,et al.  Context Incongruity and Irony Processing , 2003 .

[16]  Ellen Riloff,et al.  Sarcasm as Contrast between a Positive Sentiment and Negative Situation , 2013, EMNLP.

[17]  RossoPaolo,et al.  A multidimensional approach for detecting irony in Twitter , 2013 .

[18]  Paolo Rosso,et al.  Making objective decisions from subjective data: Detecting irony in customer reviews , 2012, Decis. Support Syst..

[19]  Nathalie Aussenac-Gilles,et al.  Towards a Contextual Pragmatic Model to Detect Irony in Tweets , 2015, ACL.

[20]  Diyi Yang,et al.  Hierarchical Attention Networks for Document Classification , 2016, NAACL.

[21]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[22]  Marilyn A. Walker,et al.  A Corpus for Research on Deliberation and Debate , 2012, LREC.

[23]  Yue Zhang,et al.  Tweet Sarcasm Detection Using Deep Neural Network , 2016, COLING.

[24]  Reza Zafarani,et al.  Sarcasm Detection on Twitter: A Behavioral Modeling Approach , 2015, WSDM.

[25]  Tony Veale,et al.  Detecting Ironic Intent in Creative Comparisons , 2010, ECAI.

[26]  Sanjay Kumar Jena,et al.  Parsing-based sarcasm sentiment recognition in Twitter data , 2015, 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM).

[27]  Tony Veale,et al.  Magnets for Sarcasm: Making Sarcasm Detection Timely, Contextual and Very Personal , 2017, EMNLP.

[28]  Byron C. Wallace,et al.  Modelling Context with User Embeddings for Sarcasm Detection in Social Media , 2016, CoNLL.

[29]  Ari Rappoport,et al.  ICWSM - A Great Catchy Name: Semi-Supervised Recognition of Sarcastic Sentences in Online Product Reviews , 2010, ICWSM.

[30]  Nina Wacholder,et al.  Identifying Sarcasm in Twitter: A Closer Look , 2011, ACL.

[31]  Elisabeth Camp Sarcasm, Pretense, and The Semantics/ Pragmatics Distinction ∗ , 2012 .

[32]  Antal van den Bosch,et al.  The perfect solution for detecting sarcasm in tweets #not , 2013, WASSA@NAACL-HLT.

[33]  Paolo Rosso,et al.  A multidimensional approach for detecting irony in Twitter , 2013, Lang. Resour. Evaluation.

[34]  Jian Su,et al.  Reasoning with Sarcasm by Reading In-Between , 2018, ACL.

[35]  Tomoaki Ohtsuki,et al.  Opinion mining in Twitter: How to make use of sarcasm to enhance sentiment analysis , 2015, 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM).

[36]  Navneet Kaur,et al.  Opinion mining and sentiment analysis , 2016, 2016 3rd International Conference on Computing for Sustainable Global Development (INDIACom).

[37]  Davide Buscaldi,et al.  From humor recognition to irony detection: The figurative language of social media , 2012, Data Knowl. Eng..

[38]  Horacio Saggion,et al.  Modelling Sarcasm in Twitter, a Novel Approach , 2014, WASSA@ACL.