This paper describes our system, entitled IronyMagnet, for the 3rd Task of the SemEval 2018 workshop, “Irony Detection in English Tweets”. In Task 1, irony classification task has been considered as a binary classification task. Now for the first time, finer categories of irony are considered as part of a shared task. In task 2, three types of irony are considered; “Irony by contrast” - ironic instances where evaluative expression portrays inverse polarity (positive, negative) of the literal proposition; “Situational irony” - ironic instances where output of a situation do not comply with its expectation; “Other verbal irony” - instances where ironic intent does not rely on polarity contrast or unexpected outcome. We proposed a Siamese neural network for irony detection, which is consisted of two subnetworks, each containing a long short term memory layer(LSTM) and an embedding layer initialized with vectors from Glove word embedding 1 . The system achieved a f-score of 0.72, and 0.50 in task 1, and task 2 respectively.

Sarcasm is a pervasive phenomenon in social media, permitting the concise communication of meaning, affect and attitude. Concision requires wit to produce and wit to understand, which demands from each party knowledge of norms, context and a speaker’s mindset. Insight into a speaker’s psychological profile at the time of production is a valuable source of context for sarcasm detection. Using a neural architecture, we show significant gains in detection accuracy when knowledge of the speaker’s mood at the time of production can be inferred. Our focus is on sarcasm detection on Twitter, and show that the mood exhibited by a speaker over tweets leading up to a new post is as useful a cue for sarcasm as the topical context of the post itself. The work opens the door to an empirical exploration not just of sarcasm in text but of the sarcastic state of mind.

This paper describes our system, entitled Idiom Savant, for the 7th Task of the Semeval 2017 workshop, “Detection and interpretation of English Puns”. Our system consists of two probabilistic models for each type of puns using Google n-gram and Word2Vec. Our system achieved f-score of calculating, 0.663, and 0.07 in homographic puns and 0.8439, 0.6631, and 0.0806 in heterographic puns in task 1, task 2, and task 3 respectively.