IIIDYT at SemEval-2018 Task 3: Irony detection in English tweets

Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018), pages 537–540 New Orleans, Louisiana, June 5–6, 2018. ©2018 Association for Computational Linguistics IIIDYT at SemEval-2018 Task 3: Irony detection in English tweets Edison Marrese-Taylor1*, Suzana Ilic2*, Jorge A. Balazs1*, Helmut Prendinger2, Yutaka Matsuo1 Graduate School of Engineering, The University of Tokyo, Japan1 emarrese,jorge,matsuo@weblab.t.u-tokyo.ac.jp National Institute of Informatics, Tokyo, Japan2 suzana,helmut@nii.ac.jp *Authors contributed equally to this work. Abstract In this paper we introduce our system for the task of Irony detection in English tweets, a part of SemEval 2018. We propose represen- tation learning approach that relies on a multi- layered bidirectional LSTM, without using ex- ternal features that provide additional seman- tic information. Although our model is able to outperform the baseline in the validation set, our results show limited generalization power over the test set. Given the limited size of the dataset, we think the usage of more pre- training schemes would greatly improve the obtained results. 1 Introduction Sentiment analysis and emotion recognition, as two closely related subfields of affective comput- ing, play a key role in the advancement of artifi- cial intelligence (Cambria et al., 2017). However, the complexity and ambiguity of natural language constitutes a wide range of challenges for compu- tational systems. In the past years irony and sarcasm detection have received great traction within the machine learning and NLP community (Joshi et al., 2016), mainly due to the high frequency of sarcastic and ironic expressions in social media. Their linguis- tic collocation inclines to flip polarity in the con- text of sentiment analysis, which makes machine- based irony detection critical for sentiment anal- ysis (Poria et al., 2016; Van Hee et al., 2015). Irony is a profoundly pragmatic and versatile lin- guistic phenomenon. As its foundations usu- ally lay beyond explicit linguistic patterns in re- constructing contextual dependencies and latent meaning, such as shared knowledge or common knowledge (Joshi et al., 2016), automatically de- tecting it remains a challenging task in natural lan- guage processing. In this paper, we introduce our system for the shared task of Irony detection in English tweets, a part of the 2018 SemEval (Van Hee et al., 2018). We note that computational approaches to auto- matically detecting irony often deploy expensive feature-engineered systems which rely on a rich body of linguistic and contextual cues (Bamman and Smith, 2015; Joshi et al., 2015). The advent of Deep Learning applied to NLP has introduced models that have succeeded in large part because they learn and use their own continuous numeric representations (Hinton, 1984) of words (Mikolov et al., 2013), offering us the dream of forgetting manually-designed features. To this extent, in this paper we propose a representation learning approach for irony detection, which relies on a bidirectional LSTM and pre-trained word embed- dings. 2 Data and pre-processing For the shared task, a balanced dataset of 2,396 ironic and 2,396 non-ironic tweets is provided. The ironic corpus was constructed by collecting self-annotated tweets with the hashtags #irony, #sarcasm and #not. The …

Content truncated to 500 words