ConSSED at SemEval-2019 Task 3: Configurable Semantic and Sentiment Emotion Detector

Proceedings of the 13th International Workshop on Semantic Evaluation (SemEval-2019), pages 175–179 Minneapolis, Minnesota, USA, June 6–7, 2019. ©2019 Association for Computational Linguistics 175 ConSSED at SemEval-2019 Task 3: Configurable Semantic and Sentiment Emotion Detector Rafał Po´swiata National Information Processing Institute al. Niepodległo´sci 188b, 00-608 Warsaw, Poland rafal.poswiata@opi.org.pl Abstract This paper describes our system participating in the SemEval-2019 Task 3: EmoContext: Contextual Emotion Detection in Text. The goal was to for a given textual dialogue, i.e. a user utterance along with two turns of context, identify the emotion of user utterance as one of the emotion classes: Happy, Sad, Angry or Others. Our system: ConSSED is a configu- rable combination of semantic and sentiment neural models. The official task submission achieved a micro-average F1 score of 75.31 which placed us 16th out of 165 participating systems. 1 Introduction Emotion detection is crucial in developing a “smart” social (chit-chat) dialogue system (Chen et al., 2018). Like many sentence classification tasks, classifying emotions requires not only un- derstanding of single sentence, but also capturing contextual information from entire conversations. For the competition we were invited to create a system for emotion detection of user utterance from short textual dialogue i.e. a user utterance along with two turns of context (Chatterjee et al., 2019b). The number of emotion classes has been limited to four (Happy, Sad, Angry and Others). The rest of the paper is organized as follows. Section 2 briefly shows the related work. Section 3 elaborates on our approach. It shows preproces- sing step and architecture of our system. Section 4 describes the data set, used word embeddings and hyper-parameters, adopted research methodology and experiments with results. Finally, Section 5 concludes our work. 2 Related Work Detection of emotions in dialogues can be divided into two types: based only on the text of the dialo- gue (Chen et al., 2018) and based on many chan- nels (video, speech, motion capture of a face, text transcriptions) (Busso et al., 2008). Regardless of the type, the most common solution is the use of neural networks, in particular variations of Recur- rent Neural Networks, such as LSTMs (Hochreiter and Schmidhuber, 1997), BiLSTMs (Schuster and Paliwal, 1997) and GRUs (Cho et al., 2014) or Co- nvolutional Neural Networks (Krizhevsky et al., 2012). Our solution uses LSTMs and BiLSTMs and is based on the ideas from SS-BED system (Chatterjee et al., 2019a). 3 Our Approach Figure 1 provides an overview of our approach. We wanted to create a system that would bene- fit from the advantages of semantic and sentiment embeddings (like SS-BED). At the same time, it would be easily configurable both in terms of the selection of parameters/network architecture as well as the change of applied embeddings, both static and dynamic. In the next subsections, we describe in details our approach. 3.1 Preprocessing For the preprocessing, we adjusted the ekphrasis tool (Baziotis et al., 2017). We use this tool for tokenization and to do the following: • Normalize URLs, emails, per- cent/money/time/date expressions and …

Content truncated to 500 words