ELiRF-UPV at SemEval-2019 Task 3: Snapshot Ensemble of Hierarchical Convolutional Neural Networks for Contextual Emotion Detection

Proceedings of the 13th International Workshop on Semantic Evaluation (SemEval-2019), pages 195–199 Minneapolis, Minnesota, USA, June 6–7, 2019. ©2019 Association for Computational Linguistics 195 ELiRF-UPV at SemEval-2019 Task 3: Snapshot Ensemble of Hierarchical Convolutional Neural Networks for Contextual Emotion Detection Jos´e- ´Angel Gonz´alez, Llu´ıs-F. Hurtado, Ferran Pla Departament de Sistemas Inform`atics i Computaci´o Universitat Polit`ecnica de Val`encia. Cam´ı de Vera, sn 46022, Val`encia {jogonba2, lhurtado, fpla}@dsic.upv.es Abstract This paper describes the approach developed by the ELiRF-UPV team at SemEval 2019 Task 3: Contextual Emotion Detection in Text. We have developed a Snapshot Ensemble of 1D Hierarchical Convolutional Neural Net- works to extract features from 3-turn conver- sations in order to perform contextual emotion detection in text. This Snapshot Ensemble is obtained by averaging the models selected by a Genetic Algorithm that optimizes the evalua- tion measure. The proposed ensemble obtains better results than a single model and it obtains competitive and promising results on Contex- tual Emotion Detection in Text. 1 Introduction Emotion Detection problem arises in the context of conversational interactions, among two or more agents, when one agent is interested in knowing the emotional state of other agent involved in the conversation. The detection of emotions is a dif- ficult task when the content is expressed by using only text, due to the lack of facial and hand ges- ture expressions, voice modulations, etc. More- over, the task becomes more complex if the detec- tion of emotions is applied only on a short piece of text without including context. This is because the context can act as an emotion modifier of a given turn in the conversation. Although, researchers mainly focus on emotion detection on text in absence of context (Moham- mad et al., 2018) (Klinger et al., 2018), tipically extracted from social media, recently, there are few works that approach the emotion detection in conversations by using context information (Haz- arika et al., 2018b) (Majumder et al., 2018) (Haz- arika et al., 2018a). These contextual systems work on long conversations where different users are involved and they use multimodal data, specif- ically, text, audio and video in order to address the emotion detection problem on large multi-party conversations. In this work, we present an approach to the Se- meval 2019 Task 3: Contextual Emotion Detec- tion in Text (Chatterjee et al., 2019). This task is a simplification of the text emotion detection problem on conversations where each conversa- tion have only three utterances. Only two different users are involved in each conversation, where the first and third turn corresponds to the first user and the second turn corresponds to the second user. The goal of this tasks is to predict the emotion of the third turn. We propose a Snapshot Ensem- ble (SE) of 1D Hierarchical Convolutional Neu- ral Networks (HCNN) trained to extract useful in- formation from 3-turn conversations. Our system was designed following some ideas of (Morris and Keltner, 2000) and (Majumder et al., 2018). Con- cretely, we consider the inter-turn and self-turn de- pendencies …

Content truncated to 500 words