Seq2Emo: A Sequence to Multi-Label Emotion Classification Model

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4717–4724 June 6–11, 2021. ©2021 Association for Computational Linguistics 4717 Seq2Emo: A Sequence to Multi-Label Emotion Classification Model Chenyang Huang, Amine Trabelsi, Xuebin Qin, Nawshad Farruque, Lili Mou, Osmar Zaïane Alberta Machine Intelligence Institute Department of Computing Science, University of Alberta {chenyangh,atrabels,xuebin,nawshad,zaiane}@ualberta.ca doublepower.mou@gmail.com Abstract Multi-label emotion classification is an impor- tant task in NLP and is essential to many applications. In this work, we propose a sequence-to-emotion (Seq2Emo) approach, which implicitly models emotion correlations in a bi-directional decoder. Experiments on SemEval’18 and GoEmotions datasets show that our approach outperforms state-of-the-art methods (without using external data). In particular, Seq2Emo outperforms the binary relevance (BR) and classifier chain (CC) ap- proaches in a fair setting.1 1 Introduction Emotion classification from text (Yadollahi et al., 2017; Sailunaz et al., 2018) plays an important role in affective computing research, and is essential to human-like interactive systems, such as emotional chatbots (Asghar et al., 2018; Zhou et al., 2018; Huang et al., 2018; Ghosal et al., 2019). Early work treats this task as multi-class classi- fication (Scherer and Wallbott, 1994; Mohammad, 2012), where each data instance (e.g., a sentence) is assumed to be labeled with one and only one emotion. More recently, researchers relax such an assumption and treat emotion analysis as multi- label classification (MLC, Mohammad et al., 2018; Demszky et al., 2020). In this case, each data in- stance may have one or multiple emotion labels. This is a more appropriate setting for emotion anal- ysis, because an utterance may exhibit multiple emotions (e.g., “angry” and “sad”, “surprise” and “joy”). The binary relevance approach (BR, Godbole and Sarawagi, 2004) is widely applied to multi- label emotion classification. BR predicts a binary indicator for each emotion individually, assuming that the emotions are independent given the in- put sentence. However, evidence in psychotherapy 1Our code is available at https://github.com/ chenyangh/Seq2Emo suggests strong correlation among different emo- tions (Plutchik, 1980). For example, “hate” may co-occur more often with “disgust” than “joy.” An alternative approach to multi-label emotion classification is the classifier chain (CC, Read et al., 2009). CC predicts the label(s) of an input in an autoregressive manner, for example, by a sequence- to-sequence (Seq2Seq) model (Yang et al., 2018). However, Seq2Seq models are known to have the problem of exposure bias (Bengio et al., 2015), i.e., an error at early steps may affect future predictions. In this work, we propose a sequence-to-emotion (Seq2Emo) approach, where we consider emotion correlations implicitly. Similar to CC, we also build a Seq2Seq-like model, but predict a binary indica- tor of an emotion at each decoding step of Seq2Seq. We do not feed predicted emotions back to the de- coder; thus, our model does not suffer from the exposure bias problem. Compared with BR, our Seq2Emo model implicitly considers the correla- tion of emotions in the hidden states of the decoder, and with an attention mechanism, our Seq2Emo is able …

Content truncated to 500 words