Event-Driven Emotion Cause Extraction with Corpus Construction

Abstract

In this paper, we present our work in emotion cause extraction. Since there is no open dataset available, the lack of annotated resources has limited the research in this area. Thus, we first present a dataset we built using SINA city news. The annotation is based on the scheme of the W3C Emotion Markup Language. Second, we propose a 7-tuple definition to describe emotion cause events. Based on this general definition, we propose a new event-driven emotion cause extraction method using multi-kernel SVMs where a syntactical tree based approach is used to represent events in text. A convolution kernel based multikernel SVM are used to extract emotion causes. Because traditional convolution kernels do not use lexical information at the terminal nodes of syntactic trees, we modify the kernel function with a synonym based improvement. Even with very limited training data, we can still extract sufficient features for the task. Evaluations show that our approach achieves 11.6% higher F-measure compared to referenced methods. The contributions of our work include resource construction, concept definition and algorithm development.

Suicidal Ideation Cause Extraction From Social Texts

“…These methods consider emotion cause extraction to be a candidate sentence or clause classification problem [63,65,67,68] or a sequence labeling problem [69,70]. The classification problem is to classify whether the candidate sentence or clause is the cause through its own features and contextual features.…”

Extracting Emotion Causes Using Learning to Rank Methods From an Information Retrieval Perspective

“…Support vector machines (SVMs) and conditional random fields (CRFs) were adopted to classify cause or non-cause text with extended rule-based features in existing studies [7], [12]. Gui et al [8] employed an SVM based method for emotion cause detection, which extracted convolution kernels from syntactic trees to capture the cause information. In their subsequent study, they proposed a memory network-based question-answering approach to further enhance the performance of emotion cause extraction [9].…”

“…In this section, we formalize the proposed framework based on learning to rank for emotion cause extraction. We follow the formal definition of emotion cause extraction by Gui et al [8]. Text contents involving emotions are an indispensable resources for opinion mining and personalized recommendation.…”

Reasoning with Heterogeneous Knowledge for Commonsense Machine Comprehension

“…Many expansions have been introduced later, including unsupervisedly learning narrative schemas and scripts (Chambers and Jurafsky, 2009;Regneri et al, 2011), event schemas and frames (Chambers and Jurafsky, 2011;Balasubramanian et al, 2013;Sha et al, 2016;Huang et al, 2016;Mostafazadeh et al, 2016b), and some generative models to learn latent structures of event knowledge (Cheung et al, 2013;Chambers, 2013;Bamman et al, 2014;Nguyen et al, 2015). Another direction for learning event-centred knowledge is causality identification (Do et al, 2011;Radinsky et al, 2012;Berant et al, 2014;Hashimoto et al, 2015;Gui et al, 2016), which tried to identify the causality relation in text.…”

“…In recent years, many methods have been proposed for commonsense machine comprehension. However, these methods mostly either focus on matching explicit information in given texts (Weston et al, 2014;Wang and Jiang, 2016a,b;Zhao et al, 2017), or paid attention to one specific kind of commonsense knowledge, such as event temporal relation (Chambers and Jurafsky, 2008;Modi and Titov, 2014;Pichotta and Mooney, 2016b;Hu et al, 2017) and event causality (Do et al, 2011;Radinsky et al, 2012;Hashimoto et al, 2015;Gui et al, 2016). As discussed above, it is obvious that commonsense machine comprehension problem is far from settled by considering only explicit or a single kind of commonsense knowledge.…”