EACL 2017 Workshop on Symbolic and Deep Learning Approaches to the Analysis of Evaluative, Affective, and Subjective Language (EASL 2017)

Description

Language is a medium for the expression of human thought. It serves as the vehicle for conveying our emotions, feelings, beliefs, judgements and opinions of people, events and objects, comparing and contrasting our evaluations with those of others in the world. Evaluative, Affective and Subjective (EAS) language satisfies our inherent human need to speak of our perceptions and evaluations in a way framed by our internally held beliefs, emotions, biases and opinions. Analysis and understanding of EAS language is multi-disciplinary and complex, deep beyond mere word cues. It extends to the underlying meaning and the implicit socio-cultural origins of the text, with both linguistic and extra-linguistic aspects to it. Machine comprehension of EAS text on par with human understanding requires identification and understanding of fine-grained emotions, beliefs, opinions, and judgements expressed in language both implicitly and explicitly. The goal of this workshop is to focus the attention of NLP research community on combining deep learning statistical NLP techniques with richer/deeper semantic representations driven by computational linguistics in analysing and understanding EAS text.

This workshop is intended to foster greater cross-disciplinary collaboration between the fields of computational linguistics, machine learning, sociolinguistics, and psycholinguistics, with the aim of improving machine comprehension of evaluative, affective and subjective text. We are also interested in non-trivial EAS text applications which go beyond the mere identification of evaluative, emotive, subjective cue phrases to underlying causative events/reasons/arguments which give rise to these emotions/feelings/beliefs/subjective opinions. We also welcome non-trivial benchmarks for comparing machine comprehension of EAS aspects with human understanding.

Topics of interest

Topics of interest include but are not limited to:

• richer/deeper linguistic representations of aspects of EAS
• understanding of cognitive processing of EAS language
• extra-linguistic aspects of EAS language
• socio-cultural aspects of EAS language
• psycholinguistic aspects of EAS text analysis
• interpretability of deep learning-based EAS analysis systems
• identifying origins/dynamic contexts/causative events/reasons in EAS text analysis (including the fields of stance detection, subjective judgements/beliefs detection, argumentation in both emotive and evaluative texts).