Computational argumentation is an interdisciplinary research field, connecting Natural Language Processing (NLP) to other disciplines such as the social sciences. This tutorial will focus on a task that recently got into the center of attention in the community: argument quality assessment, that is, what makes an argument good or bad? We structure the tutorial along three main coordinates: (1) the notions of argument quality across disciplines (how do we recognize good and bad arguments?), (2) the modeling of subjectivity (who argues to whom; what are their beliefs?), and (3) the generation of improved arguments (what makes an argument better?). The tutorial highlights interdisciplinary aspects of the field, ranging from the collaboration of theory and practice (e.g., in NLP and social sciences), to approaching different types of linguistic structures (e.g., social media versus parliamentary texts), and facing the ethical issues involved (e.g., how to build applications for the social good). A key feature of this tutorial is its interactive nature: We will involve the participants in two annotation studies on the assessment and the improvement of quality, and we will encourage them to reflect on the challenges and potential of these tasks.

Emotion analysis in text is an area of research that encompasses a set of various natural language processing (NLP) tasks, including classification and regression settings, as well as structured prediction tasks like role labelling or stimulus detection. In this tutorial, we provide an overview of research from emotion psychology which sets the ground for choosing adequate NLP methodology, and present existing resources and classification methods used for emotion analysis in texts. We further discuss appraisal theories and how events can be interpreted regarding their presumably caused emotion and briefly introduce emotion role labelling. In addition to these technical topics, we discuss the use cases of emotion analysis in text, their societal impact, ethical considerations, as well as the main challenges in the field.

Conversations are the natural communication format for people. This fact has motivated the large body of question answering and chatbot research as a seamless way for people to interact with machines. The conversations between people however, captured as video, audio or private or public written conversations, largely remain untapped as a source of compelling starting point for developing language technology. Summarizing such conversations can be enormously beneficial: automatic minutes for meetings or meeting highlights sent to relevant people can optimize communication in various groups while minimizing demands on people’s time; similarly analysis of conversations in online support groups can provide valuable information to doctors about the patient concerns. Summarizing written and spoken conversation poses unique research challenges—text reformulation, discourse and meaning analysis beyond the sentence, collecting data, and proper evaluation metrics. All these have been revisited by researchers since the emergence of neural approaches as the dominant approach for solving language processing problems. In this tutorial, we will survey the cutting-edge methods for summarization of conversations, covering key sub-areas whose combination is needed for a successful solution.

With NLP research now quickly being transferred into real-world applications, it is important to be aware of and think through the consequences of our scientific investigation. Such ethical considerations are important in both authoring and reviewing. This tutorial will equip participants with basic guidelines for thinking deeply about ethical issues and review common considerations that recur in NLP research. The methodology is interactive and participatory, including case studies and working in groups. Importantly, the participants will be co-building the tutorial outcomes and will be working to create further tutorial materials to share as public outcomes.

Automated Machine Learning (AutoML) is an emerging field that has potential to impact how we build models in NLP. As an umbrella term that includes topics like hyperparameter optimization and neural architecture search, AutoML has recently become mainstream at major conferences such as NeurIPS, ICML, and ICLR. What does this mean to NLP? Currently, models are often built in an ad hoc process: we might borrow default hyperparameters from previous work and try a few variant architectures, but it is never guaranteed that final trained model is optimal. Automation can introduce rigor in this model-building process. This tutorial will summarize the main AutoML techniques and illustrate how to apply them to improve the NLP model-building process.

This cutting-edge tutorial will help the NLP community to get familiar with current research in privacy-preserving methods. We will cover topics as diverse as membership inference, differential privacy, homomorphic encryption, or federated learning, all with typical applications to NLP. The goal is not only to draw the interest of the broader community, but also to present some typical use-cases and potential pitfalls in applying privacy-preserving methods to human language technologies.