Argumentation Mining


Goal of the tutorial
Nowadays, on the one hand, text analysis is a promising approach to identify and extract arguments from text, receiving attention from the natural language processing community (e.g., argument mining of legal documents, on-line debates, newspaper and scientific articles); on the other hand, computational models of argumentation have made substantial progress in providing abstract and structured formal models to represent and reason over argumentation structures. This tutorial focusses on the interaction between Computational Linguistics and Argumentation Theory with the goal to discuss the techniques and frameworks that have been proposed to analyze, aggregate, synthesize, structure, summarize, and reason about arguments in texts.

Tutorial Description
Argumentation is a multi-disciplinary research field, which studies debate interactions and reasoning processes, and spans across and ties together diverse research areas such as logic and philosophy, language, psychology and com- puter science. Argumentation has come to be increasingly central as a main study within Artificial Intelligence, due to its ability to conjugate representational needs with user-related cognitive models and computational models for automated reasoning. An important source of data for many of the disciplines interested in such studies is the Web, and social media in particular. Online newspapers, blogs, online debate platforms and social networks provide an heterogeneous flow of information where natural language arguments can be found, isolated and analyzed. The availability of such data, together with advances in computational linguistics and machine learning, created fertile ground for the rise of a new area of research called argument mining.
The goal of this tutorial is to provide an overview of the techniques, methodologies and tools for processing argumentation in natural language texts, as well as of the solved issues and open challenges the new research area of argument mining is facing with. The tutorial is conceived to present the main approaches proposed in this area, from the annotation of natural language argument corpora to the application of natural language processing techniques (e.g., grammars and classifiers) to obtain automatically annotated arguments. Argument mining is applied with the aim to analyze, aggregate, synthesize and reason over user- generated arguments. The tutorial will be concluded with an overview of some real world applications of argument mining.