HWHenning Wachsmuth

Henning Wachsmuth

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Henning Wachsmuth has a total of 103 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Argumentative Language

    by Manfred Stede, Jodi Schneider, Henning Wachsmuth

    In this chapter, we consider the linguistic side of argumentation: What does the language of arguing look like, and how does it differ from other ways of speaking or writing? The chapter thus is intended to serve primarily as background for readers who approach argument mining originally from a technical perspective but are also interested in the underlying linguistic phenomena and their terminology. We will also touch upon some NLP tasks that are related to argumentation, to build some bridges to areas the reader might be familiar with.

  • Open Access

    Tools & Applications

    by Manfred Stede, Jodi Schneider, Henning Wachsmuth

    This chapter discusses tools for working with arguments as well as applications that use or could use argument mining. In our usage, tools process arguments as input or output for well-defined tasks within argumentation theory; they may be relevant for tasks such as creating corpora or assessing argument quality. By applications we mean complete argumentation systems designed to support or interact with human users to achieve a specific goal that substantively involves argument or controversy in some way.

  • Open Access

    Representing Arguments

    by Manfred Stede, Jodi Schneider, Henning Wachsmuth

    In this chapter we discuss representing arguments and give examples of how particular representations have been adopted in NLP research for argument mining. To mine arguments, we need some way to represent them. Those representations are given by argument models that describe the components of an argument, such as the ‘standpoint’ in our definition from Sect. 1.1.1 , and relations between components such as ‘support’ and ‘rebut’ in our example from Fig. 1.1 .

  • Open Access

    Argument Reasoning

    by Manfred Stede, Jodi Schneider, Henning Wachsmuth

    Reasoning is the heart of argumentation—so much that some researchers might equate the terms reasoning and argumentation . This is because, conceptually, an argument manifests a reasoning process (or process step) in natural language: the relation that it defines from one or more premises to a conclusion instantiates the act of giving a reason, or reasons, to support a claim. In a broader sense, though, argumentation comprises more than just reasoning. As the previous chapters on perspective and quality assessment have emphasized, subjective viewpoints and perceptions are inherent to argumentation, and rhetoric and dialectic are important in any real-world argumentation setting. Thus, reasoning can be understood as the part of argumentation that describes how people infer new (or hidden) information from given information through the use or exchange of arguments. As such, reasoning is where the NLP tasks of analysis and synthesis meet. In this chapter, we discuss some main strands of NLP research that model key aspects of reasoning, given previously mined or otherwise structured arguments.

  • Open Access

    Introduction

    by Manfred Stede, Jodi Schneider, Henning Wachsmuth

    Argument mining is inherently computational, building on various techniques from natural language processing (NLP) and different areas of artificial intelligence (AI). At its core, it deals with the development and evaluation of models and methods for the computational understanding and generation of human language, with the data underlying both of them, and with the applications that deploy them. However, argument mining is motivated in the treatment of argumentation specifically, a pervasive human activity in both spoken and written language that has been studied in linguistics as well as philosophy and other disciplines for millenia. Understanding the fundamental goals and ideas of argument mining hence also requires knowledge about the linguistic and argumentation-theoretic concepts it draws from.

  • Open Access

    Perspective Assessment

    by Manfred Stede, Jodi Schneider, Henning Wachsmuth

    Chapters 4 and 5 have presented the core of argument mining, that is, the identification of argumentative structure in natural language texts. While this information constitutes the basis of any application dealing with arguments, many applications also need knowledge about the perspectives that mined arguments convey toward the controversial issues discussed. For example, existing argument search engines separately display pro and con arguments on an issue. Debating technologies should frame arguments in a way that supports their side convincingly, and the effectiveness of arguments may depend on whether the values they encode match those of their audience. In this chapter, we review NLP methods that assess the perspectives of arguments or argumentative texts.

  • Open Access

    Argument Generation

    by Manfred Stede, Jodi Schneider, Henning Wachsmuth

    Both the mining of arguments from natural language text (Chaps. 4 and 5 ) and the assessment of their properties (Chaps. 6 and 7 ) imply analysis tasks: NLP methods infer information from input texts. In the context of argument quality and reasoning, Chaps. 7 and 8 already covered some more synthesis-oriented tasks, the rewriting of argumentative text to improve its quality and the reconstruction of argument components left implicit in a text, respectively. In this chapter, we fully turn our view to situations in which new argumentative content is to be produced, be it single claims, complete arguments, or longer argumentative texts. That is, we consider synthesis tasks in detail here (even if, seen strictly, they lie outside the scope of a book called Argument Mining ): NLP methods produce new text from information or other input texts. We cover all such methods under the term argument generation .

  • Open Access

    Argument Unit Identification

    by Manfred Stede, Jodi Schneider, Henning Wachsmuth

    While the first three chapters gave relatively high-level overviews, we now turn to the computational side of argument mining (AM), where we assume readers to be equipped with a basic background in NLP techniques.

  • Open Access

    Argument Quality Assessment

    by Manfred Stede, Jodi Schneider, Henning Wachsmuth

    In some sense, the question about the quality of an argument is the ‘ultimate’ one for argument mining. Being able to reconstruct argumentative structures from a text (Chaps. 4 – 5 ) and learning about the perspectives that arguments convey toward a topic (Chap. 6 ) lays the ground to make arguments processable by machines. However, nearly all practical applications of NLP research on argumentation require some distinction of good from bad arguments, in order to focus on the strongest arguments or to identify weak arguments. Argument search engines aim to rank the best arguments highest, debating technologies aim to choose arguments that help convince their opponent or audience, argumentative writing assistance tools aim to spot the weak points to give feedback on, and so forth. In this chapter, we therefore discuss how to assess argument quality with computational means.

  • Open Access

    Argument Relation Identification

    by Manfred Stede, Jodi Schneider, Henning Wachsmuth

    Identifying the relations between argument components, the topic of this chapter, becomes relevant when the constellations between the ACs are ambiguous—for example when the same text has more than one claim and several premises that need to be linked to ‘their’ claim. Another constellation is serial argumentation, where a claim is supported by a premise, which in turn is supported by another AC. These situations occur typically in the document- or discourse-based setting of argument mining, which is therefore the primary perspective for the chapter.