Henning Wachsmuth
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:
- Jodi Schneider
Information School, University of Wisconsin-Madison , Madison, WI 53706
11 shared publications Manfred Stede
Universität Potsdam
11 shared publications- Maja Stahl
Leibniz Universität Hannover Hannover Germany
9 shared publications - Martin Potthast
University of Kassel, hessian.AI, and ScaDS.AI, Kassel, Germany
5 shared publications - Timon Ziegenbein
Faculty of Electrical Engineering and Computer Science, Institute of Artificial Intelligence, Leibniz University Hannover, Germany
5 shared publications - Gabriella Skitalinskaya
Institute of Artificial Intelligence Leibniz University Hannover
4 shared publications
Latest Publications
- Open Access
- 18 October 2026
- Published by Springer Nature
- p. 13-32
Argumentative Language
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.
- 18 October 2026
- Published by Springer Nature
- p. 13-32
Open AccessArgumentative Language
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
- 18 October 2026
- Published by Springer Nature
- p. 295-318
Tools & Applications
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.
- 18 October 2026
- Published by Springer Nature
- p. 295-318
Open AccessTools & Applications
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
- 18 October 2026
- Published by Springer Nature
- p. 33-56
Representing Arguments
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 .
- 18 October 2026
- Published by Springer Nature
- p. 33-56
Open AccessRepresenting Arguments
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
- 18 October 2026
- Published by Springer Nature
- p. 219-257
Argument Reasoning
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.
- 18 October 2026
- Published by Springer Nature
- p. 219-257
Open AccessArgument Reasoning
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
- 18 October 2026
- Published by Springer Nature
- p. 1-12
Introduction
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.
- 18 October 2026
- Published by Springer Nature
- p. 1-12
Open AccessIntroduction
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
- 18 October 2026
- Published by Springer Nature
- p. 137-174
Perspective Assessment
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.
- 18 October 2026
- Published by Springer Nature
- p. 137-174
Open AccessPerspective Assessment
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
- 18 October 2026
- Published by Springer Nature
- p. 259-293
Argument Generation
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 .
- 18 October 2026
- Published by Springer Nature
- p. 259-293
Open AccessArgument Generation
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
- 18 October 2026
- Published by Springer Nature
- p. 57-99
Argument Unit Identification
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.
- 18 October 2026
- Published by Springer Nature
- p. 57-99
Open AccessArgument Unit Identification
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
- 18 October 2026
- Published by Springer Nature
- p. 175-217
Argument Quality Assessment
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.
- 18 October 2026
- Published by Springer Nature
- p. 175-217
Open AccessArgument Quality Assessment
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
- 18 October 2026
- Published by Springer Nature
- p. 101-136
Argument Relation Identification
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.
- 18 October 2026
- Published by Springer Nature
- p. 101-136
Open AccessArgument Relation Identification
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.