Combining Argument Mining Techniques

Proceedings of the 2nd Workshop on Argumentation Mining, pages 127–136, Denver, Colorado, June 4, 2015. c⃝2015 Association for Computational Linguistics Combining Argument Mining Techniques John Lawrence School of Computing University of Dundee UK j.lawrence@dundee.ac.uk Chris Reed School of Computing University of Dundee UK c.a.reed@dundee.ac.uk Abstract In this paper, we look at three different meth- ods of extracting the argumentative structure from a piece of natural language text. These methods cover linguistic features, changes in the topic being discussed and a supervised machine learning approach to identify the components of argumentation schemes, pat- terns of human reasoning which have been detailed extensively in philosophy and psy- chology. For each of these approaches we achieve results comparable to those previously reported, whilst at the same time achieving a more detailed argument structure. Finally, we use the results from these individual tech- niques to apply them in combination, further improving the argument structure identifica- tion. 1 Introduction The continuing growth in the volume of data which we produce has driven efforts to unlock the wealth of information this data contains. Automatic tech- niques such as Opinion Mining and Sentiment Anal- ysis (Liu, 2010) allow us to determine the views expressed in a piece of textual data, for example, whether a product review is positive or negative. Ex- isting techniques struggle, however, to identify more complex structural relationships between concepts. Argument Mining1 is the automatic identification of the argumentative structure contained within a piece of natural language text. By automatically identifying this structure and its associated premises 1Sometimes also referred to as Argumentation Mining and conclusions, we are able to tell not just what views are being expressed, but also why those par- ticular views are held. The desire to achieve this deeper understanding of the views which people express has led to the recent rapid growth in the Argument Mining field (2014 saw the first ACL workshop on the topic in Baltimore2 and meetings dedicated to the topic in both Warsaw3 and Dundee4). A range of techniques have been applied to this problem, including super- vised machine learning (starting with (Moens et al., 2007)) and topic modelling ((Lawrence et al., 2014)) as well as purely linguistic methods (such as (Vil- lalba and Saint-Dizier, 2012)); however, little work has currently been carried out to bring these tech- niques together. In this paper, we look at three individual argu- ment mining approaches. Firstly, we look at us- ing the presence of discourse indicators, linguistic expressions of the relationship between statements, to determine relationships between the propositions in a piece of text. We then move on to look at a topic based approach. Investigating how changes in the topic being discussed relate to the argumenta- tive structure being expressed. Finally, we imple- ment a supervised machine learning approach based on argumentation schemes (Walton et al., 2008), en- abling us to not only identify premises and conclu- sions, but to determine how exactly these argument components are working together. Based on the results from the individual imple- …

Content truncated to 500 words