Despite the central role that argumentation plays in human communication, the computational linguistics community has paid relatively little attention in proposing a methodology for automatically identifying arguments and their relations in texts. Argumentation is intimately related with discourse structure, since an argument often spans more than one phrase, forming thus an entity with its own coherent internal structure. Moreover, arguments are linked between them either with a support, an attack or a rebuttal relation. Those argumentation relations are often realized via a discourse relation. Unfortunately, most of the discourse representation theories use trees in order to represent discourse, a format which is incapable of representing phenomena such as long distance attachments and crossed dependencies which are crucial for argumentation. A notable exception is Segmented Discourse Representation Theory (SDRT) (Asher and Lascarides, 2003). In this paper we show how SDRT can help identify arguments and their relations. We use counter-argumentation as our case study following Apothe´loz (1989) and Amgoud and Prade (2012) showing how the identification of the discourse structure can greatly benefit the identification of the argumentation structure.
in game theoretic terms it is an equilibrium in a
persuasion game in which the addressee adopts an optimal
action based on the conversational history and in which
the arguer adopts her conversational strategy based on
the addressee’s strategy for adopting an action
One domain of research in Computational
Linguistics that is of particular interest for argumentation is
that of discourse. In a typical argumentation process,
which takes the form of a dialogue, every argument
has an internal coherence meaning that it can be
represented by a discourse graph. Moreover arguments are
linked between themselves either with support, attack
or rebuttal relations which are realized once again as
discourse relations linking either the whole discourse
subgraphs representing the arguments or parts of them.
Any attempt to automatically extract the argumentation
structure from a given text cannot afford to ignore
discourse. Our goal in this paper is to show how
argumentation is intimately involved with discourse structure.
We achieve this by using counter-argumentation
(following
The remainder of this paper is structured as follows.
In section 2 we present the current work in the so-called
argumentation mining, the subfield of computational
linguistics that deals with the automatic extraction of
the argumentation structure from texts. In section 3 we
tell a few words on discourse and in section 4 we show
how SDRT (Segmented Discourse Representatuin
Theory,
Despite its general neglect, argumentation has been the focus of some work in Computational Linguistics. Teufel (1999), Teufel and Moens (2002) aim at identifying what they call the argumentative zones of scientific articles. The zones they have used include the aim of the paper, general scientific background, description of the authors’ previous work, comparison with other works, etc. They are using a naive bayes model trying to classify each sentence into one of the predefined categories using mostly surface features (position, length, etc) and whether the sentence contains title words or words scoring high in terms of tf.idf .
Palau and Moens (2009) have recently attempted argumentation mining, or the identification of arguments in a text. They assume that an argument consists of a series of premises and a conclusion. Premises and conclusions are represented by propositions in the text. Of course, not all propositions in a given text are part of an argument. In order to tackle the problem of argumentation mining the authors break it into a series of subtasks. Initially they are interested in performing a binary classification of each proposition into either a proposition participating in an argument or not. Propositions that are positively classified are then sent to a second classifier which determines whether it is a premise or a conclusion. For both classification tasks they use a maximum entropy model and the Araucaria corpus1 as well as a corpus extracted from the european court of human rights. The features they use for the first classifier include surface features ({1, 2, 3}grams, punctuation, sentence and word length), POS information (adverbs, verbs and modal auxiliaries) and syntactic parsing. The second classifier uses again surface features, POS tags for the subject and main verb, simple rhetorical and argumentative patterns as well as the results of the first classifier (although no structured prediction is attempted which would probably be more appropriate, given that the two classifiers are not independent). Of course, once one has identified the propositions that are premises and conclusions, one does not yet have the full arguments. In order to get them, the authors create a simple CFG grammar which tries to get the tree structure of arguments. The authors do not attempt to detect the relations (e.g. support, attack, rebuttal) that connect the arguments between each other.
The Araucaria corpus is used by Feng and Hirst
(2011) as well but their goal is not performing
argumentation mining. Instead they focus on the task
of classifying arguments into argumentation schemes
Cabrio and Villata (2012a; 2012b) take a different stance. Their goal is to use Dung’s (1995) abstract argumentation framework in order to detect a set of accepted arguments from online debates. They extract arguments from Debatopedia2 using textual entailment techniques. More precisely, if a sentence T entails another sentence H then they consider that there is a support relation between the two sentences (and thus points of views) otherwise there is an attack relation. They use the open source software package EDITS3 in order to perform textual entailment. In order then to identify the set of arguments that would be acceptable by a an external observer the authors use Dung’s (1995) abstract argumentation framework. In essence an argument belongs to the aforementioned set if all the arguments attacking it are rejected. An argument is rejected if at least one accepted argument attacks it. 3
The little prior work on argumentation has ignored discourse structure, and we think this is a mistake. A complete discourse structure of a dialogue will determine how each interlocutor’s contribution relates to other contributions, both her own and that of other dialogue participants. This structure already by itself is crucial to determining the structure of an argument—which attacks are directed towards which other contributions. Moreover, an argument is not just a sequence of attacks but a much more complex structure. For one thing, arguments contain support moves as well; a good persuasion strategy is to explain why one’s claims are true, but another is to provide background that will enable the addressee to understand one’s reasons, and yet another is to provide more details about the claims themselves. All of these ”strategies” involve in fact rhetorical moves that are different and that may be appropriate in different situations. A discourse structure makes plain these different types of moves through the use of different discourse relations.
In effect, discourse structure has the promise to give a much more detailed picture of the nature and structure of argumentation. At the moment, we don’t know exactly what that picture is. But by pursuing the analysis of dialogues in terms of argument structure and discourse structure we can find out. 4
To illustrate our point in the previous section, we illustrate how constructed examples of different sorts of 2http://debatepedia.idebate.org 3http://edits.fbk.eu arguments given by Apothe´loz (1989) look from a discourse structure point of view. Apothe´loz (1989) identified four different modes of arguing against a given argument. In this work an argument is simply a pair C(x) : R(y) where R represents the function of reason and x its content and C the function of conclusion and x its content. x and y can be either propositions, conclusions or enthymemes. Given the above, Apothe´loz (1989) distinguishes between four different modes of arguing against a given argument C(x): 1. disputing the plausibility or the truth of a reason, that is the propositions used in y 2. disputing the completeness of the reason 3. disputing the relevance of the reason with respect to the conclusion, and 4. disputing the argumentative orientation of the reason by showing the reason presented is rather in favor of the conclusion’s opposite.
Nonetheless, Apothe´loz (1989) completely ignores the
internal structure that the arguments have. In the
following we analyse the different modes of
counterargumentation that Apothe´loz (1989) provides, giving
examples found in
When one disputes the plausibility of a reason essentially it amounts to proving that the reason is false. Apothe´loz (1989) provides three different ways of showing that; we illustrate them with the following examples. (1) (2)
3 — [Clara will fail her exams.]1 [She did not work hard]2 — [Clara?!]3 [She worked non-stop.]4 (4) 1 2 — [Clara will fail her exams.]1 [She did not work hard]2 2 4 In this example, the second speaker neither affirms neither denies the reason, i.e. the fact that Clara didn’t work hard. Instead, she is ignoring it (manifested by
— [No, she worked hard.]3 [Her eyes have bags underneath them.]4 (3) — [Clara works hard]1 [because she is ambitious.]2 — [It is not out of ambition that Clara works hard.]3 [She is not ambitious.]4 In all three examples, the second speaker does not challenge her interlocutor concerning her conclusion (EDU 1 in all three cases). In fact, in the example (3) the second speaker explicitly acknowledges the content of the conclusion (Acknowledgment(1, 3)). Instead the second speaker’s disagreement is always with the truth value of the reason behind the conclusion. This takes the form of a Correction relation between the first speaker’s EDU representing the reason (EDU 2 in all cases) and the second speaker’s counter-argument (EDU 3 for examples (2) and (3) and CDU π1 for example (1)). For the last two examples the speaker provides additional reason for her beliefs either by means of an Elaboration relation or an Explanation∗ relation. This last relation signals an explanation of why b said that Clara worked hard. It is an explanation of a speech act and provides epistemic grounds for the content of the assertion. Note that in all the above examples the Correction discourse relation amounts to an attack relation.
In the second mode of counter-argumentation that Apothe´loz (1989) has identified, the second speaker does not attack the truthfulness of the reason but rather its completeness. Here are some examples.
— [Clara will fail her exams.]1 [She did not work hard]2 — [Clara will not fail her exams.]3 [She is very smart.]4 1 the fact that no discourse relation exists between EDUs 2 and 3 or 4). Instead she corrects the conclusion of the first speaker by providing more evidence which lead to the contrary. Again, the Correction discourse relation connects two arguments and serves as an attack argumentative relation.
— [Paul is in his office ]1 [because his car is in the carpark.]2 — [But the car is in the carpark]3 [because it has a mechanical problem and is undriveable.]4 π1
In this case both arguments (as before) are thoroughly supported by an Explanation discourse relation. Moreover the second speaker even explicitly agrees with the reason given by the first one (Acknowledgment(2, 3)) but she disagrees with the whole argument (note the Correction relation between the two CDUs) since she judges that the reason is not enough and provides more evidence (EDU 4) to back her disagreement up.
— [This object is red]1 [since it looks red.]2 — [But the object is illuminated by a red light.]3
1 2 Contrast 4 3 1 (8) 1 (9)
2 3 Ack. Here the second speaker acknowledges the reason of the first person, as seen by the discourse relation between EDUs 2 and 3, but then shows that there is a contrast between this and her conclusion, disagreeing thus with the whole argument. It is important to note once again that in this example, as the preceding ones, the discourse analysis enables us to clearly pinpoint which elements of the first argument are accepted and which are attacked by the second speaker.
— [Clara will fail her exams.]1 [She did not work hard]2 — [She will not fail her exams]3 [because she did not work hard,]4 [but rather because of the stress.]5 π1
2 ¬Expl. 4 3
Now, this example is quite more complicated to analyze. There is a contrast between the object’s looking red, which generates the expectation that it is red, and the fact that the object is illuminated by a red light, which would tend to put that expectation in doubt. But putting the expectation into doubt also puts into doubt the causal relation supposed by the first speaker between 1 and 2.
In the third mode of counter-argumentation that Apothe´loz (1989) has identified concerns the second speaker does not attack the truthfulness or the completeness of a reason but instead its relevance. Below are some examples of this mode of counterargumentation. (7) — [Clara will fail her exams.]1 [She did not work hard]2 — [Indeed, she did not work hard,]3 [but not working hard is not a reason to necessarily fail one’s exams.]4 This is a very interesting example. As the discourse analysis shows the undirected cycle that is produced between EDUs 3, 4 and 5 enables the second speaker to explain why she disagrees with the whole of the initial statement.
In the final mode of counter-argumentation that Apothe´loz (1989) has proposed the second speaker does not dispute neither the reason nor the conclusion. Instead she argues that the reason corroborates towards the opposite of the conclusion. This can be illustrated with the following example.
1 — [Running a marathon is exhausting.]1 [The whole body undergoes too much stress.]2 — [That’s precisely what makes it nice!]3
2 3 5
In the previous section we have showed via the use of a case study how the use of a discourse representation theory can help us represent in fine detail the phenomena that take place during argumentation—in this particular case, counter argumentation during a dialogue. In order to represent discourse we have chosen to use the Segmented Discourse Representation Theory (SDRT) of Asher and Lascarides (2003). This choice was made after careful consideration of the phenomena present during argumentation as well as the expressive power of other discourse representation theories.
Take for example the Rhetorical Structure Theory
(RST, Mann and Thompson (1988)), which is the most
widely cited and used discourse representation theory
currently. In RST, as in SDRT, the basic units are the
same, namely EDUs.4 In RST adjacent EDUs can
be linked together with rhetorical relations in order to
form what in RST’s jargon are called spans. Spans
can be linked with rhetorical relations either with other
adjacent EDUs or adjacent spans. We keep on
emphasizing the word “adjacent” since this constitutes in
our opinion (but see also
The second problem that RST has as far as the
representation of argumentative structures is concerned, is
that it cannot correctly represent rebuttals. This is
problem that is also reported by Peldszus and Stede (2013)
so we are using their example, slightly modified in
order to illustrate this point. Consider the following
dialogue:
(10)
— [We should tear the building down.]1 [It is
full of asbestos.]2
— [It is possible to clean it up.]3
— [But that would be forbiddingly
expensive!]4
The argumentation graph that results from this
dialogue, according to the scheme proposed in
4There is a big difference as far as EDUs are concerned between the two theories. In SDRT EDUs can be embedded the one within the other whilst RST does not allow it. 1 2 3 where edges with arrows denote support relations and edges with circles denote undercuts. The RST graph for the above dialogue is the following:
EVIDENCE ✠ EVIDENCE ✠ 1
ANTITHESIS
❘ 2 3 4
As we can see, the structural properties of those two graphs are completely different and the use of RST for argumentative analysis does not seem to be a promising path to follow. On the other hand, SDRT neatly follows the argumentation graph (we have used the box representation of SDRT here) making it thus more appropriate for use in argumentative analysis.
At this point we would like to say a few words on the computational extraction of discourse structures. Most of the published work currently is using the RST framework. This is due to two facts. Firstly there are more annotated data available for RST and secondly the problem is computationally less demanding since decisions are always made locally (attachments can be either left or right of a given span) which renders this framework more simple and thus more attractive to researchers. Of course, this implies that all long distance attachements are completely lost, an aspect which is crucial, as we have seen, for argumentation.
Muller et al. (2012) have recently attempted
extraction of SDRT structures using data from the ANNODIS
corpus
The authors perform structured prediction on the dependency graphs they produced which can be broken down into two steps. Initially they learn local probability distributions for attaching and labeling EDUs, based on naive bayes and logistic regression models. They effectively thus create a complete graph where each node represents an EDU and each arc a probability of attachment. The authors then move on to the decoding phase where the goal is to extract the graph that approaches the reference object. They use two decoding approaches based on A∗ and Maximum Spanning Tree (MST) algorithms.
Closing this paper we would like to state that one of
the main reasons that extraction of argumentative
structures has not been more widely explored by the
computational linguistics community is due to the fact that
few annotated corpora exist. We believe that a project
with the goal of jointly annotating argumentative and
discourse structures is crucial for the advancement of
this field, as well as other fields such as automatic
summarization