How Are the Members of a Parliament Arguing? Analysis of an

Argument Corpus

Mare Koit

Institute of Computer Science, University of Tartu, Narva mnt 18, Tartu, Estonia

Keywords: Argument, Inter-argument Relations, Argument Diagramming, Language Features, Annotated Corpus.

Abstract: Estonian argument corpus includes verbatim records (in Estonian) of sessions held in the Parliament of

Estonia (Riigikogu). Arguments used in negotiation and inter-argument relations are annotated in the corpus.

Every argument consists of one or more premises, and a claim. By using the corpus, inter-argument relations

(rebuttal, attack, and support), argument diagramming (argument structures – basic, convergent, serial,

divergent, and linked), and the linguistic features of the arguments are studied. Some problems are discussed

in relation to the arguments the members of Riigikogu use when negotiating. Our aim is to add an additional

layer to our argument corpus by annotating the structures of arguments as well as extending the corpus in

order to make it possible the automatic recognition of arguments in Estonian political texts. A further

challenge will be the comparison of discussions in Riigikogu with other parliaments and other languages.

1 INTRODUCTION

There are many ongoing initiatives for compiling

digital collections of parliament data (CLARIN

Survey, 2020). The data can be used for linguistic,

political, sociological, historical etc. research. The

data also makes it possible to compare discussions in

different parliaments.

A lot of work has been done when studying

political discourse and argumentation in political

discussions (Bara et al., 2007; Naderi and Hirst, 2015;

Petukhova et al., 2015; Lippi and Torroni, 2016). The

review of Atkinson et al. (2015) considers the

development of artiﬁcial tools that capture the human

ability to argue. Such systems can be used when

modelling political argumentation being able

automatically extract arguments and relations

between them.

We study negotiations on motions in the

Parliament of Estonia (Riigikogu) by using an

annotated argument corpus. The corpus currently

includes a part of verbatim records (in Estonian) of

sittings of the Riigikogu. The records are accessible

on the web as pdf files (cf. Riigikogu). In the records,

repetitions and disﬂuencies are omitted, while

supplementary information such as speaker names are

https://orcid.org/0000-0002-7318-087X

added. In the corpus, argument components (premises

and claims) and inter-argument relations (rebuttal,

attack, support) are annotated. The first attempt to

analyze and model the formal structure and relations

of arguments in Estonian political discourse is made

in (Koit, 2020a). Based on the study, an argument

corpus is being developed. The current paper

considers the arguments presented by the Members of

the Parliament (MPs) in negotiation when passing an

act. Our aim is to demonstrate how the corpus can be

used for the analysis of parliamentary negotiations.

The corpus has to be extended in order to make it

possible the automatic recognition of arguments as

well as further analysis of political discussions.

The remainder of the paper is structured as

follows. Section 2 describes related work. In Section

3, we examine one randomly selected discussion in

Riigikogu by using the argument corpus. We consider

the arguments presented by the MPs – do they support

or attack the bill or some amendments, the structure

of arguments and their linguistic features. Section 4

discusses problems related to the arguments – how

are they used in negotiation, how are they built up, do

they support or attack previous arguments, how do

they characterize the MPs participating in

negotiation. Section 5 draws conclusions and figures

out future work.

1046

Koit, M.

How Are the Members of a Parliament Arguing? Analysis of an Argument Corpus.

DOI: 10.5220/0010314910461053

In Proceedings of the 13th International Conference on Agents and Artiﬁcial Intelligence (ICAART 2021) - Volume 2, pages 1046-1053

ISBN: 978-989-758-484-8

2 RELATED WORK

Stab and Gurevych (2014) introduce an argument

corpus that includes 90 persuasive essays in English.

The corpus has been annotated in two consecutive

steps. First, the annotators identiﬁed argument

components (claims and premises) at the clause level.

Second, they annotated argumentative support and

attack relations between argument components.

Amgoud et al. (2015) propose a formal language

for representing arguments encountered in natural

language, and demonstrate that it is possible to

represent rebut, attack and support relations between

arguments as formulas of the same language.

Visser et al. (2018) present a corpus comprising

the first general election debate between Clinton and

Trump (17,190 words) annotated with types of

argument. They use the Periodic Table of Arguments

classification that is based on three discriminating

properties: first- or second-order arguments;

predicate or subject arguments; propositions of fact,

value or policy (Wagemans, 2016).

Haddadan et al. (2018) present the annotation

guidelines for annotating arguments in political

debates. The dataset is taken from the Commission on

Presidential Debates website.

Menini et al. (2018) apply argumentation mining

techniques, to study political speeches where there is

no direct interaction between opponents. They use a

tool called OVA+ (Janier et al., 2014), an on-line

interface for the manual analysis of natural language

arguments.

Musi et al. (2018) present a multi-layer annotated

corpus of 112 argumentative micro-texts

encompassing not only argument structure and

discourse relations (Stede et al., 2016), but also

argument schemes – the inferential relations linking

premises to claims. They propose a set of guidelines

for the annotation of argument schemes both for

support and attack relations. They have built the

ArgScheme Annotator Tool, which provides a user-

friendly interface for the labelling of support and

attack relations with argument schemes.

Stab and Gurevych (2017) and Lawrence and

Reed (2019) consider argument diagramming which

aims at transferring natural language arguments into

a structured representation. An argument diagram

(argument structure) is a node-link diagram whereby

each node represents an argument component (i.e., a

statement of natural language) and each link

represents a directed argumentative relation

indicating that the source component is a justiﬁcation

of the target component. There are different types of

argument diagrams (Stab and Gurevych, 2017:626).

A basic argument, the minimal form of an argument,

includes a claim supported by a single premise. In a

convergent argument, multiple premises are used to

independently support a single conclusion. In a linked

argument, multiple premises work together to support

a conclusion, each premise requires the others in

order to work fully. In a divergent argument, the same

premise supports multiple conclusions. In a

sequential (serial) argument, one premise leads to

another and this, in turn, leads to the conclusion.

More complicated, hybrid arguments, involve several

combinations of the above elements into a larger

argument structure.

Argument structures can be used to characterize a

convincing argumentation. For example, Indrajani

and Anggie (2009) examine the argument structures

used by Hillary Clinton in her presidential debate.

The linked arguments were the most frequent while

the divergent ones were the rarest. Therefore, the

linked argument structure turned out to be the most

effective strategy for the speaker when arguing about

the political, economic, and social issues.

Voloshchuk and Usyk (2018) analyse the power

of persuasion in argumentative political discourse.

Argumentation is aimed at achieving the ultimate

communicative goal – to persuade the audience in the

truthfulness of a certain thought, and it can be

fulfilled by different means. In simple argumentation,

the main reasoning relies on one argument. On the

other hand, compound argumentation uses several

arguments, and main reasons are supported by several

facts or examples that validate the speaker’s goal.

Persuasion verbalizes in speeches, the speaker

realizes oneself as a communicative individuality

with own style – the stylistic and semantic

composition of the speech.

Calegari and Sartor (2020) provide a formal

model for the burden of persuasion in legal

proceedings. The burden of persuasion indicates that

it is necessary to give a dialectically convincing

argument to establish a claim. In order to be

convincing, the argument must prevail over all

counter-arguments that are non-rejected on other

grounds.

Quijano-Sánchez and Cantador (2020) propose an

extension of an argumentative model. Their new

generic model considers argument structures with

different semantic components and relationships. A

case study is carried out on contents of the Spanish

Parliament demonstrating how to extract structured

arguments from texts.

How Are the Members of a Parliament Arguing? Analysis of an Argument Corpus

1047

3 ARGUMENTS PRESENTED IN

NEGOTIATION

In this paper, we are analysing the verbatim records

of discussions held in the Parliament of Estonia, in

order to figure out which arguments and in which way

are presented by the MPs in negotiation. We are using

an annotated argument corpus.

3.1 Empirical Material

Our study is based on the Estonian argument corpus.

The corpus currently includes verbatim records of the

proceedings on seven bills in the Riigikogu (social

care, animal protection, etc.). In the corpus,

arguments and inter-argument relations are annotated

(Koit, 2020b). For the current study, we have

randomly chosen the bill on (sale and consumption

of) alcohol proceeded in 2001. The records of the

three sittings include 27,768 running words in total.

The passing of acts and resolutions is an important

task of the Riigikogu. A draft act (a bill) initiated by

the government will pass three readings in the

Riigikogu, during which it is refined and amended.

The proceeding of a bill is managed by the relevant

leading committee. After having been passed by the

Riigikogu, the act is sent to the President of the

Republic for proclamation, and is then published in

State Gazette. The readings have a predetermined

structure (cf. Koit et al., 2019). Every reading

includes negotiation. The procedure of a negotiation

follows the definite rules. If a speech of an MP is

made from the rostrum, it may last 5+3 minutes,

according to the agreement with the chair of the

sitting. A speech made from the seat of the MP in the

Hall may take up to 2 minutes. In any case, MPs have

only limited time to present their arguments when

negotiating.

3.2 Arguments for and against the Bill

An argument is a series of statements in a natural

language, called the premises, intended to determine

the degree of truth of another statement – the claim.

Three types of relations can appear between the

arguments: attack, support, and rebuttal (Amgoud et

al., 2015). Although Stab and Gurevich (2014)

differently determine support and attack relations –

between two statements (premises or claims of

arguments) – we are departing from (Amgoud et al.,

2015).

When analysing persuading essays, Stab and

Gurevych (2014) make a distinction between the

main claim and a claim of an argument. In

parliamentary discussions, we similarly can

differentiate the main claim and a claim of an

arbitrary argument. The main claim together with its

premises is given in the introductory report of

Minister in the beginning of the first sitting and it is

always ‘to accept the bill’. Therefore, we can consider

set of the statements in the report as ‘the main

argument’. As a rule, the claim of a supporting

argument presented in following negotiation,

coincides with the main claim. The claim of a

rebutting argument is opposite: do not accept the bill.

The claim of an attacking argument depends on a

previous argument that is under attack.

In total, 35 arguments are presented by 12 MPs in

negotiations when proceeding the bill on alcohol. The

components of the arguments occur in the order either

‘premise(s)-claim’ or ‘claim-premise(s)’. In average,

an MP presents 2-4 supporting or attacking arguments

in a speech. Only two MPs limit themselves with one

argument, both rebutting the main argument

(Example 1). The arguments are annotated following

(Koit, 2020b).

(1) <argument>

- - rebutting the main argument

Täielikult puudub seaduseelnõus sotsiaalne

dimensioon. The social dimension is fully missing in

the bill.

</premise>

<claim>Seaduse vastuvõtmisega sel kujul

näitame oma rahulolevat suhtumist sellesse, et meil

alkoholi palju tarbitakse […] If we approve the bill in

the present form then we express our satisfaction with

the high consumption of alcohol […]

</claim>

</argument>

An argument can attack another argument or its

premise (Example 2).

(2) <argument>

-- attacking a premise of the main argument

[…] ma ei ole nõus sõnastusega, et alkohol on

toidugrupp või kuulub toidugruppi […] I don’t agree

with the definition of alcohol as a food group […]

</claim>

See on kindlasti eksitav […] This is definitely

misleading […]

</premise>

ICAART 2021 - 13th International Conference on Agents and Artiﬁcial Intelligence

1048

[…] On selge, et siin on tegemist alkoholiäriga,

[…] It is clear that this is the alcohol business […]

</premise>

</argument>

An argument can also support a premise or a claim of

another argument (Example 3).

(3) <argument>

-- supporting the claim of another argument

[…] alkohol on bioloogilist sõltuvust tekitav aine.

Alcohol causes biological dependency.

</premise>

<claim>

Just see on minu jaoks ka ainus põhjendus, miks

võiks alkoholi hakata müüma alles alates 21.

eluaastast […] This is the only reason to sell it from

age of 21 years. […]

</claim>

</argument>

Most (66%) of the arguments are related to

amendments (which texts are unfortunately not

accessible on the web). In negotiation, MPs support

the amendments earlier made by themselves. They

also attack some amendments made by the other MPs.

Figure 1: Distribution of inter-argument relations.

However, an argument can support a (premise or

claim of) previous argument and at the same time,

attack another argument or its premise. Arguments

given for an amendment, at the same time, attack one

of the premises of the main argument presented in the

report of Minister in the beginning of the first sitting.

The distribution of inter-argument relations is

shown in Fig. 1.

3.3 Argument Diagramming

When taking the floor in negotiation, the members of

the Riigikogu are mostly presenting their arguments

by more than one sentence. In this case, a premise and

the claim are located in different sentences. There are

also some complex, nested arguments where one

argument is a premise or a claim of another (cf.

Amgoud et al., 2015). A speech of an MP always

includes also a non-argumentative part that can be

longer than its argumentative part.

In more than half cases (54%), an argument has

only one premise and one claim, i.e. its structure

(diagram) is basic like in Examples 1 and 3 (cf. Stab

and Gurevych, 2017:626).

The next most frequent (29%) structure is

convergent where the argument has more than one

premise that independently support the claim

(Example 2). In a few of cases, there are arguments

with two or more premises that work together to

support a claim (i.e. linked arguments, Example 4).

(4) <argument>

-- supporting the claim of another argument

Paljudes riikides, sealhulgas USA-s, on

alkohoolsete jookide, ka õlle tarbimine lubatud alates

21. eluaastast […] In many countries, among them in

USA, consumption of alcohol, including beer, is

allowed from age of 20 years […]

</premise>

Selline piirang ei diskrimineeri neid noori

kodanikke, kes ei saa 18-20aasta vanusena alkoholi

osta [..] Such a limitation does not discriminate the

young citizens who can’t buy alcohol being 18-20

years old […]

</premise>

Seevastu on alkoholiga seotud noorte

surmajuhtumeid Ühendriikides üle viie korra

harvemini kui Eestis. The number of deaths of young

men is more than five times lower than in Estonia.

</premise>

<claim>

Alkoholimüüki tuleks piirata nii vanuselises ja

asukohalises mõttes kui ka kellaajaliselt. The sale of

alcohol has to be limited depending on age, place and

time.

</claim>

</argument>

There are also some hybrid arguments that

involve several combinations of simpler arguments

into a larger argument structure. One MP especially

distinguishes himself by his complicated arguments

(Example 5).

(5) <argument>

-- supporting the claim of another argument

-- rebutting an argument

How Are the Members of a Parliament Arguing? Analysis of an Argument Corpus

1049

Kindlasti leidub neid, kes väidavad, et karmim

keelupoliitika ei lahenda probleeme. Definitely, there

are people who claim that a stronger prohibitive

policy does not solve the problems.

</premise>

<claim>

Ma ei nõustu sellega. I don’t agree.

</claim>

</argument>

</premise>

Seadusega kehtestatavad rangemad reeglid on

ainult üks osa paljudest abinõudest eesmärgi

saavutamisel. Stronger rules sanctioned by law are

only one part of many instruments to achieve the goal.

</premise>

Eestis on seni alkoholipoliitika puudunud, […]

Alcohol policy is missing in Estonia so far, […]

</premise>

<claim>

-- rebutting the main argument

Küsime: kas käesolev seaduseelnõu proovib neid

küsimusi lahendada? We ask: will the current bill

solve the problems?

</premise>

<claim>

Arvan, et mitte. I guess that not.

</claim>

</argument>

</claim>

</argument>

The argument (5) has three premises. Among

them, the first one is another argument. The claim is

also presented as another argument. This hybrid

argument includes linked and basic argument

structures inside. Let us mention that, in fact, there

would be different options to annotate the argument

(5), e.g. annotate the first premise as a divergent

argument with two claims. Still, we are departing

from the current annotation of the corpus.

Divergent arguments have not been used by MPs

when proceeding the bill on alcohol (according to our

corpus).

The distribution of argument structures is shown

in Fig. 2.

Figure 2: Distribution of argument structures.

3.4 Linguistic Features of Arguments

Some of the MPs (especially women) use figurative

language (e.g. an emotional claim in Example 6).

(6) Aga kas selle eest peaks siis risti lööma ainult

putkad ja bensiinijaamad, kas nemad on siis Jeesus

Kristuse rollis, kes kogu alkoholi õuduse ja patu

peavad kinni maksma? But should we only crucify

booths and service stations, do they have the role of

Saviour who buys out the horror and enormity of

alcohol?

Some MPs tend to prefer special voice and mood

in their arguments (cf. Abbott et al. 2016; Examples

6 and 7).

(7) <argument>

-- supporting an amendment

Kui riik siiski tahaks osaleda alkoholiturul

alkoholi kättesaadavuse ja tarbimise reguleerimisel, If

the state aims to participate in the alcohol market in

order to regulate the availability and consumption of

alcohol

</premise>

siis then

<claim>

võiks riik astuda uue sammu ja naasta alkoholi

tootmise ja alkoholikaubanduse turule eesmärgiga

turgu tasakaalustada. the state will take the new step

and return to the market of alcohol production and

alcohol business with the goal to balance the market.

</claim>

</argument>

Some speeches are ironic or sarcastic (an ironic

claim in Example 8).

(8) See seadus on väga hea alkoholiäri seadus.

This law is very good just for alcohol business.

ICAART 2021 - 13th International Conference on Agents and Artiﬁcial Intelligence

1050

However, these features have been found only in

a few of the speeches and they do not characterize the

majority of the MPs.

4 DISCUSSION

The paper describes an experience of analysing

arguments in Estonian parliamentary discourse in

order to explain how the MPs use arguments in

negotiation. The empirical material is formed by the

corpus that includes verbatim records of sittings held

in the Riigikogu. The components of arguments

(premises and claims) and inter-argument relations

(attack, support, and rebuttal) are annotated in the

corpus.

As an example, proceedings on the bill of alcohol

are considered. The discussions in the Riigikogu have

been intensive, the total number of questions asked

after reports presented by the representatives of the

government (Minister) and the leading committee is

81. The amendments were presented in written form,

in the breaks between the sittings, their number is 97.

However, only 39 of them were approved by the MPs

after voting. In total, 35 arguments have been

presented by 12 MPs in negotiations on the general

principles of the bill and the amendments.

Relations (rebuttal, attack, support) between the

arguments make it possible to figure out the progress

of the negotiation. It curiously starts with an argument

rebutting the main argument. After that, a lot of

arguments are presented to support or attack some

amendments. At the same time, they attack or support

some premises of the main argument, respectively.

Between these arguments, a few of arguments are

presented to attack the main argument or on the

opposite, to support the main claim (‘to adopt the

act’). At the end of the negotiation, arguments

presented by two MPs, rebut the main argument

and/or attack different amendments. Nevertheless,

the arguments supporting the bill seem to prevail over

the counterarguments (by their weightiness, not the

number) and the debate ends after voting with

adopting the act.

Considering the structure (diagrams) of the

arguments, we can conclude that the MPs give

preference to the simplest, basic arguments. Such an

argument seems to be the strongest to transfer the

message expressing the relation between a premise

and a claim. Using an argument corpus it is easy to

label basic arguments as structures with one premise

and one claim. On the other hand, the automatic

distinction between convergent and linked structures

is problematic – how to decide whether two premises

of an argument are independent or not? What is more,

the question of whether to distinguish between linked

and convergent arguments is still debated in

argumentation theory (Stab and Gurevych, 2017).

What next, we do not find serial arguments in our

corpus. If s1 implies s2 and s2 implies s3 then it is

annotated as a complex (hybrid) argument. The

premise of the hybrid argument is another argument

(with premise s1 and claim s2) and the claim is s3.

The MPs only use hybrid arguments in three cases.

Doubtless, these arguments are not easy to

understand. Divergent arguments are also missing in

our annotated corpus. However, we do not exclude

the arguments where one premise implies two

different claims. It should be mentioned that Amgoud

et al. (2015) consider such cases as two separate

arguments (differently from Stab and Gurevych,

2017).

Language features mark off some MPs who

decline to use figurative language, prefer special

voice and mood when arguing. Still, majority of the

MPs does not distinguish oneself by the language

usage.

Our current aim is to add labels of structures

(basic, convergent, etc.) to the arguments, i.e. an

additional layer to our annotated argument corpus.

What next, we can study whether are there differences

between the usage of supporting, attacking and

rebutting arguments by MPs, depending on the final

result of voting on the bill. To characterize the MPs

by their used arguments (incl. the structures and

language features) we need to study different

proceedings because according to regulations, every

MP is allowed to take a floor only once in one

negotiation. This requests extending of the corpus in

order to make a step toward the automatic recognition

of arguments.

An interesting further research question is

whether there are differences in political

argumentation between the Estonian Parliament and

other parliaments, i.e. the comparison of different

political cultures in different languages. Another

challenge will be the development of a tool that helps

young politicians to carry out effective negotiation in

Estonian.

5 CONCLUSIONS

Verbatim records of sittings of the Parliament of

Estonia can be accessed online. A corpus is being

developed where arguments used in negotiation when

proceeding a bill are annotated. For the current study,

an act on alcohol is chosen as an example. Argument

How Are the Members of a Parliament Arguing? Analysis of an Argument Corpus

1051

components (premises and claims) and inter-

argument relations (rebuttal, attack and support) as

well as their linguistic form are considered. The

members of the Parliament use various means to

transfer their messages when arguing, incl. arguments

with one or more premises (basic, linked,

convergent), nested (hybrid) arguments, figurative

language for expressing emotions, etc.

The current aim has been to demonstrate how an

annotated argument corpus can be used for

characterizing the members of a parliament in the

process of adopting a bill. This study is a step towards

the automatic analysis of political arguments in

Estonian parliamentary discussions. The automatic

recognition of arguments in Estonian parliamentary

discourse and comparison with other parliaments

remains for the further work.

ACKNOWLEDGEMENTS

This work was supported by the European Union

through the European Regional Development Fund

(Centre of Excellence in Estonian Studies).

REFERENCES

Abbott, R., Ecker, B., Anand, P., and Walker. M.A., 2016.

Internet Argument Corpus 2.0: An SQL schema for

Dialogic Social Media and the Corpora to go with it. In

Proceedings of LREC, 4445-4452.

Amgoud, L., Besnard, P., Hunter, A., 2015. Logical

Representation and Analysis for RC-Arguments. In

IEEE 27th International Conference on Tools with

Artificial Intelligence (ICTAI), 104–110.

Atkinson, K., Baroni, P., Giacomin, M., Hunter, A.,

Prakken, H., Reed, C., Simari, G., Thimm, M., Villata,

S., 2017. Towards Artiﬁcial Argumentation. In AI

Magazine, 38(3). https://doi.org/10.1609/aimag.v38i3.-

2704

Bara, J., Weale, A., Bicquelet, A., 2007. Analysing

Parliamentary Debate with Computer Assistance. In

Swiss Political Science Review 13(4): 577–605.

Calegari, R., Sartor, G. 2020. A Model for the Burden of

Persuasion in Argumentation. In Proceedings of the

36th International Conference on Logic Programming

(Technical Communications), EPTCS 325, 151–163.

https://doi.org/10.4204/EPTCS.325.21

CLARIN Survey, 2020. https://www.clarin.eu/resource-

families/parliamentary-corpora

Haddadan, S., Cabrio, E., Serena Villata, S., 2018.

Annotation of Argument Components in Political

Debates Data. In Proceedings of the Workshop on

Annotation in Digital Humanities, 12–16.

Indrajani, N. T., Anggie, A., 2009. The Types of Argument

Structure Used by Hillary Clinton in the CNN

Democratic Presidential Debate. In k@ta lama, vol

11(2), 184–200. https://doi.org/10.9744/kata.11.2.184-

200

Janier, M., Lawrence, J., Reed, C., 2014. OVA+: An

Argument Analysis Interface. In Frontiers in Artificial

Intelligence and Applications, vol, 266, 463-464.

https://doi.org/10.3233/978-1-61499-436-7-463

Koit, M. 2020a. Arguments in Parliamentary Negotiation:

a Study of Verbatim Records. In Proceedings of the

12th International Conference on Agents and Artificial

Intelligence ICAART-2020, vol. 2, 822−828.

Koit, M. 2020b. Annotating Arguments in a Parliamentary

Corpus: An Experience. In Proceedings of the 12th

International Joint Conference on Knowledge

Discovery, Knowledge Engineering and Knowledge

Management (IC3K 2020), vol. 2: KEOD, 213−218.

Koit, M., Õim, H., Roosmaa, T., 2019. How Do the

Members of a Parliament Negotiate? Analysing

Verbatim Records. In Proceedings of the 11th

International Joint Conference on Knowledge

Discovery, Knowledge Engineering and Knowledge

Management (IC3K 2019), vol. 2: KEOD, 329−335.

Lawrence, J., Reed, C., 2019. Argument Mining: A Survey.

In Computational Linguistics, vol. 45 (4), 765–818.

https://doi.org/10.1162/COLI.a.00364

Lippi, M., Torroni, P., 2016. Argument mining from

speech: detecting claims in political debates. In

Proceedings of the Thirtieth AAAI Conference on

Artiﬁcial Intelligence (AAAI’16), 2979-2985. AAAI

Press

Menini, S., Cabrio, E., Tonelli, S., and Villata, S., 2018.

Never retreat, never retract: Argumentation analysis for

political speeches. In The Thirty-Second AAAI

Conference on Artificial Intelligence (AAAI-18), 4889-

4896.

Musi, E., Alhindi, T., Stede, M., Kriese, L., Muresan, S.,

Rocci, A., 2018. A Multi-layer Annotated Corpus of

Argumentative Text: From Argument Schemes to

Discourse Relations. In Proceedings of LREC 2018,

1629–1636. https://www.aclweb.org/anthology/L18-

1258.pdf

Naderi, N., Hirst, G. 2015. Argumentation mining in

parliamentary discourse. In CMNA 2015, IWEC 2015,

IWEC 2014: Principles and Practice of Multi-Agent

Systems, 16-25.

Petukhova, V., Malchanau, A., Bunt, H., 2015. Modelling

argumentative behaviour in parliamentary debates: data

collection, analysis and test case. In Principles and

Practice of Multi-Agent Systems. CMNA 2015, IWEC

2015, IWEC 2014. Lecture Notes in Computer Science,

vol 9935. Springer, Cham. https://doi.org/10.1007/978-

3-319-46218-9_3

Quijano-Sánchez, L., Cantador, I., 2020. Structured

argumentation modeling and extraction: Understanding

the semantics of parliamentary content. In Proceedings

of the Joint Conference of the Information Retrieval

Communities in Europe (CIRCLE 2020). http://ceur-

ws.org/Vol-2621/

ICAART 2021 - 13th International Conference on Agents and Artiﬁcial Intelligence

1052

Riigikogu (Parliament of Estonia) https://www.riigikogu.-

ee/en/

Stab, C. and Gurevych, I., 2017. Parsing Argumentation

Structures in Persuasive Essays. In 1636., vol. 43 (3),

619–659. https://doi.org/10.1162/COLI.a.00295

Stab, C., Gurevych, I., 2014. Annotating Argument

Components and Relations in Persuasive Essays. In

Proceedings of COLING 2014, the 25th International

Conference on Computational Linguistics: Technical

Papers, 1501–1510, Dublin, Ireland.

Stede, M., Afantenos, S. D., Peldszus, A., Asher, N., Perret,

J., 2016. Parallel discourse annotations on a corpus of

short texts. In Proceedings of LREC 2016, 1051–1058.

https://www.aclweb.org/anthology/L16-1167.pdf

Visser, J., Lawrence, J., Wagemans, J., and Reed, C., 2018.

An annotated corpus of argument schemes in US

election debates. In 9th Conference of the International

Society for the Study of Argumentation (ISSA), 1101–

1111.

Voloshchuk, I., Usyk, G., 2018. Argumentation in Political

Discourse: Semantic, Composition and Stylistic

8(2):223–232.

Wagemans, J. H. M., 2016. Constructing a Periodic Table

of Arguments. In P. Bondy & L. Benacquista (Eds.),

Argumentation, Objectivity, and Bias: Proceedings of

the 11th international conference of the Ontario society

for the study of argumentation (OSSA), 1–12.

How Are the Members of a Parliament Arguing? Analysis of an Argument Corpus

1053