Comparing Arguments in Discussions of Two Parliaments

Mare Koit

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

Keywords: Argument, Parliament, Comparison, Argument Structure, Inter-argument Relations, Annotated Corpus.

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

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

By using the corpus, argument structures (basic, convergent, divergent, linked, and hybrid) and inter-argument

relations (rebuttal, attack, and support) are studied. For comparison, a discussion in the UK Parliament House

of Commons is analysed. Similarities and differences are considered between arguments of both parliaments.

Our further aim is extending the corpus in order to make it possible the automatic recognition of arguments

in Estonian political texts and comparison of discussions in the Riigikogu with other parliaments and other

languages.

1 INTRODUCTION

Verbatim records of sittings of many parliaments can

be accessed online. The CLARIN ERIC infrastructure

offers access to 27 parliamentary corpora

(Parliamentary corpora, 2022). The first stage of the

ParlaMint project has produced freely available

comparable and interoperable corpora of 17 European

parliaments with almost half a billion words

(ParlaMint, 2022). The corpora are uniformly

encoded, structured and supplied with metadata about

11 thousand speakers, and are linguistically annotated

following the Universal Dependencies formalism and

with named entities. The corpora have already been

used in several studies, incl. the 2021 Helsinki Digital

Humanities Hackathon (Erjavec et al., 2022). There,

the research questions focused on the identification of

differences and similarities in parliamentary debates

on the COVID pandemic in four countries (Calabretta

et al., 2021).

The parliamentary data allows compare

proceeding on bills in different parliaments and can

be used for linguistic, political, sociological,

historical etc. research. Discussions in parliaments

include numerous arguments.

Therefore, in the first part of the paper, we analyse

discussions on motions in the Parliament of Estonia

(Riigikogu) by using an annotated argument corpus.

The corpus currently includes a part of verbatim

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

records (in Estonian) of sittings in the Riigikogu (cf.

Riigikogu, 2022). In the corpus, argument

components (premises and claims) and inter-

argument relations (rebuttal, attack, and 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, 2020).

The current paper considers the arguments presented

by the Members of the Parliament (MPs) when

passing an act. In the second part of the paper, we

compare our parliamentary discussions with the UK

Parliament House of Commons. The aim is to

demonstrate how the annotated corpora can be used

for the analysis and comparison of parliamentary

discussions.

The remainder of the paper is structured as

follows. Section 2 describes related work. In Section

3, we examine a discussion in the Riigikogu by using

the annotated argument corpus. We consider the

arguments presented by the MPs – the structure of

arguments and do they support or attack the bill or its

amendments. In Section 4, we consider a discussion

in the UK Parliament in order to compare the

structure of arguments and inter-argument relations

with the Riigikogu. In Section 5, we discuss the

similarities and differences between the arguments in

both parliaments. Section 6 draws conclusions and

figures out future work. Our further aim is to make it

possible to automatically analyze Estonian

156

Koit, M.

Comparing Arguments in Discussions of Two Parliaments.

DOI: 10.5220/0011539400003335

In Proceedings of the 14th Inter national Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2022) - Volume 2: KEOD, pages 156-164

ISBN: 978-989-758-614-9; ISSN: 2184-3228

parliamentary discourse and compare it with other

parliaments.

2 RELATED WORK

Argumentation in political discussions is studied in

many works (Bara et al., 2007; Stab and Gurevych,

2014; Naderi and Hirst, 2015; Petukhova et al., 2015;

Atkinson et al., 2015).

Amgoud et al. (2015) propose a formal language

for representing arguments occurring in natural

language, and demonstrate that it is possible to

represent rebut, attack and support relations between

arguments as formulas of the same language.

Lippi and Torroni (2016) study whether vocal

features of speech can improve the automatic

extraction of arguments from text. They develop a

machine learning classiﬁer and train it on an original

dataset based on the 2015 UK political elections

debate.

Stab and Gurevych (2017) introduce a corpus of

402 persuasive essays annotated with discourse-level

argumentation structures. Three annotators

independently annotated a random subset of 80

essays. The remaining essays were annotated by the

expert annotator. The annotation scheme models the

argumentation structure of a document as a connected

tree.

Petukhova et al. (2018) describe the Metalogue

Debate Trainee Corpus. A debate is a communication

process in which participants argue for or against a

certain position proposed for the dispute. In the

training scenario, each debate session is motivated by

a motion – new law proposal or changes to an existing

law. The actual debate training session starts by the

Proponent presenting the motion and an argument in

favor of it. An argument is deﬁned as consisting of a

statement that can be supported by evidence. A

statement (claim) is an assertion that deserves

attention. There may be a conclusion which presents

a result, which can be derived from certain evidence

(premises). The task of the Opponent is to attack the

proponent’s argument. Both trainees can be in the role

of either a proponent or opponent.

Haddadan et al. (2018) present the annotation

guidelines for annotating arguments in political

debates. The dataset is taken from the U.S.

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.

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

linked argument, multiple premises work together to

support a conclusion, each premise requires the others

in order to work fully. In a convergent argument,

multiple premises are used to independently support

a single conclusion. 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.

Calegari and Sartor (2020) are modelling 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.

Navaretta and Hansen (2020) consider

differences in the word use of two left-winged and

two right-winged Danish parties and study how these

differences can be used to automatically identify the

party of politicians from their speeches. The analysis

shows that the most frequently occurring lemmas

reﬂect either the ideology or the position of the

parties.

Ruiz-Dolz et al. (2021) present a large, richly

annotated debate corpus VivesDebate. The corpus has

been created from the transcripts of 29 complete

competitive debates in Catalan and includes 139,756

words. The annotation contains argumentative

propositions, argumentative relations, debate

Comparing Arguments in Discussions of Two Parliaments

157

interactions and professional evaluations of the

arguments and argumentation.

This article studies discussions in two parliaments

in order to identify arguments and relations between

arguments. An annotated corpus of Estonian

Parliament discussions is introduced and compared

with the corpus of UK Parliament debates. We aim at

demonstrating how the annotated corpora can be used

for comparisons.

3 ARGUMENTS PRESENTED IN

THE PARLIAMENT OF

ESTONIA

Let us start with the analysis of discussions held in the

Parliament of Estonia, in order to figure out how the

arguments are used in discussions.

3.1 Empirical Material

Our empirical material comes from the Estonian

argument corpus. The corpus currently includes

verbatim records of the proceedings on seven bills in

the Riigikogu (social care, animal protection, etc.).

Arguments and inter-argument relations are

annotated in the corpus (Koit, 2020).

The passing of acts and resolutions is an important

task of the Riigikogu. A bill initiated by the

government will pass three readings, during which it

is refined and amended. The proceeding of a bill is

managed by the relevant leading committee. The

proceedings have predetermined structure (Figure 1).

First, the representatives of the government and the

leading committee make their reports about the bill

and/or its amendments. After every presentation, MPs

can ask questions which will be answered by the

presenter. Then negotiation follows where arguments

for and against the bill and its amendments are given.

Arguments can be presented also in reports and when

asking and answering questions. The 2

and 3

readings in addition include voting on amendments

and final voting, respectively.

As an example, let us consider the bill on sale and

consumption of alcohol proceeded in 2001. The

records of three sittings consist of 27,768 tokens in

total.

3.2 Argument Structures

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.

- - 1

reading

Presenter (Minister): Report

{

MP: question

Presenter: answer

}

Co-presenter (Head of leading committee):

Report

{

MP: question

Co-presenter: answer

}

- - negotiation

{

MP: argument

}

- - 2

reading

Presenter (Head of leading committee): Report

on amendments

{

MP: question

Presenter: answer

}

- - negotiation

{

MP: argument

}

voting on amendment motions

- - 3

reading

- - negotiation

{

MP: argument

}

final voting

Figure 1: General structure of proceeding a bill in the

Riigikogu. The brackets {} connect a part that can be

repeated; ’- -’ starts a comment. MP – any member of

Riigikogu.

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

determine the main claim that is together with its

premises given in the report of Minister in the

beginning of the first reading. We can consider a set

of the statements supporting the main claim (i.e. main

premises) together with the main claim as the main

argument. Example 1 presents the main argument of

proceeding the bill on alcohol. The annotation

follows (Koit, 2020).

As said before, arguments can be presented in

reports as well as when asking and answering

questions. Nevertheless, 75% of arguments are given

in special parts of readings – negotiations (cf. Koit,

2021). The total number of arguments is 48 (in

addition to the main argument).

KEOD 2022 - 14th International Conference on Knowledge Engineering and Ontology Development

158

(1)

<…>kehtiva alkoholiseaduse asendamiseks vastu

võtta uus seadus. … adopt a new law that will

substitute the existing one.

</main claim>

Kehtivast seadusest kaks korda mahukama eelnõu

väljatöötamisel on peetud silmas vajadust tagada

tooteohutus <…>, illegaalsete alkoholikäitlejate

vastutuse möödapääsmatus. … assure product safety

<…>, responsibility of illegal dealers.

</premise>

<…>

<…> tänavakaubanduses oleks igasugune

alkoholimüük keelatud. <…> prohibit selling alcohol

in street commerce.

</premise>

<…> puskariajamine nii oma tarbeks kui müügi

eesmärgil on keelatud. <…> prohibit distillation of

homebrew both for own usage and for sale.

</premise>

</main argument>

In majority of cases, an argument has only one

premise and one claim, i.e. its structure (diagram) is

basic (Stab and Gurevych, 2017:626). The next most

frequent structure is linked where the argument has

more than one premise that work together to support

a claim (like the main argument, Example 1). There

are some arguments with two or more premises that

independently support a claim (convergent

arguments). There are also some hybrid arguments

that involve several combinations of simpler

arguments into a larger argument structure (Example

2).

(2)

Ma arvan, et I think that

kui me peaksime millegi bensiinijaamas müümise

keelama, if we prohibit selling of something in petrol

stations,

</premise>

<claim>

siis me peaksime keelama just nimelt lahjade

alkohoolsete jookide müügi, siidrite, lahjade õllede

müügi, then we have to prohibit just selling of cider,

bear etc.,

</claim>

</argument>

</premise>

<claim>

sest need võivad tekitada autojuhil isu ja arvamuse, et

selle võib ta siiski ära juua. because they whet

appetite and bring a driver to believe that he may

drink them off.

</claim>

</argument>

This hybrid argument includes two basic

argument structures inside. Let us mention that there

is a different option to annotate the argument (2) as

serial. However, we are departing from the current

annotation of our argument corpus.

Divergent arguments have not been used by MPs

when proceeding the bill on alcohol (according to our

annotation).

The distribution of different argument structures

is shown in Figure 2.

Figure 2: Distribution of argument structures when

proceeding the bill on alcohol (number of arguments).

3.3 Arguments for and against the Bill

Three types of relations can appear between the

arguments: support, attack and rebuttal (Amgoud et

al., 2015).

An argument can support a premise or a claim of

another argument. An argument also can attack

another argument or its premise (Example 3). The

distribution of different inter-argument relations is

shown in Figure 3.

(3)

- - attacking a premise of the main argument (1)

Kui aina rohkem piiratakse alkoholi kättesaadavust If

availability of alcohol will be restricted more and

</premise>

#arguments

Argumentstructures:Estonia

Comparing Arguments in Discussions of Two Parliaments

159

<claim> – see on Põhjamaade kogemus – hakkavad

levima igasugused kompenseerivad toimingud ja

äritsemised. – that is the experience of the Nordic

countries – then all kinds of neutralising activities

and trades will escalate.

</claim>

</argument>

Figure 3: Distribution of inter-argument relations when

proceeding the bill on alcohol (number of arguments).

The number of attacking arguments is twice

bigger as compared with the number of supporting

ones. However, majority (66%) of the arguments are

related to amendments and do not attack the premises

of the main argument presented in the report of

Minister in the first reading. An argument can support

(a premise or claim of) a previous argument and at the

same time, explicitly attack another argument or its

premise. Two arguments curiously rebut the main

argument.

4 ARGUMENTS PRESENTED IN

THE UK PARLIAMENT

For comparison, let us consider a discussion in the

UK Parliament from the same year (2001). The

proceedings can be accessed online, similarly with

many other parliaments.

4.1 Empirical Material

A debate is a formal discussion of a specific proposal

(motion) in the House of Commons or House of

Lords. Members take it in turns to speak and there are

rules and conventions that are followed. Debates can

be read in the Official Report (Hansard) and viewed

online via Parliament TV. We selected the Tobacco

Advertising and Promotion Bill (2001) discussed in

the House of Commons. We analyse the second

reading which is the first opportunity for MPs for

debate on the bill (the verbatim record includes

55,327 tokens). The Secretary of State for Health

opens the discussion. His presentation includes the

main argument (Example 4).

(4)

The Bill will ban tobacco advertising and sponsorship

in this country.

</main claim>

It will do so to protect public health, to safeguard

children and to reduce health inequalities.

</premise>

<…>

Smoking kills 120,000 people <…> every year.

</premise>

<…>

It is one of the principal causes of the health gap

between the richest and the poorest in our country.

</premise>

</main argument>

After the report of the Secretary of State, the official

opposition spokesperson responds with their views on

the bill. The discussion continues with other

opposition parties and backbench MPs giving their

opinions. After every report, MPs can ask questions

that will be answered by the presenter. Finally, the

Commons decides whether the Bill should be given

its second reading by voting, meaning it can proceed

to the next stage. Therefore, the procedure is quite

different as compared with the Riigikogu. However,

arguments can be presented in every report as well as

when asking and answering questions.

4.2 Argument Structures

An expert annotated the arguments and inter-

argument relations in the proceedings. In total, 41

arguments have been found in addition to the main

argument (4). More than half of the arguments (63%)

have the simplest, basic structure, i.e. including one

premise and one claim (Example 5).

(5)

<claim>

There are all kinds of pragmatic arguments against

the Bill

</claim>

<…> its most offensive aspect is that it proposes a

total ban on the advertising of a legal, much-used

attack support att./supp. rebuttal

#arguments

Relations:Estonia

KEOD 2022 - 14th International Conference on Knowledge Engineering and Ontology Development

160

product and denies consumers information that

would enable them to make an informed choice.

</premise>

</argument>

Out of the remaining arguments, there are some

linked and convergent arguments. There are also

some complex, hybrid arguments (Example 6).

(6)

<claim>

If we want to stop children smoking —I am one who

does—

</claim>

<claim>

we must recognise that the most effective way is to

limit their access to cigarettes

</claim>

by making the laws prohibiting under-age sales more

effective;

</premise>

implementing education programmes designed to

discourage children from buying cigarettes

</premise>

and encourage adults to exercise more responsibility;

</premise>

and by clamping down on the illicit importation of

cigarettes.

</premise>

</argument>

</premise>

</argument>

The premise of the argument (6) is a different, linked

argument. The distribution of argument structures is

shown in Figure 4.

4.3 Arguments for and against the Bill

The arguments attack or support premises of the main

argument presented in the first report. Some

arguments attack or support premises of the (single)

amendment presented by the opposition (stating there

is insufficient evidence that the ban would reduce

tobacco consumption).

The number of attacking arguments is slightly

greater than of supporting ones. For example, the

argument (5) is the only which rebuts the main

argument. The argument (6) supports a premise and

the claim of the main argument. The distribution of

relations is shown in Figure 5.

Figure 4: Distribution of argument structures when

proceeding the Tobacco Bill (number of arguments).

Figure 5: Distribution of inter-argument relations when

proceeding the Tobacco Bill (number of arguments).

5 DISCUSSION

We are analysing arguments presented in two

different parliaments when discussing a bill – in the

Estonian Riigikogu and the UK Parliament House of

Commons. The legislation procedures are different

but arguments are presented in both parliaments.

In the Riigikogu, the representatives of

government and the leading committee make reports

about the bill. Every report will be followed by

questions of MPs. 75% of arguments are presented

during special parts of readings – negotiations, the

remaining 25% – in reports and questions or answers

(Figure 1).

Discussions in the UK Parliament are more

complicated because the Parliament has two Houses.

We consider here only one sitting in the House of

Commons – the 2

reading of the bill. Here,

arguments for and against the bill are presented in

reports and in following question-answer dialogues.

We compare the argument structures and inter-

argument relations in the two parliaments. We also

#arguments

Argumentstructures:UK

attack support att./supp. rebuttal

#arguments

Relations:UK

Comparing Arguments in Discussions of Two Parliaments

161

figure out the general procedures of presentation of

arguments in both parliaments.

Figure 6: Distribution of argument structures (% of

arguments): comparison of two parliaments.

In the Riigikogu, 48 arguments are presented

either in reports, when asking and answering

questions, or in negotiations on the general principles

and the amendments of the bill (in addition to the

main argument). In the UK Parliament, 41 arguments

are given in reports and when asking and answering

questions.

Considering the structure (diagrams) of the

arguments, we can conclude that the debaters give

preference to the simplest, basic arguments in both

parliaments (Figure 6). Such an argument seems to be

the strongest and most accessible to transfer the

message expressing the relation between a premise

and a claim.

More complex, hybrid arguments are only used in

seven cases both in the Riigikogu and in the UK

Parliament. Obviously, such arguments are not

always easy to understand. Divergent arguments

where more than one claim follows to one premise

have not been found in neither of proceedings. The

main argument presented in the very first report has

the linked structure in both parliaments. Here, the

premises work together to conclude the claim.

Comparative distribution of relations (rebuttal,

attack, support) between the arguments is shown in

Figure 7. Relations make it possible to figure out the

progress of the debate. In the Riigikogu, negotiation

curiously starts with an argument rebutting the main

argument ([…] If we approve the bill in the present

form then we express our satisfaction with the high

consumption of alcohol […]). After that, many

arguments are presented to support or attack some

amendments (only 39 amendments out of proposed

97 have been accepted after voting). Few arguments

support the main claim (‘to adopt the bill’) or to the

contrary, attack premises of the main argument.

Finally, it turns out that the arguments supporting the

bill are more convincing than the counterarguments

and the debate after final voting ends with adopting

the act.

Figure 7: Distribution of inter-argument relations (% of

arguments): comparison of two parliaments.

In the UK Parliament House of Commons, the

debate starts with arguments supporting some

premises or the claim of the main argument.

Attacking arguments are presented later in the debate.

Although their total number is greater, the voting

decides that the bill can proceed to the next stage.

Therefore, similarly with the Riigikogu, the

supporting arguments turn out to be more convincing.

In the UK Parliament, arguments are often

presented by using check questions (Bunt et al.,

2020). There are 51 check questions out of 73 asked

questions. Differently from the Riigikogu, 3

person

is used when applying to another person in

discussion, e.g. Does the Secretary of State think …?,

The hon. Gentleman is wrong (not Do you think…?,

You are wrong as in the Riigikogu). Specific style

(negative question) often appears in the UK

Parliament (e.g. Does he not …?). That is different in

the Riigikogu – Estonian MPs argue more personally

and directly. It seems to be a cultural difference.

In this study, we compared the form and functions

of arguments in two different parliaments. In order to

characterize the MPs by their used arguments (incl.

the structures and language features of arguments) we

need to study different proceedings with the same

participants. This requests extending our corpus in

order to make a step toward the automatic recognition

of arguments.

%arguments

Argumentstructures

Estonia UK

attack support att./supp. rebuttal

%arguments

Relations

Estonia UK

KEOD 2022 - 14th International Conference on Knowledge Engineering and Ontology Development

162

6 CONCLUSIONS

In the first part of the paper, a discussion on the bill

of alcohol in the Riigikogu is analyzed. For

comparison, the 2

reading of the Tobacco

Advertising and Promotion Bill in the UK Parliament

House of Commons is considered in the second part

of the paper. Argument structures and inter-argument

relations are compared in two parliaments. The

simplest, basic arguments prevail in both parliaments.

Although the number of supporting arguments is less

than of attacking ones, the former arguments turn out

to be more convincing and both discussions end with

approving the bill.

The current aim has been to demonstrate how

annotated argument corpora can be used for

characterizing and comparing the discussions in two

parliaments. Our corpus has to be extended in order

to make it possible the automatic recognition of

arguments as well as further analysis of political

discussions. This remains for further work.

ACKNOWLEDGEMENTS

This work was supported by the European Union

through the European Regional Development Fund

(Centre of Excellence in Estonian Studies).

REFERENCES

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

Representation and Analysis for RC-Arguments. In

Proc. of 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.

Bunt, H., Petukhova, V., Gilmartin, E., Pelachaud, C.,

Fang, A.C., Keizer, S., Prévot, L. The ISO Standard for

Dialogue Act Annotation, Second Edition. 2020. In

Proc. of LREC, 549–558.

Calabretta, I., Dalton, C., Griscom, R., Kołczyńska, M.,

Pahor de Maiti, K., Ros, R. 2021. Parliamentary debates

in the COVID times. https://dhhackathon.-

wordpress.com/2021/05/28/parliamentary-debates-in-

the-covid-times/

Calegari, R., Sartor, G. 2020. Burden of Persuasion in

Argumentation. In Proc. of ICLP, 151–163.

Erjavec, T., Ogrodniczuk, M., Osenova, P. et al. 2022. The

ParlaMint corpora of parliamentary proceedings. In

Language Resources and Evaluation.

https://doi.org/10.1007/s10579-021-09574-0

Haddadan, S., Cabrio, E., Villata, S., 2018. Annotation of

Argument Components in Political Debates Data. In

Proc. of the Workshop on Annotation in Digital

Humanities, 12–16.

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

Argument Analysis Interface. In Frontiers in Artificial

Intelligence and Applications. Vol, 266, 463–464.

Koit, M., 2021. How Are the Members of a Parliament

Arguing? Analysis of an Argument Corpus. In Proc. of

ICAART. Vol. 2, 1046−1053.

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

Corpus: An Experience. In Proc. of KEOD. Vol 2,

213−218.

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 Proc. of

AAAI’16, 2979-2985.

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

Never retreat, never retract: Argumentation analysis for

political speeches. In Proc. of AAAI-18, 4889–4896.

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

parliamentary discourse. In Proc. of CMNA-15, 1625.

Navarretta, C., Hansen, D.H. 2020. Identifying Parties in

Manifestos and Parliament Speeches. 2020. In Proc. of

ParlaCLARIN II, 51–57.

Parliamentary corpora. 2022. https://www.clarin.eu/-

resource-families/parliamentary-corpora

ParlaMint: Towards Comparable Parliamentary Corpora.

2022. https://www.clarin.eu/content/parlamint-towards

-comparable-parliamentary-corpora

Petukhova, V., Malchanau, A., Oualil, Y., Klakow, D., Luz,

S., Haider, F., Campbell, N., Koryzis, D.,

Spiliotopoulos, D., Albert, P., Linz, N., Alexandersson,

J. 2018. The Metalogue Debate Trainee Corpus: Data

Collection and Annotations. In Proc. of LREC, 749-755.

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

argumentative behaviour in parliamentary debates: data

collection, analysis and test case. In LNCS, 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 Proc. of

CIRCLE. http://ceur-ws.org/Vol-2621/

Riigikogu (Parliament of Estonia). 2022.

https://www.riigikogu.ee/en/

Ruiz-Dolz, R., Nofre, M., Taulé, M., Heras, S., García-

Fornes, 2021. A. VivesDebate: A New Annotated

Multilingual Corpus of Argumentation in a Debate

Tournament. In Appl. Sci., 11, 7160.

https://doi.org/10.3390/app11157160

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

Structures in Persuasive Essays. In Computational

Linguistics, 43(3), 619–659.

Comparing Arguments in Discussions of Two Parliaments

163

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

Components and Relations in Persuasive Essays. In

Proc. of COLING, 1501–1510, Dublin, Ireland.

Tobacco Advertising and Promotion Bill. 2001.

http://hansard.millbanksystems.com/commons/2001/ja

n/22/

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

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

Argumentation, Objectivity, and Bias: Proceedings of

the 11th international conference of the Ontario society

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

KEOD 2022 - 14th International Conference on Knowledge Engineering and Ontology Development

164