RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication
Contribución de congreso (ConferenceOutput)
Automatic Debate Evaluation with Argumentation Semantics and Natural Language Argument Graph Networks
[EN] The lack of annotated data on professional argumentation and complete argumentative debates has led to the oversimplification and the
inability of approaching more complex natural
language processing tasks. Such is the case
of the automatic evaluation of complete professional argumentative debates. In this paper,
we propose an original hybrid method to automatically predict the winning stance in this
kind of debates. For that purpose, we combine concepts from argumentation theory such
as argumentation frameworks and semantics,
with Transformer-based architectures and neural graph networks. Furthermore, we obtain
promising results that lay the basis on an unexplored new instance of the automatic analysis
of natural language arguments., This work has been developed thanks to
the funding of the following projects:
Grant PID2021-123673OB-C31 funded
by MCIN/AEI/10.13039/501100011033, Grant TED2021-131295B-C32 funded by
AEI/10.13039/501100011033/ European Union
NextGenerationEU/PRTR, Spanish Government
project PID2020-113416RB-I00, and the AI for
Citizen Intelligence Coaching against Disinformation (TITAN) project, funded by the EU Horizon
2020 research and innovation programme under
grant agreement 101070658, and by UK Research
and innovation under the UK governments Horizon
funding guarantee grant numbers 10040483 and
10055990.
Project:
Agencia Estatal de Investigación / Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020 PID2020-113416RB-I00
,
Agencia Estatal de Investigación / Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 PID2021-123673OB-C31
,
European Commission / HE 101070658
,
Agencia Estatal de Investigación TED2021-131295B-C32
,
UK Research and Innovation 10055990
,
UK Research and Innovation 10040483