Loading [MathJax]/extensions/tex2jax.js

Argument Novelty and Validity Assessment via Multitask and Transfer Learning

Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review

Authors

Research Organisations

Details

Original languageEnglish
Title of host publicationProceedings of the 9th Workshop on Argument Mining
Pages111-114
Number of pages4
Volume29
Publication statusPublished - 2022
Event9th Workshop on Argument Mining - Gyeongju, Korea, Republic of
Duration: 17 Oct 2022 → 17 Oct 2022

Publication series

NameProceedings - International Conference on Computational Linguistics, COLING
ISSN (Print)2951-2093

Abstract

An argument is a constellation of premises reasoning towards a certain conclusion. The automatic generation of conclusions is becoming a very prominent task, raising the need for automatic measures to assess the quality of these generated conclusions. The SharedTask at the 9th Workshop on Argument Mining proposes a new task to assess the novelty and validity of a conclusion given a set of premises. In this paper, we present a multitask learning approach that transfers the knowledge learned from the natural language inference task to the tasks at hand. Evaluation results indicate the importance of both knowledge transfer and joint learning, placing our approach in the fifth place with strong results compared to baselines.

ASJC Scopus subject areas

Sustainable Development Goals

Cite this

Argument Novelty and Validity Assessment via Multitask and Transfer Learning. / Alshomary, Milad; Stahl, Maja.
Proceedings of the 9th Workshop on Argument Mining. Vol. 29 14. ed. 2022. p. 111-114 (Proceedings - International Conference on Computational Linguistics, COLING).

Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review

Alshomary, M & Stahl, M 2022, Argument Novelty and Validity Assessment via Multitask and Transfer Learning. in Proceedings of the 9th Workshop on Argument Mining. 14 edn, vol. 29, Proceedings - International Conference on Computational Linguistics, COLING, pp. 111-114, 9th Workshop on Argument Mining, Gyeongju, Korea, Republic of, 17 Oct 2022. <https://aclanthology.org/2022.argmining-1.10.pdf>
Alshomary, M., & Stahl, M. (2022). Argument Novelty and Validity Assessment via Multitask and Transfer Learning. In Proceedings of the 9th Workshop on Argument Mining (14 ed., Vol. 29, pp. 111-114). (Proceedings - International Conference on Computational Linguistics, COLING). https://aclanthology.org/2022.argmining-1.10.pdf
Alshomary M, Stahl M. Argument Novelty and Validity Assessment via Multitask and Transfer Learning. In Proceedings of the 9th Workshop on Argument Mining. 14 ed. Vol. 29. 2022. p. 111-114. (Proceedings - International Conference on Computational Linguistics, COLING).
Alshomary, Milad ; Stahl, Maja. / Argument Novelty and Validity Assessment via Multitask and Transfer Learning. Proceedings of the 9th Workshop on Argument Mining. Vol. 29 14. ed. 2022. pp. 111-114 (Proceedings - International Conference on Computational Linguistics, COLING).
Download
@inproceedings{c242beb9abab472cb13413b33ec45fd8,
title = "Argument Novelty and Validity Assessment via Multitask and Transfer Learning",
abstract = "An argument is a constellation of premises reasoning towards a certain conclusion. The automatic generation of conclusions is becoming a very prominent task, raising the need for automatic measures to assess the quality of these generated conclusions. The SharedTask at the 9th Workshop on Argument Mining proposes a new task to assess the novelty and validity of a conclusion given a set of premises. In this paper, we present a multitask learning approach that transfers the knowledge learned from the natural language inference task to the tasks at hand. Evaluation results indicate the importance of both knowledge transfer and joint learning, placing our approach in the fifth place with strong results compared to baselines.",
author = "Milad Alshomary and Maja Stahl",
note = "Publisher Copyright: {\textcopyright} 2022 Proceedings - International Conference on Computational Linguistics, COLING. All Rights Reserved.; 9th Workshop on Argument Mining, ArgMining ; Conference date: 17-10-2022 Through 17-10-2022",
year = "2022",
language = "English",
volume = "29",
series = "Proceedings - International Conference on Computational Linguistics, COLING",
pages = "111--114",
booktitle = "Proceedings of the 9th Workshop on Argument Mining",
edition = "14",

}

Download

TY - GEN

T1 - Argument Novelty and Validity Assessment via Multitask and Transfer Learning

AU - Alshomary, Milad

AU - Stahl, Maja

N1 - Publisher Copyright: © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All Rights Reserved.

PY - 2022

Y1 - 2022

N2 - An argument is a constellation of premises reasoning towards a certain conclusion. The automatic generation of conclusions is becoming a very prominent task, raising the need for automatic measures to assess the quality of these generated conclusions. The SharedTask at the 9th Workshop on Argument Mining proposes a new task to assess the novelty and validity of a conclusion given a set of premises. In this paper, we present a multitask learning approach that transfers the knowledge learned from the natural language inference task to the tasks at hand. Evaluation results indicate the importance of both knowledge transfer and joint learning, placing our approach in the fifth place with strong results compared to baselines.

AB - An argument is a constellation of premises reasoning towards a certain conclusion. The automatic generation of conclusions is becoming a very prominent task, raising the need for automatic measures to assess the quality of these generated conclusions. The SharedTask at the 9th Workshop on Argument Mining proposes a new task to assess the novelty and validity of a conclusion given a set of premises. In this paper, we present a multitask learning approach that transfers the knowledge learned from the natural language inference task to the tasks at hand. Evaluation results indicate the importance of both knowledge transfer and joint learning, placing our approach in the fifth place with strong results compared to baselines.

UR - http://www.scopus.com/inward/record.url?scp=105007043678&partnerID=8YFLogxK

M3 - Conference contribution

VL - 29

T3 - Proceedings - International Conference on Computational Linguistics, COLING

SP - 111

EP - 114

BT - Proceedings of the 9th Workshop on Argument Mining

T2 - 9th Workshop on Argument Mining

Y2 - 17 October 2022 through 17 October 2022

ER -

By the same author(s)