%0 Generic %1 a9787c04f4de457b97f358921415c2b9 %A Kiesel, Johannes %A Alshomary, Milad %A Mirzakhmedova, Nailia %A Heinrich, Maximilian %A Handke, Nicolas %A Wachsmuth, Henning %A Stein, Benno %D 2023 %K #sys:relevantfor:l3s myown nlp %P 2287--2303 %R 10.18653/V1/2023.SEMEVAL-1.313 %T SemEval-2023 Task 4: ValueEval: Identification of Human Values Behind Arguments %X Argumentation is ubiquitous in natural language communication, from politics and media to everyday work and private life. Many arguments derive their persuasive power from human values, such as self-directed thought or tolerance, albeit often implicitly. These values are key to understanding the semantics of arguments, as they are generally accepted as justifications for why a particular option is ethically desirable. Can automated systems uncover the values on which an argument draws? To answer this question, 39 teams submitted runs to ValueEval’23. Using a multi-sourced dataset of over 9K arguments, the systems achieved F 1-scores up to 0.87 (nature) and over 0.70 for three more of 20 universal value categories. However, many challenges remain, as evidenced by the low peak F 1-score of 0.39 for stimulation, hedonism, face, and humility.

@conference{a9787c04f4de457b97f358921415c2b9, abstract = {Argumentation is ubiquitous in natural language communication, from politics and media to everyday work and private life. Many arguments derive their persuasive power from human values, such as self-directed thought or tolerance, albeit often implicitly. These values are key to understanding the semantics of arguments, as they are generally accepted as justifications for why a particular option is ethically desirable. Can automated systems uncover the values on which an argument draws? To answer this question, 39 teams submitted runs to ValueEval{\textquoteright}23. Using a multi-sourced dataset of over 9K arguments, the systems achieved F 1-scores up to 0.87 (nature) and over 0.70 for three more of 20 universal value categories. However, many challenges remain, as evidenced by the low peak F 1-score of 0.39 for stimulation, hedonism, face, and humility.}, added-at = {2024-02-13T13:24:54.000+0100}, author = {Kiesel, Johannes and Alshomary, Milad and Mirzakhmedova, Nailia and Heinrich, Maximilian and Handke, Nicolas and Wachsmuth, Henning and Stein, Benno}, biburl = {https://www.bibsonomy.org/bibtex/20852aa8174fd39716496a5c4c1121bda/ail3s}, doi = {10.18653/V1/2023.SEMEVAL-1.313}, interhash = {f4339d9b8c5658b8dbda99b462175c8d}, intrahash = {0852aa8174fd39716496a5c4c1121bda}, keywords = {#sys:relevantfor:l3s myown nlp}, language = {English}, pages = {2287--2303}, timestamp = {2024-02-27T12:19:46.000+0100}, title = {SemEval-2023 Task 4: ValueEval: Identification of Human Values Behind Arguments}, year = 2023 }