Overview of the author identification task at PAN 2014
Uloženo v:
| Název: | Overview of the author identification task at PAN 2014 |
|---|---|
| Autoři: | Stamatatos E., Daelemans W., Verhoeven B., Potthast M., Stein B., Juola P., Sanchez-Perez M. A., Barron-Cedeno A. |
| Zdroj: | CLEF 2014 Evaluation Labs and Workshop Working Notes Papers, Sheffield, UK, 2014 |
| Informace o vydavateli: | CEUR-WS, 2014. |
| Rok vydání: | 2014 |
| Témata: | author identification, author profiling, forensic linguistics, Linguistics |
| Popis: | The author identification task at PAN-2014 focuses on author verification. Similar to PAN-2013 we are given a set of documents by the same author along with exactly one document of questioned authorship, and the task is to determine whether the known and the questioned documents are by the same author or not. In comparison to PAN-2013, a significantly larger corpus was built comprising hundreds of documents in four natural languages (Dutch, English, Greek, and Spanish) and four genres (essays, reviews, novels, opinion articles). In addition, more suitable performance measures are used focusing on the accuracy and the confidence of the predictions as well as the ability of the submitted methods to leave some problems unanswered in case there is great uncertainty. To this end, we adopt the c@1 measure, originally proposed for the question answering task. We received 13 software submissions that were evaluated in the TIRA framework. Analytical evaluation results are presented where one language-independent approach serves as a challenging baseline. Moreover, we continue the successful practice of the PAN labs to examine meta-models based on the combination of all submitted systems. Last but not least, we provide statistical significance tests to demonstrate the important differences between the submitted approaches. |
| Druh dokumentu: | Conference object |
| Popis souboru: | pdf; application/pdf |
| Jazyk: | English |
| Přístupová URL adresa: | https://repository.uantwerpen.be/docman/irua/9c2840/118298.pdf https://hdl.handle.net/10067/1182980151162165141 https://hdl.handle.net/11585/709289 |
| Přístupové číslo: | edsair.dedup.wf.002..12f7cbb4bc5cf889253c4467c9b0240f |
| Databáze: | OpenAIRE |
Nájsť tento článok vo Web of Science | Abstrakt: | The author identification task at PAN-2014 focuses on author verification. Similar to PAN-2013 we are given a set of documents by the same author along with exactly one document of questioned authorship, and the task is to determine whether the known and the questioned documents are by the same author or not. In comparison to PAN-2013, a significantly larger corpus was built comprising hundreds of documents in four natural languages (Dutch, English, Greek, and Spanish) and four genres (essays, reviews, novels, opinion articles). In addition, more suitable performance measures are used focusing on the accuracy and the confidence of the predictions as well as the ability of the submitted methods to leave some problems unanswered in case there is great uncertainty. To this end, we adopt the c@1 measure, originally proposed for the question answering task. We received 13 software submissions that were evaluated in the TIRA framework. Analytical evaluation results are presented where one language-independent approach serves as a challenging baseline. Moreover, we continue the successful practice of the PAN labs to examine meta-models based on the combination of all submitted systems. Last but not least, we provide statistical significance tests to demonstrate the important differences between the submitted approaches. |
|---|