Pregled bibliografske jedinice broj: 989941
Using Analytic Scoring Rubrics in the Automatic Assessment of College-Level Summary Writing Tasks in L2
Using Analytic Scoring Rubrics in the Automatic Assessment of College-Level Summary Writing Tasks in L2 // Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers) / Kondrak, Greg ; Watanabe, Taro (ur.).
Taipei: Asian Federation of Natural Language Processing, 2017. str. 181-186 (ostalo, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 989941 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Using Analytic Scoring Rubrics in the Automatic Assessment of College-Level Summary Writing Tasks in L2
Autori
Sladoljev-Agejev, Tamara ; Šnajder, Jan
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
/ Kondrak, Greg ; Watanabe, Taro - Taipei : Asian Federation of Natural Language Processing, 2017, 181-186
ISBN
978-1-948087-01-8
Skup
The Eighth International Joint Conference on Natural Language Processing
Mjesto i datum
Taipei, Tajvan, 27.11.2017. - 01.12.2017
Vrsta sudjelovanja
Ostalo
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
summary writing, analytic scoring, reference-based features, linguistic features
Sažetak
Assessing summaries is a demanding, yet useful task which provides valuable information on language competence, especially for second language learners. We consider automated scoring of college-level summary writing task in English as a second language (EL2). We adopt the Reading- forUnderstanding (RU) cognitive framework, extended with the Reading-to-Write (RW) element, and use analytic scoring with six rubrics covering content and writing quality. We show that regression models with reference- based and linguistic features considerably outperform the baselines across all the rubrics. Moreover, we find interesting correlations between summary features and analytic rubrics, revealing the links between the RU and RW constructs.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo, Kognitivna znanost (prirodne, tehničke, biomedicina i zdravstvo, društvene i humanističke znanosti)
POVEZANOST RADA
Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb,
Ekonomski fakultet, Zagreb