Pregled bibliografske jedinice broj: 948479
Quality assurance in computer-assisted translation in business environment
Quality assurance in computer-assisted translation in business environment // Natural Language Processing for Global and Local Business / Pinarbași, Fatih ; Nurdan Oncel Taskiran, M. (ur.).
Hershey (PA): IGI Global, 2021. str. 247-270 doi:10.4018/978-1-7998-4240-8
CROSBI ID: 948479 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Quality assurance in computer-assisted translation
in business environment
Autori
Seljan, Sanja ; Škof Erdelja, Nikolina ; Kučiš, Vlasta ; Dunđer, Ivan ; Pejić Bach, Mirjana
Vrsta, podvrsta i kategorija rada
Poglavlja u knjigama, znanstveni
Knjiga
Natural Language Processing for Global and Local Business
Urednik/ci
Pinarbași, Fatih ; Nurdan Oncel Taskiran, M.
Izdavač
IGI Global
Grad
Hershey (PA)
Godina
2021
Raspon stranica
247-270
ISBN
9781799842408
Ključne riječi
Evaluation, Quality, Error, Translation Memory, Multidimensional Quality Metric, QA Tools, CAT Tools, Technology, ICT in Translation, Data Analysis, Translation Industry, Digital Transformation
Sažetak
Increased use of computer-assisted translation (CAT) technology in business settings with augmented amount of tasks, collaborative work and short deadlines give rise to errors and the need for quality assurance (QA). The research has three operational aims: a) methodological framework for QA analysis b) comparative evaluation of four QA tools c) to justify introduction of QA into CAT process. The research includes building of translation memory, terminology extraction and creation of terminology base. Error categorization is conducted by multidimensional quality (MQM) framework. The level of mistake is calculated considering detected, false and not detected errors. Weights are assigned to errors (minor, major or critical), penalties are calculated and quality estimation for translation memory is given. Results show that process is prone to errors due to differences in error detection, harmonization and error counting. Data analysis of detected errors lead to further data-driven decisions related to the quality of output results and improved efficacy of translation business process.
Izvorni jezik
Engleski
Znanstvena područja
Ekonomija, Informacijske i komunikacijske znanosti
POVEZANOST RADA
Projekti:
NadSve-Sveučilište u Zagrebu-VirasIntel - Razvoj i implementacija VIRtualnog Asistenta i resursa za Strojno prevođenje iz specijaliziranih domena primjenom metoda umjetne INTELigencije (VirasINTEL) (VirasIntel) (Seljan, Sanja, NadSve - Natječaj 2020/2021.) ( CroRIS)
Ustanove:
Ekonomski fakultet, Zagreb,
Filozofski fakultet, Zagreb
Citiraj ovu publikaciju:
Časopis indeksira:
- Scopus