Systems and Means of Informatics
2021, Volume 31, Issue 3, pp 144-157
EXPERT EVALUATION OF MACHINE TRANSLATION: ERROR CLASSIFICATION
- A. Yu. Egorova
- I. M. Zatsman
- V. A. Nuriev
Abstract
The paper considers the error classification applied in the expert evaluation of the machine translation quality. The classification includes common error headings (for errors at the level of grammar, vocabulary, punctuation, etc.) as well as headings that are associated with a specific type of linguistic unit selected for evaluating the machine translation quality. The quality evaluation is performed by experts as they linguistically annotate machine translation outcomes. If, while annotating, an expert finds errors, then headings, necessary to characterize these errors, are included in the annotation. The headings allow one to calculate the relative frequency of machine translation errors for the array of test sentences selected for translation and quality evaluation. The main goal of the paper is to describe the proposed classification of common and specific errors. The principal difference of the classification from the existing error classifications is that it is aimed at backing interval evaluation for machine translation systems, whose quality of work may vary over time. The headings of the proposed classification allow experts to record both improvements and decreases in machine translation quality at a given time interval.
[+] References (26)
- Moorkens, J., S. Castilho, F. Gaspari, and S. Doherty, eds. 2018. Translation quality assessment: From principles to practice. Machine translation: Technologies and applications ser. Cham, Switzerland: Springer International Publishing. Vol. 1. 299 p.
- Specia, L., C. Scarton, and G. H. Paetzold. 2018. Quality estimation for machine translation. Synthesis lectures on human language technologies ser. London: Morgan & Claypool. 162 p.
- Bittner, H. 2020. Evaluating the evaluator: A novel perspective on translation quality assessment. New York, NY: Routledge. 282 p.
- Nuriev, V.A., and A. Yu. Egorova. 2021. Metody otsenki kachestva mashinnogo perevoda: sovremennoe sostoyanie [Methods of quality estimation for machine translation: State-of-the-art]. Informatika i ee Primeneniya - Inform. Appl. 15(2):104-111.
- Popovic, M. 2018. Error classification and analysis for machine translation quality assessment. Translation quality assessment: From principles to practice. Eds. J. Moorkens, Sh. Castilho, F. Gaspari, and S. Doherty. Machine translation: Technologies and applications ser. Cham: Springer International Publishing. 1:129-158.
- Castilho, Sh., J. Moorkens, F. Gaspari, I. Calixto, J. Tinsley, and A. Way. 2017. Is neural machine translation the new state of the art? Prague Bull. Math. Linguist. 108(1):109-120.
- Castilho, Sh., S. Doherty, F. Gaspari, and J. Moorkens. 2018. Approaches to human and machine translation quality assessment. Translation quality assessment: From principles to practice. Eds. J. Moorkens, Sh. Castilho, F. Gaspari, and S. Doherty. Machine translation: Technologies and applications ser. Cham, Switzerland: Springer. 1:9-38.
- Popovicc, M. 2018. Language-related issues for NMT and PBMT for English-German and English-Serbian. Machine Translation 32:237-253.
- Castilho, S., J. Moorkens, F. Gaspari, et al. 2018. Evaluating MT for massive open online courses. A multifaceted comparison between PBSMT and NMT systems. Machine Translation 32:255-278.
- Castilho, S., F. Gaspari, J. Moorkens, M. Popovic, and A. Toral. 2019. Editors' foreword to the special issue on human factors in neural machine translation. Machine Translation 33:1-7.
- Inkova-Manzotti, O.Yu. 2001. Konnektory protivopostavleniya vo frantsuzskom i russkom yazykakh. Sopostavitel'noe issledovanie [Connectors of opposition in French and Russian: A comparative study]. Moscow: Informelektro. 429 p.
- Inkova, O.Yu., and M. G. Kruzhkov. 2018. Metod opisaniya struktury neodnoslovnykh konnektorov v nadkorpusnykh bazakh dannykh [Method for description of multiword connectives in supracorpora databases]. Sistemy i Sredstva Informati- ki - Systems and Means of Informatics 28(4): 168-181.
- Inkova, O.Yu., and M. G. Kruzhkov. 2019. Sochetaemost' logiko-semanticheskikh otnosheniy: kolichestvennye metody analiza [Compatibility of logical semantic relations: Methods of quantitative analysis]. Informatika i ee Primeneniya - Inform. Appl.
13 (2):83-91.
- Egorova, A. Yu., I. M. Zatsman, V. V. Kosarik, and V. A. Nuriev. 2020. Nestabil'nost' neyronnogo mashinnogo perevoda [Instability of neural machine translation]. Sistemy i Sredstva Informatiki - Systems and Means of Informatics 30(2): 124-135.
- Egorova, A. Yu., I. M. Zatsman, M. G. Kruzhkov, and V. A. Nuriev. 2020. Metodika temporal'noy otsenki nestabil'nosti mashinnogo perevoda [The technique allowing for temporal estimation of the machine translation instability]. Sistemy i Sredstva Informatiki - Systems and Means of Informatics 30(3):67-80.
- Egorova, A. Yu., I. M. Zatsman, M. G. Kruzhkov, and V. A. Nuriev. 2020. Mashinnyy perevod: indikatornaya otsenka rezul'tatov obucheniya iskusstvennoy neyronnoy seti [Machine translation: Indicator-based evaluation of training progress in neural processing]. Sistemy i Sredstva Informatiki - Systems and Means of Informatics 30(4): 124-137.
- Egorova, A. Yu., I. M. Zatsman, M. G. Kruzhkov, and V.A. Nuriev. 2021. Indikatornaya otsenka nestabil'nosti neyronnogo mashinnogo perevoda [Indicator-based evaluation of machine translation instability]. Sistemy i Sredstva Informatiki - Systems and Means of Informatics 31 (2): 139-151.
- Natsional'nyy korpus russkogo yazyka [Russian National Corpus]. Available at: http://www.ruscorpora.ru/ (accessed August 11, 2021).
- Zaliznyak, A. A., I. M. Zatsman, and O.Yu. Inkova. 2017. Nadkorpusnaya baza dannykh konnektorov: postroenie sistemy terminov [Supracorpora database on connectives: Term system development]. Informatika i ee Primeneniya - Inform. Appl. 11(1): 100-108.
- Zatsman, I. M., and M. G. Kruzhkov. 2018. Nadkorpusnaya baza dannykh konnektorov: razvitie sistemy terminov proektirovaniya [Supracorpora database of connectives: Design-oriented evolution of the term system]. Sistemy i Sredstva Informatiki - Systems and Means of Informatics 28(4): 15 6-167.
- Egorova, A. Yu., I. M. Zatsman, and O. S. Mamonova. 2019. Nadkorpusnye bazy dannykh v lingvisticheskikh proektakh [Supracorpora databases in linguistic projects]. Sistemy i Sredstva Informatiki - Systems and Means of Informatics 29(3):77-91.
- Ranganathan, S. R. 1933. Colon classification. London: Edward Goldston. 106 p.
- Nelson, D., and L. Turney. 2015. What's in a word? Rethinking facet headings in a discovery service. Inform. Technol. Libr. 34(2):76-91.
- Ide, N., and J. Pustejovsky, eds. 2017. Handbook of linguistic annotation. Dordrecht, The Netherlands: Springer Science + Business Media. 1468 p.
- Huber, G. P. 1985. Temporal stability and response-order biases in participant descriptions of organizational decisions. Acad. Manage. J. 28(4):943-950.
- Belinkov, Y., andY. Bisk. 2018. Synthetic and natural noise both break neural machine translation. 6th Conference (International) on Learning Representations Proceedings. La Jolla, CA: ICLR Board. 1-13.
[+] About this article
Title
EXPERT EVALUATION OF MACHINE TRANSLATION: ERROR CLASSIFICATION
Journal
Systems and Means of Informatics
Volume 31, Issue 3, pp 144-157
Cover Date
2021-11-10
DOI
10.14357/08696527210313
Print ISSN
0869-6527
Publisher
Institute of Informatics Problems, Russian Academy of Sciences
Additional Links
Key words
machine translation; quality evaluation; error classification; common errors; specific errors; linguistic annotation; interval evaluation
Authors
A. Yu. Egorova , I. M. Zatsman , and V. A. Nuriev
Author Affiliations
Federal Research Center "Computer Science and Control", Russian Academy of Sciences, 44-2 Vavilov Str., Moscow 119333, Russian Federation
|