Starting from last year, WMT human evaluation has been performed within the Multidimensional Quality Metrics (MQM) framework, where human annotators are asked to identify error spans in translations, alongside an error category and a severity. In this paper, we describe our submission to the WMT 2022 Metrics Shared Task, where we propose using the same paradigm for automatic evaluation: we present the MATESE metrics, which reframe machine translation evaluation as a sequence tagging problem. Our submission also includes a reference-free metric, denominated MATESE-QE. Despite the paucity of the openly available MQM data, our metrics obtain promising results, showing high levels of correlation with human judgements, while also enabling an evaluation that is interpretable. Moreover, MATESE-QE can also be employed in settings where it is infeasible to curate reference translations manually.
MaTESe: Machine Translation Evaluation as a Sequence Tagging Problem / Perrella, Stefano; Proietti, Lorenzo; Scirã, Alessandro; Campolungo, Niccolò; Navigli, Roberto. - (2022), pp. 569-577. (Intervento presentato al convegno Conference on Machine Translation tenutosi a Abu Dhabi, United Arab Emirates).
MaTESe: Machine Translation Evaluation as a Sequence Tagging Problem
Stefano Perrella
;Lorenzo Proietti
;Alessandro ScirÃ
;Niccolò Campolungo
;Roberto Navigli
2022
Abstract
Starting from last year, WMT human evaluation has been performed within the Multidimensional Quality Metrics (MQM) framework, where human annotators are asked to identify error spans in translations, alongside an error category and a severity. In this paper, we describe our submission to the WMT 2022 Metrics Shared Task, where we propose using the same paradigm for automatic evaluation: we present the MATESE metrics, which reframe machine translation evaluation as a sequence tagging problem. Our submission also includes a reference-free metric, denominated MATESE-QE. Despite the paucity of the openly available MQM data, our metrics obtain promising results, showing high levels of correlation with human judgements, while also enabling an evaluation that is interpretable. Moreover, MATESE-QE can also be employed in settings where it is infeasible to curate reference translations manually.File | Dimensione | Formato | |
---|---|---|---|
Perrella_MATESE_2022.pdf
accesso aperto
Note: https://aclanthology.org/2022.wmt-1.51
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Creative commons
Dimensione
725.23 kB
Formato
Adobe PDF
|
725.23 kB | Adobe PDF |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.