| Téléchargement | - Voir la version finale : MSLC24: further challenges for metrics on a wide landscape of translation quality (PDF, 3.9 Mio)
|
|---|
| Lien | https://aclanthology.org/2024.wmt-1.34 |
|---|
| Auteur | Rechercher : Knowles, Rebecca1Identifiant ORCID : https://orcid.org/0000-0002-1647-584X; Rechercher : Larkin, Samuel1Identifiant ORCID : https://orcid.org/0009-0000-6147-9631; Rechercher : Lo, Chi-Kiu1Identifiant ORCID : https://orcid.org/0000-0001-8714-7846 |
|---|
| Affiliation | - Conseil national de recherches du Canada. Technologies numériques
|
|---|
| Format | Texte, Article |
|---|
| Conférence | Ninth Conference on Machine Translation (WMT24), November 15-16, 2024, Miami, Florida, USA |
|---|
| Résumé | In this second edition of the Metric Score Landscape Challenge (MSLC), we examine how automatic metrics for machine translation perform on a wide variety of machine translation output, ranging from very low quality systems to the types of high-quality systems submitted to the General MT shared task at WMT. We also explore metric results on specific types of data, such as empty strings, wrong- or mixed-language text, and more. We raise several alarms about inconsistencies in metric scores, some of which can be resolved by increasingly explicit instructions for metric use, while others highlight technical flaws. |
|---|
| Date de publication | 2024-11-15 |
|---|
| Maison d’édition | Association for Computational Linguistics |
|---|
| Licence | |
|---|
| Dans | |
|---|
| Langue | anglais |
|---|
| Publications évaluées par des pairs | Oui |
|---|
| Exporter la notice | Exporter en format RIS |
|---|
| Signaler une correction | Signaler une correction (s'ouvre dans un nouvel onglet) |
|---|
| Identificateur de l’enregistrement | 888f2024-592a-4b55-a841-52f62072f3f3 |
|---|
| Enregistrement créé | 2024-11-14 |
|---|
| Enregistrement modifié | 2024-11-15 |
|---|
