Paper Revision{2024.acl-short.45}, closes #4427.

data/xml/2024.acl.xml

@@ -12754,9 +12754,11 @@
       <author><first>Brian</first><last>Thompson</last><affiliation>Amazon</affiliation></author>
       <pages>488-500</pages>
       <abstract>We introduce a new, extensive multidimensional quality metrics (MQM) annotated dataset covering 11 language pairs in the biomedical domain. We use this dataset to investigate whether machine translation (MT) metrics which are fine-tuned on human-generated MT quality judgements are robust to domain shifts between training and inference. We find that fine-tuned metrics exhibit a substantial performance drop in the unseen domain scenario relative to both metrics that rely on the surface form and pre-trained metrics that are not fine-tuned on MT quality judgments.</abstract>
-      <url hash="d4d0d79d">2024.acl-short.45</url>
+      <url hash="eebb2c9a">2024.acl-short.45</url>
       <bibkey>zouhar-etal-2024-fine</bibkey>
       <doi>10.18653/v1/2024.acl-short.45</doi>
+      <revision id="1" href="2024.acl-short.45v1" hash="d4d0d79d"/>
+      <revision id="2" href="2024.acl-short.45v2" hash="eebb2c9a" date="2025-02-06">Adds the missing legend and axis labels on Figure 2.</revision>
     </paper>
     <paper id="46">
       <title><fixed-case>I</fixed-case>ndic<fixed-case>IRS</fixed-case>uite: Multilingual Dataset and Neural Information Models for <fixed-case>I</fixed-case>ndian Languages</title>