Retract 2021.acl-long.222 (acl-org#3694)

data/xml/2021.acl.xml

@@ -3637,10 +3637,13 @@
       <author><first>Guodong</first><last>Zhou</last></author>
       <pages>2851–2861</pages>
       <abstract>Context-aware neural machine translation (NMT) remains challenging due to the lack of large-scale document-level parallel corpora. To break the corpus bottleneck, in this paper we aim to improve context-aware NMT by taking the advantage of the availability of both large-scale sentence-level parallel dataset and source-side monolingual documents. To this end, we propose two pre-training tasks. One learns to translate a sentence from source language to target language on the sentence-level parallel dataset while the other learns to translate a document from deliberately noised to original on the monolingual documents. Importantly, the two pre-training tasks are jointly and simultaneously learned via the same model, thereafter fine-tuned on scale-limited parallel documents from both sentence-level and document-level perspectives. Experimental results on four translation tasks show that our approach significantly improves translation performance. One nice property of our approach is that the fine-tuned model can be used to translate both sentences and documents.</abstract>
-      <url hash="1a937860">2021.acl-long.222</url>
+      <url hash="9ceda8ac">2021.acl-long.222</url>
       <doi>10.18653/v1/2021.acl-long.222</doi>
       <bibkey>chen-etal-2021-breaking</bibkey>
       <video href="2021.acl-long.222.mp4"/>
+      <revision id="1" href="2021.acl-long.222v1" hash="1a937860"/>
+      <revision id="2" href="2021.acl-long.222v2" hash="9ceda8ac" date="2024-07-23">Retracted.</revision>
+      <retracted date="2024-07-23">This paper violated ACL's dual-submission policy.</retracted>
     </paper>
     <paper id="223">
       <title>Guiding Teacher Forcing with Seer Forcing for Neural Machine Translation</title>