Papers › Structured Prediction as Translation between Augmented Natural Languages

Structured Prediction as Translation between Augmented Natural Languages

14 Jan 2021ICLR 2021 1arXiv:2101.05779archive 2025-07-28

Giovanni Paolini, Ben Athiwaratkun, Jason Krone, Jie Ma, Alessandro Achille, Rishita Anubhai, Cicero Nogueira dos santos, Bing Xiang, Stefano Soatto

We propose a new framework, Translation between Augmented Natural Languages (TANL), to solve many structured prediction language tasks including joint entity and relation extraction, nested named entity recognition, relation classification, semantic role labeling, event extraction, coreference resolution, and dialogue state tracking. Instead of tackling the problem by training task-specific discriminative classifiers, we frame it as a translation task between augmented natural languages, from which the task-relevant information can be easily extracted. Our approach can match or outperform task-specific models on all tasks, and in particular, achieves new state-of-the-art results on joint entity and relation extraction (CoNLL04, ADE, NYT, and ACE2005 datasets), relation classification (FewRel and TACRED), and semantic role labeling (CoNLL-2005 and CoNLL-2012). We accomplish this while using the same architecture and hyperparameters for all tasks and even when training a single model to solve all tasks at the same time (multi-task learning). Finally, we show that our framework can also significantly improve the performance in a low-resource regime, thanks to better use of label semantics.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

amazon-research/tanl officialmentioned in papermentioned on GitHubpytorch report
amazon-science/tanl mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Coreference ResolutionDialogue State TrackingEvent ExtractionJoint Entity and Relation ExtractionMulti-Task LearningNamed Entity RecognitionNamed Entity Recognition (NER)Nested Named Entity RecognitionPredictionRelation ClassificationRelation ExtractionSemantic Role LabelingStructured PredictionTranslationcoreference-resolutionnamed-entity-recognition

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Relation Classification TACRED TANL (multi-task) F1 61.9 #3 of 17 Archive leaderboard report
Relation Classification TACRED TANL F1 71.9 #12 of 17 Archive leaderboard report
Relation Extraction CoNLL04 TANL RE+ Micro F1 72.6 #12 of 16 Archive leaderboard report
Relation Extraction TACRED TANL F1 71.9 #15 of 40 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections