Papers › Autoregressive Structured Prediction with Language Models

Autoregressive Structured Prediction with Language Models

26 Oct 2022arXiv:2210.14698archive 2025-07-28

Tianyu Liu, Yuchen Jiang, Nicholas Monath, Ryan Cotterell, Mrinmaya Sachan

Recent years have seen a paradigm shift in NLP towards using pretrained language models ({PLM}) for a wide range of tasks. However, there are many difficult design decisions to represent structures (e.g. tagged text, coreference chains) in a way such that they can be captured by PLMs. Prior work on structured prediction with PLMs typically flattens the structured output into a sequence, which limits the quality of structural information being learned and leads to inferior performance compared to classic discriminative models. In this work, we describe an approach to model structures as sequences of actions in an autoregressive manner with PLMs, allowing in-structure dependencies to be learned without any loss. Our approach achieves the new state-of-the-art on all the structured prediction tasks we looked at, namely, named entity recognition, end-to-end relation extraction, and coreference resolution.

PaperPDFCode

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

Code

lyutyuh/asp officialmentioned in papermentioned on GitHubpytorchMIT 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 ResolutionNamed Entity RecognitionNamed Entity Recognition (NER)PredictionRelation ExtractionStructured Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Coreference Resolution CoNLL 2012 ASP+T0-3B Avg F1 82.3 #4 of 18 Archive leaderboard report
Coreference Resolution OntoNotes ASP+T0-3B F1 82.3 #3 of 26 Archive leaderboard report
Named Entity Recognition (NER) CoNLL 2003 (English) ASP+T5-3B F1 94.1 #5 of 73 Archive leaderboard report
Named Entity Recognition (NER) CoNLL 2003 (English) ASP+flan-T5-large F1 93.8 #11 of 73 Archive leaderboard report
Relation Extraction ACE 2005 ASP+T5-3B Cross Sentence Yes #3 of 30 Archive leaderboard report
Relation Extraction ACE 2005 ASP+T5-3B NER Micro F1 91.3 #3 of 30 Archive leaderboard report
Relation Extraction ACE 2005 ASP+T5-3B RE Micro F1 72.7 #3 of 30 Archive leaderboard report
Relation Extraction ACE 2005 ASP+T5-3B RE+ Micro F1 70.5 #3 of 30 Archive leaderboard report
Relation Extraction ACE 2005 ASP+T5-3B Sentence Encoder T5-3B #3 of 30 Archive leaderboard report
Relation Extraction CoNLL04 ASP+T0-3B NER Micro F1 90.3 #10 of 16 Archive leaderboard report
Relation Extraction CoNLL04 ASP+T0-3B RE+ Micro F1 76.3 #10 of 16 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