Papers › Generalizing Natural Language Analysis through Span-relation Representations
Generalizing Natural Language Analysis through Span-relation Representations
Zhengbao Jiang, Wei Xu, Jun Araki, Graham Neubig
Natural language processing covers a wide variety of tasks predicting syntax, semantics, and information content, and usually each type of output is generated with specially designed architectures. In this paper, we provide the simple insight that a great variety of tasks can be represented in a single unified format consisting of labeling spans and relations between spans, thus a single task-independent model can be used across different tasks. We perform extensive experiments to test this insight on 10 disparate tasks spanning dependency parsing (syntax), semantic role labeling (semantics), relation extraction (information content), aspect based sentiment analysis (sentiment), and many others, achieving performance comparable to state-of-the-art specialized models. We further demonstrate benefits of multi-task learning, and also show that the proposed method makes it easy to analyze differences and similarities in how the model handles different tasks. Finally, we convert these datasets into a unified format to build a benchmark, which provides a holistic testbed for evaluating future models for generalized natural language analysis.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
1 archive task tag without a task page not shown.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Constituency Parsing | Penn Treebank | SpanRel | F1 score | 95.5 | #13 of 27 | Archive leaderboard | report |
| Dependency Parsing | Penn Treebank | SpanRel | LAS | 94.70 | #9 of 22 | Archive leaderboard | report |
| Dependency Parsing | Penn Treebank | SpanRel | UAS | 96.44 | #9 of 22 | Archive leaderboard | report |
| Named Entity Recognition (NER) | CoNLL 2003 (English) | SpanRel | F1 | 92.2 | #48 of 73 | Archive leaderboard | report |
| Named Entity Recognition (NER) | WLPC | SpanRel | F1 | 79.2 | #2 of 2 | Archive leaderboard | report |
| Part-Of-Speech Tagging | Penn Treebank | SpanRel | Accuracy | 97.7 | #6 of 20 | Archive leaderboard | report |
| Relation Extraction | SemEval-2010 Task-8 | SpanRel | F1 | 87.4 | #23 of 31 | Archive leaderboard | report |
| Relation Extraction | WLPC | SpanRel | F1 | 65.5 | #1 of 2 | Archive leaderboard | report |
| Semantic Role Labeling (predicted predicates) | CoNLL 2012 | SpanRel | F1 | 82.4 | #5 of 7 | 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.
Methods
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