Papers › Zero-Shot Information Extraction as a Unified Text-to-Triple Translation

Zero-Shot Information Extraction as a Unified Text-to-Triple Translation

23 Sep 2021EMNLP 2021 11arXiv:2109.11171archive 2025-07-28

Chenguang Wang, Xiao Liu, Zui Chen, Haoyun Hong, Jie Tang, Dawn Song

We cast a suite of information extraction tasks into a text-to-triple translation framework. Instead of solving each task relying on task-specific datasets and models, we formalize the task as a translation between task-specific input text and output triples. By taking the task-specific input, we enable a task-agnostic translation by leveraging the latent knowledge that a pre-trained language model has about the task. We further demonstrate that a simple pre-training task of predicting which relational information corresponds to which input text is an effective way to produce task-specific outputs. This enables the zero-shot transfer of our framework to downstream tasks. We study the zero-shot performance of this framework on open information extraction (OIE2016, NYT, WEB, PENN), relation classification (FewRel and TACRED), and factual probe (Google-RE and T-REx). The model transfers non-trivially to most tasks and is often competitive with a fully supervised method without the need for any task-specific training. For instance, we significantly outperform the F1 score of the supervised open information extraction without needing to use its training set.

PaperPDFConference PDFCode

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

Code

cgraywang/deepex officialmentioned in papermentioned on GitHubpytorchApache-2.0 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

Factual probeLanguage ModelingLanguage ModellingOpen Information ExtractionRelation ClassificationTranslation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Open Information Extraction NYT DeepEx (zero-shot) AUC 72.5 #4 of 4 Archive leaderboard report
Open Information Extraction NYT DeepEx (zero-shot) F1 85.5 #4 of 4 Archive leaderboard report
Open Information Extraction OIE2016 DeepEx (zero-shot) AUC 58.6 #1 of 12 Archive leaderboard report
Open Information Extraction OIE2016 DeepEx (zero-shot) F1 72.6 #1 of 12 Archive leaderboard report
Open Information Extraction Penn Treebank DeepEx (zero-shot) AUC 81.5 #3 of 4 Archive leaderboard report
Open Information Extraction Penn Treebank DeepEx (zero-shot) F1 88.5 #3 of 4 Archive leaderboard report
Open Information Extraction Web DeepEx (zero-shot) AUC 82.4 #4 of 4 Archive leaderboard report
Open Information Extraction Web DeepEx (zero-shot) F1 91.2 #4 of 4 Archive leaderboard report
Relation Classification FewRel DeepEx (zero-shot top-1) F1 48.8 #4 of 5 Archive leaderboard report
Relation Classification FewRel DeepEx (zero-shot top-10) F1 92.9 #5 of 5 Archive leaderboard report
Relation Classification TACRED DeepEx (zero-shot top-1) F1 49.2 #2 of 17 Archive leaderboard report
Relation Classification TACRED DeepEx (zero-shot top-10) F1 76.4 #16 of 17 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