Name
Abstract | ||
|---|---|---|
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. |
Year | Venue | Keywords |
|---|---|---|
2021 | EMNLP | Information extraction,Language model,Task (project management),F1 score,Natural language processing,Computer science,Translation (geometry),Suite,Zero (linguistics),Simple (abstract algebra),Artificial intelligence |
DocType | Volume | Citations |
Conference | 2021.emnlp-main | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Chenguang Wang | 1 | 0 | 0.34 |
| Xiao Liu | 2 | 0 | 0.34 |
| Zui Chen | 3 | 0 | 1.01 |
| Haoyun Hong | 4 | 0 | 0.68 |
| Jie Tang | 5 | 5871 | 300.22 |
| Dawn Song | 6 | 7084 | 442.36 |