Name
Abstract | ||
|---|---|---|
The problem of entity-typing has been studied predominantly in supervised learning fashion, mostly with task-specific annotations (for coarse types) and sometimes with distant supervision (for fine types). While such approaches have strong performance within datasets, they often lack the flexibility to transfer across text genres and to generalize to new type taxonomies. In this work we propose a zero-shot entity typing approach that requires no annotated data and can flexibly identify newly defined types. Given a type taxonomy defined as Boolean functions of FREEBASE "types", we ground a given mention to a set of type-compatible Wikipedia entries and then infer the target mention's types using an inference algorithm that makes use of the types of these entries. We evaluate our system on a broad range of datasets, including standard fine-grained and coarse-grained entity typing datasets, and also a dataset in the biological domain. Our system is shown to be competitive with state-of-the-art supervised NER systems and outperforms them on out-of-domain datasets. We also show that our system significantly outperforms other zero-shot fine typing systems. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.18653/v1/d18-1231 | EMNLP |
Field | DocType | Volume |
Boolean function,Computer science,Inference,Supervised learning,Ground,Typing,Natural language processing,Artificial intelligence,Machine learning | Conference | D18-1 |
Citations | PageRank | References |
2 | 0.36 | 0 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ben Zhou | 1 | 6 | 2.46 |
| Daniel Khashabi | 2 | 114 | 15.14 |
| Chen-Tse Tsai | 3 | 56 | 8.14 |
| Dan Roth | 4 | 7735 | 695.19 |