Numeric Fused-Head
Introduced by Elazar et al. in Where's My Head? Definition, Dataset and Models for Numeric Fused-Heads Identification and Resolution
The Numeric Fused-Head dataset consists of ~10K examples of crowd-sourced classified examples, labeled into 7 different categories, from two types. In the first type, Reference, the missing head is referenced explicitly somewhere else in the discourse, either in the same sentence or in surrounding sentences. In the second type, Implicit, the missing head does not appear in the text and needs to be inferred by the reader or hearer based on the context or world knowledge. This category was labeled into the 6 most common categories of the dataset. Models are evaluated based on accuracy.
Source: NLP ProgressBenchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
Numeric Fused-Head (dev)
|
Bi-LSTM + Scoring + Elmo
|
|||
|
Numeric Fused-Head (test)
|
Bi-LSTM + Scoring + Elmo
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
