Update README.md
Browse files
README.md
CHANGED
|
@@ -27,10 +27,26 @@ Here you can find our NER models:
|
|
| 27 |
|
| 28 |
[3] **BI-BI Problem**: Building training corpus when entities from the same type appear in sequence, labeled as continuations of one another.
|
| 29 |
|
| 30 |
-
[4] **Classic**: which types
|
| 31 |
-
|
| 32 |
For example, the text "讛讗专讬 驻讜讟专 讜专讜谉 讜讜讬讝诇讬" would tagged as **SINGLE** entity. That problem prevent the model to extract entities correctly.
|
| 33 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
# Results
|
| 35 |
We test our models on the **IAHALT test set**. We also check another models, such as [DictaBert](https://huggingface.co/dicta-il/dictabert) and [HeBert](https://huggingface.co/avichr/heBERT). This is the performence results:
|
| 36 |
|
|
|
|
| 27 |
|
| 28 |
[3] **BI-BI Problem**: Building training corpus when entities from the same type appear in sequence, labeled as continuations of one another.
|
| 29 |
|
|
|
|
|
|
|
| 30 |
For example, the text "讛讗专讬 驻讜讟专 讜专讜谉 讜讜讬讝诇讬" would tagged as **SINGLE** entity. That problem prevent the model to extract entities correctly.
|
| 31 |
|
| 32 |
+
[4] **Classic**: The classic NER types:
|
| 33 |
+
|
| 34 |
+
| entity type | full name | examples |
|
| 35 |
+
|:-----------:|:---------:| --------:|
|
| 36 |
+
| **TIMEX** | Time Expression | 1945, 砖谞转 1993, 讬讜诐 讛砖讜讗讛, 砖谞讜转 讛-90 |
|
| 37 |
+
| **GPE** | Geopolitical Entity | 讙专诪谞讬讛, 驻讜诇讬谉, 讘专诇讬谉, 讜讜专砖讛 |
|
| 38 |
+
| **PER** | Person | 讗讚讜诇祝 讛讬讟诇专, 专讜讚讜诇祝 讛住, 诪专讚讻讬 讗谞讬诇讘讬抓 |
|
| 39 |
+
| **LOC** | Location | 诪讝专讞 讗讬专讜驻讛, 讗讙谉 讛讬诐 讛转讬讻讜谉, 讛讙诇讬诇 |
|
| 40 |
+
| **TTL** | Title | 驻讬讛专专, 拽讬住专, 诪谞讻"诇 |
|
| 41 |
+
| **ANG** | Language | 注讘专讬转, 注专讘讬转, 讙专诪谞讬转 |
|
| 42 |
+
| **DUC** | Product | 驻讬讬住讘讜拽, F-16, 转谞讜讘讛 |
|
| 43 |
+
| **WOA** | Work of Art | 讚讜"讞 诪讘拽专 讛诪讚讬谞讛, 注讬转讜谉 讛讗专抓, 讛讗专讬 驻讜讟专, 转讬拽 2000, |
|
| 44 |
+
| **EVE** | Event | 讛砖讜讗讛, 诪诇讞诪转 讛注讜诇诐 讛砖谞讬讬讛, 砖诇讟讜谉 讛讗驻专讟讛讬讬讚 |
|
| 45 |
+
| **MISC** | Miscellaneous聽 | 拽讜专讜谞讛, 讛转讜 讛讬专讜拽, 诪讚诇讬转 讝讛讘, 讘讬讟拽讜讬谉 |
|
| 46 |
+
| **ORG** | Organization | 讛-SS, 驻讚"诐, 诪诪砖诇转 讞讜祝 讛砖谞讛讘 |
|
| 47 |
+
| **FAC** | Facility | 讗讜讜砖讜讜讬抓, 诪讙讚诇讬 讛转讗讜诪讬诐, 谞转讘"讙 2000, 专讞讜讘 拽驻诇谉 |
|
| 48 |
+
|
| 49 |
+
|
| 50 |
# Results
|
| 51 |
We test our models on the **IAHALT test set**. We also check another models, such as [DictaBert](https://huggingface.co/dicta-il/dictabert) and [HeBert](https://huggingface.co/avichr/heBERT). This is the performence results:
|
| 52 |
|