Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,53 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
---
|
4 |
+
|
5 |
+
This model is a BERT-based Location Mention Recognition model that is adopted from the [TLLMR4CM GitHub](https://github.com/rsuwaileh/TLLMR4CM/). The model identifies the toponyms' spans in the text without and predicts their location types. The location type can be coarse-grained (e.g., country, city, etc.) and fine-grained (e.g., street, POI, etc.)
|
6 |
+
|
7 |
+
The model is trained using the training splits of all events from [IDRISI-R dataset](https://github.com/rsuwaileh/IDRISI) under the Type-less LMR mode and using the random version of the data. You can download this data in BILOU format from [here](https://github.com/rsuwaileh/IDRISI/tree/main/data/LMR/AR/gold-random-bilou/). More details about the models are available [here](https://github.com/rsuwaileh/IDRISI/tree/main/models).
|
8 |
+
|
9 |
+
|
10 |
+
* Different variants of the model are available through HuggingFace:
|
11 |
+
- [rsuwaileh/IDRISI-LMR-AR-random-typeless](https://huggingface.co/rsuwaileh/IDRISI-LMR-AR-random-typeless/)
|
12 |
+
- [rsuwaileh/IDRISI-LMR-AR-timebased-typeless](https://huggingface.co/rsuwaileh/IDRISI-LMR-AR-timebased-typeless/)
|
13 |
+
- [rsuwaileh/IDRISI-LMR-AR-timebased-typebased](https://huggingface.co/rsuwaileh/IDRISI-LMR-AR-timebased-typebased/)
|
14 |
+
|
15 |
+
* English models are also available:
|
16 |
+
- [rsuwaileh/IDRISI-LMR-EN-random-typeless](https://huggingface.co/rsuwaileh/IDRISI-LMR-EN-random-typeless/)
|
17 |
+
- [rsuwaileh/IDRISI-LMR-EN-random-typebased](https://huggingface.co/rsuwaileh/IDRISI-LMR-EN-random-typebased/)
|
18 |
+
- [rsuwaileh/IDRISI-LMR-EN-timebased-typeless](https://huggingface.co/rsuwaileh/IDRISI-LMR-EN-timebased-typeless/)
|
19 |
+
- [rsuwaileh/IDRISI-LMR-EN-timebased-typebased](https://huggingface.co/rsuwaileh/IDRISI-LMR-EN-timebased-typebased/)
|
20 |
+
|
21 |
+
|
22 |
+
|
23 |
+
To cite the models:
|
24 |
+
|
25 |
+
```
|
26 |
+
@article{suwaileh2022tlLMR4disaster,
|
27 |
+
title={When a Disaster Happens, We Are Ready: Location Mention Recognition from Crisis Tweets},
|
28 |
+
author={Suwaileh, Reem and Elsayed, Tamer and Imran, Muhammad and Sajjad, Hassan},
|
29 |
+
journal={International Journal of Disaster Risk Reduction},
|
30 |
+
year={2022}
|
31 |
+
}
|
32 |
+
|
33 |
+
@inproceedings{suwaileh2020tlLMR4disaster,
|
34 |
+
title={Are We Ready for this Disaster? Towards Location Mention Recognition from Crisis Tweets},
|
35 |
+
author={Suwaileh, Reem and Imran, Muhammad and Elsayed, Tamer and Sajjad, Hassan},
|
36 |
+
booktitle={Proceedings of the 28th International Conference on Computational Linguistics},
|
37 |
+
pages={6252--6263},
|
38 |
+
year={2020}
|
39 |
+
}
|
40 |
+
```
|
41 |
+
|
42 |
+
To cite the IDRISI-R dataset:
|
43 |
+
```
|
44 |
+
@article{rsuwaileh2022Idrisi-r,
|
45 |
+
title={IDRISI-R: Large-scale English and Arabic Location Mention Recognition Datasets for Disaster Response over Twitter},
|
46 |
+
author={Suwaileh, Reem and Elsayed, Tamer and Imran, Muhammad},
|
47 |
+
journal={...},
|
48 |
+
volume={...},
|
49 |
+
pages={...},
|
50 |
+
year={2022},
|
51 |
+
publisher={...}
|
52 |
+
}
|
53 |
+
```
|