Hugging Face's logo

sapienzanlp
/
maverick-mes-preco

English
coreference-resolution
Eval Results
Model card Files Community
g185 commited on
Commit
db674ce
•
1 Parent(s): 3536ff7

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +75 -0
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+
3
+ language:
4
+ - en
5
+ tags:
6
+ - coreference-resolution
7
+ license:
8
+ - cc-by-nc-sa-4.0
9
+ datasets:
10
+ - PreCo
11
+ metrics:
12
+ - CoNLL
13
+ task_categories:
14
+ - coreference-resolution
15
+ model-index:
16
+ - name: sapienzanlp/maverick-mes-preco
17
+ results:
18
+ - task:
19
+ type: coreference-resolution
20
+ name: coreference-resolution
21
+ dataset:
22
+ name: preco
23
+ type: coreference
24
+ metrics:
25
+ - name: Avg. F1
26
+ type: CoNLL
27
+ value: 87.4
28
+
29
+ ---
30
+
31
+
32
+ # Maverick mes PreCo
33
+ Official weights for *Maverick-mes* trained on PreCo and based on DeBERTa-large.
34
+ This model achieves 87.4 Avg CoNLL-F1 on PreCo coreference resolution dataset.
35
+
36
+ Other available models at [SapienzaNLP huggingface hub](https://huggingface.co/collections/sapienzanlp/maverick-coreference-resolution-66a750a50246fad8d9c7086a):
37
+
38
+ | hf_model_name | training dataset | Score | Singletons |
39
+ |:-----------------------------------:|:----------------:|:-----:|:----------:|
40
+ | ["sapienzanlp/maverick-mes-ontonotes"](https://huggingface.co/sapienzanlp/maverick-mes-ontonotes) | OntoNotes | 83.6 | No |
41
+ | ["sapienzanlp/maverick-mes-litbank"](https://huggingface.co/sapienzanlp/maverick-mes-litbank) | LitBank | 78.0 | Yes |
42
+ | ["sapienzanlp/maverick-mes-preco"](https://huggingface.co/sapienzanlp/maverick-mes-preco) | PreCo | 87.4 | Yes |
43
+ <!-- | ["sapienzanlp/maverick-s2e-ontonotes"](https://huggingface.co/sapienzanlp/maverick-mes-preco) | OntoNotes | 83.4 | No | No | -->
44
+ <!-- | "sapienzanlp/maverick-incr-ontonotes" | Ontonotes | 83.5 | No | No | -->
45
+ <!-- | "sapienzanlp/maverick-mes-ontonotes-base" | Ontonotes | 81.4 | No | No | -->
46
+ <!-- | "sapienzanlp/maverick-s2e-ontonotes-base" | Ontonotes | 81.1 | No | No | -->
47
+ <!-- | "sapienzanlp/maverick-incr-ontonotes-base" | Ontonotes | 81.0 | No | No | -->
48
+ <!-- | "sapienzanlp/maverick-s2e-litbank" | LitBank | 77.6 | Yes | No | -->
49
+ <!-- | "sapienzanlp/maverick-incr-litbank" | LitBank | 78.3 | Yes | No | -->
50
+ <!-- | "sapienzanlp/maverick-s2e-preco" | PreCo | 87.2 | Yes | No | -->
51
+ <!-- | "sapienzanlp/maverick-incr-preco" | PreCo | 88.0 | Yes | No | -->
52
+ N.B. Each dataset has different annotation guidelines, choose your model according to your use case.
53
+
54
+
55
+ ## Maverick: Efficient and Accurate Coreference Resolution Defying recent trends
56
+
57
+ [![Conference](https://img.shields.io/badge/ACL%202024%20Paper-red)](https://arxiv.org/pdf/2407.21489)
58
+ [![License: CC BY-NC 4.0](https://img.shields.io/badge/License-CC%20BY--NC%204.0-green.svg)](https://creativecommons.org/licenses/by-nc/4.0/)
59
+ [![Pip Package](https://img.shields.io/badge/🐍%20Python%20package-blue)](https://pypi.org/project/maverick-coref/)
60
+ [![git](https://img.shields.io/badge/Git%20Repo%20-yellow.svg)](https://github.com/SapienzaNLP/maverick-coref)
61
+
62
+ ### Citation
63
+
64
+ ```
65
+ @inproceedings{martinelli-etal-2024-maverick,
66
+ title = "Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trends",
67
+ author = "Martinelli, Giuliano and
68
+ Barba, Edoardo and
69
+ Navigli, Roberto",
70
+ booktitle = "Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL 2024)",
71
+ year = "2024",
72
+ address = "Bangkok, Thailand",
73
+ publisher = "Association for Computational Linguistics",
74
+ }
75
+ ```