lorenzoscottb
commited on
Commit
•
11bd5a5
1
Parent(s):
6e53d58
Update README.md
Browse files
README.md
CHANGED
@@ -17,16 +17,16 @@ widget:
|
|
17 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
18 |
should probably proofread and complete it, then remove this comment. -->
|
19 |
|
20 |
-
#
|
21 |
|
22 |
-
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on
|
23 |
It achieves the following results on the evaluation set:
|
24 |
-
|
25 |
- Accuracy: 0.9043
|
26 |
|
27 |
## Model description
|
28 |
|
29 |
-
|
30 |
|
31 |
## Intended uses & limitations
|
32 |
|
@@ -34,7 +34,7 @@ More information needed
|
|
34 |
|
35 |
## Training and evaluation data
|
36 |
|
37 |
-
|
38 |
|
39 |
## Training procedure
|
40 |
|
@@ -49,13 +49,29 @@ The following hyperparameters were used during training:
|
|
49 |
- lr_scheduler_type: linear
|
50 |
- num_epochs: 1
|
51 |
|
52 |
-
### Training results
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
### Framework versions
|
57 |
|
58 |
- Transformers 4.25.1
|
59 |
- Pytorch 1.12.1
|
60 |
- Datasets 2.5.1
|
61 |
-
- Tokenizers 0.12.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
18 |
should probably proofread and complete it, then remove this comment. -->
|
19 |
|
20 |
+
# BERT for PLANE classification
|
21 |
|
22 |
+
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on one of the PLANE's dataset split (no.2), introduced in [Bertolini et al., COLING 2022](https://aclanthology.org/2022.coling-1.359/)
|
23 |
It achieves the following results on the evaluation set:
|
24 |
+
|
25 |
- Accuracy: 0.9043
|
26 |
|
27 |
## Model description
|
28 |
|
29 |
+
The model is trined to perform a sequence classification task over phrase-level adjective-noun inferences (e.g., "A red car is a vehicle").
|
30 |
|
31 |
## Intended uses & limitations
|
32 |
|
|
|
34 |
|
35 |
## Training and evaluation data
|
36 |
|
37 |
+
The data used for training and testing, as well as the other splits used for the experiments, are available on the paper's git page [here](https://github.com/lorenzoscottb/PLANE)
|
38 |
|
39 |
## Training procedure
|
40 |
|
|
|
49 |
- lr_scheduler_type: linear
|
50 |
- num_epochs: 1
|
51 |
|
|
|
|
|
|
|
|
|
52 |
### Framework versions
|
53 |
|
54 |
- Transformers 4.25.1
|
55 |
- Pytorch 1.12.1
|
56 |
- Datasets 2.5.1
|
57 |
+
- Tokenizers 0.12.1
|
58 |
+
|
59 |
+
# Cite
|
60 |
+
|
61 |
+
if you want to use the model or data in your work please reference the paper too
|
62 |
+
|
63 |
+
```
|
64 |
+
@inproceedings{bertolini-etal-2022-testing,
|
65 |
+
title = "Testing Large Language Models on Compositionality and Inference with Phrase-Level Adjective-Noun Entailment",
|
66 |
+
author = "Bertolini, Lorenzo and
|
67 |
+
Weeds, Julie and
|
68 |
+
Weir, David",
|
69 |
+
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
|
70 |
+
month = oct,
|
71 |
+
year = "2022",
|
72 |
+
address = "Gyeongju, Republic of Korea",
|
73 |
+
publisher = "International Committee on Computational Linguistics",
|
74 |
+
url = "https://aclanthology.org/2022.coling-1.359",
|
75 |
+
pages = "4084--4100",
|
76 |
+
}
|
77 |
+
```
|