Update README.md
Browse files
README.md
CHANGED
@@ -32,11 +32,11 @@ adapter_name = model.load_adapter("allenai/specter2_aug2023refresh", source="hf"
|
|
32 |
|
33 |
**\*\*\*\*\*\*Update\*\*\*\*\*\***
|
34 |
|
35 |
-
This update introduces a new set of
|
36 |
-
For benchmarking purposes please use the existing
|
37 |
|
38 |
-
#
|
39 |
-
|
40 |
This is the base model to be used along with the adapters.
|
41 |
Given the combination of title and abstract of a scientific paper or a short texual query, the model can be used to generate effective embeddings to be used in downstream applications.
|
42 |
|
@@ -48,7 +48,7 @@ Given the combination of title and abstract of a scientific paper or a short tex
|
|
48 |
|
49 |
## Model Description
|
50 |
|
51 |
-
|
52 |
Post that it is trained with additionally attached task format specific adapter modules on all the [SciRepEval](https://huggingface.co/datasets/allenai/scirepeval) training tasks.
|
53 |
|
54 |
Task Formats trained on:
|
@@ -72,9 +72,9 @@ It builds on the work done in [SciRepEval: A Multi-Format Benchmark for Scientif
|
|
72 |
|
73 |
<!-- Provide the basic links for the model. -->
|
74 |
|
75 |
-
- **Repository:** [https://github.com/allenai/
|
76 |
- **Paper:** [https://api.semanticscholar.org/CorpusID:254018137](https://api.semanticscholar.org/CorpusID:254018137)
|
77 |
-
- **Demo:** [Usage](https://github.com/allenai/
|
78 |
|
79 |
# Uses
|
80 |
|
@@ -165,9 +165,9 @@ We also evaluate and establish a new SoTA on [MDCR](https://github.com/zoranmedi
|
|
165 |
|[SPECTER](https://huggingface.co/allenai/specter)|54.7|57.4|68.0|(30.6, 25.5)|
|
166 |
|[SciNCL](https://huggingface.co/malteos/scincl)|55.6|57.8|69.0|(32.6, 27.3)|
|
167 |
|[SciRepEval-Adapters](https://huggingface.co/models?search=scirepeval)|61.9|59.0|70.9|(35.3, 29.6)|
|
168 |
-
|[
|
169 |
|
170 |
-
Please cite the following works if you end up using
|
171 |
|
172 |
[SPECTER paper](https://api.semanticscholar.org/CorpusID:215768677):
|
173 |
|
|
|
32 |
|
33 |
**\*\*\*\*\*\*Update\*\*\*\*\*\***
|
34 |
|
35 |
+
This update introduces a new set of SPECTER2 models with the base transformer encoder pre-trained on an extended citation dataset containing more recent papers.
|
36 |
+
For benchmarking purposes please use the existing SPECTER2 [models](https://huggingface.co/allenai/specter2) w/o the **aug2023refresh** suffix.
|
37 |
|
38 |
+
# SPECTER2 (Base)
|
39 |
+
SPECTER2 is the successor to [SPECTER](https://huggingface.co/allenai/specter) and is capable of generating task specific embeddings for scientific tasks when paired with [adapters](https://huggingface.co/models?search=allenai/specter-2_).
|
40 |
This is the base model to be used along with the adapters.
|
41 |
Given the combination of title and abstract of a scientific paper or a short texual query, the model can be used to generate effective embeddings to be used in downstream applications.
|
42 |
|
|
|
48 |
|
49 |
## Model Description
|
50 |
|
51 |
+
SPECTER2 has been trained on over 6M triplets of scientific paper citations, which are available [here](https://huggingface.co/datasets/allenai/scirepeval/viewer/cite_prediction_new/evaluation).
|
52 |
Post that it is trained with additionally attached task format specific adapter modules on all the [SciRepEval](https://huggingface.co/datasets/allenai/scirepeval) training tasks.
|
53 |
|
54 |
Task Formats trained on:
|
|
|
72 |
|
73 |
<!-- Provide the basic links for the model. -->
|
74 |
|
75 |
+
- **Repository:** [https://github.com/allenai/SPECTER2](https://github.com/allenai/SPECTER2)
|
76 |
- **Paper:** [https://api.semanticscholar.org/CorpusID:254018137](https://api.semanticscholar.org/CorpusID:254018137)
|
77 |
+
- **Demo:** [Usage](https://github.com/allenai/SPECTER2/blob/main/README.md)
|
78 |
|
79 |
# Uses
|
80 |
|
|
|
165 |
|[SPECTER](https://huggingface.co/allenai/specter)|54.7|57.4|68.0|(30.6, 25.5)|
|
166 |
|[SciNCL](https://huggingface.co/malteos/scincl)|55.6|57.8|69.0|(32.6, 27.3)|
|
167 |
|[SciRepEval-Adapters](https://huggingface.co/models?search=scirepeval)|61.9|59.0|70.9|(35.3, 29.6)|
|
168 |
+
|[SPECTER2-Adapters](https://huggingface.co/models?search=allenai/specter-2)|**62.3**|**59.2**|**71.2**|**(38.4, 33.0)**|
|
169 |
|
170 |
+
Please cite the following works if you end up using SPECTER2:
|
171 |
|
172 |
[SPECTER paper](https://api.semanticscholar.org/CorpusID:215768677):
|
173 |
|