SPECTER2
SPECTER2 is a family of models that succeeds SPECTER and is capable of generating task specific embeddings for scientific tasks when paired with adapters. 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.
Note:For general embedding purposes, please use allenai/specter2.
To get the best performance on a downstream task type please load the associated adapter () with the base model as in the example below.
Dec 2023 Update:
Model usage updated to be compatible with latest versions of transformers and adapters (newly released update to adapter-transformers) libraries.
******Update******
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. For benchmarking purposes please use the existing SPECTER2 models w/o the aug2023refresh suffix.
Adapter allenai/specter2_aug2023refresh
for allenai/specter2_aug2023refresh_base
An adapter for the allenai/specter2_aug2023refresh_base model that was trained on the allenai/scirepeval dataset.
This adapter was created for usage with the adapters library.
Usage
First, install adapters
:
pip install -U adapters
Note: adapters is built as an add-on to transformers that acts as a drop-in replacement with adapter support. More
Now, the adapter can be loaded and activated like this:
from adapters import AutoAdapterModel
model = AutoAdapterModel.from_pretrained("allenai/specter2_aug2023refresh_base")
adapter_name = model.load_adapter("allenai/specter2_aug2023refresh", source="hf", set_active=True)
Model Details
Model Description
SPECTER2 has been trained on over 6M triplets of scientific paper citations, which are available here. Post that it is trained with additionally attached task format specific adapter modules on all the SciRepEval training tasks.
Task Formats trained on:
- Classification
- Regression
- Proximity
- Adhoc Search
This is a retrieval specific adapter. For tasks where given a paper query, other relevant papers have to be retrieved from a corpus, use this adapter to generate the embeddings.
It builds on the work done in SciRepEval: A Multi-Format Benchmark for Scientific Document Representations and we evaluate the trained model on this benchmark as well.
- Developed by: Amanpreet Singh, Mike D'Arcy, Arman Cohan, Doug Downey, Sergey Feldman
- Shared by : Allen AI
- Model type: bert-base-uncased + adapters
- License: Apache 2.0
- Finetuned from model: allenai/scibert.
Model Sources
- Repository: https://github.com/allenai/SPECTER2
- Paper: https://api.semanticscholar.org/CorpusID:254018137
- Demo: Usage
Uses
Direct Use
Model | Name and HF link | Description |
---|---|---|
Proximity* | allenai/specter2_aug2023refresh | Encode papers as queries and candidates eg. Link Prediction, Nearest Neighbor Search |
Adhoc Query | allenai/specter2_aug2023refresh_adhoc_query | Encode short raw text queries for search tasks. (Candidate papers can be encoded with the proximity adapter) |
Classification | allenai/specter2_aug2023refresh_classification | Encode papers to feed into linear classifiers as features |
Regression | allenai/specter2_aug2023refresh_regression | Encode papers to feed into linear regressors as features |
*Proximity model should suffice for downstream task types not mentioned above
from transformers import AutoTokenizer
from adapters import AutoAdapterModel
# load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained('allenai/specter2_aug2023refresh_base')
#load base model
model = AutoAdapterModel.from_pretrained('allenai/specter2_aug2023refresh_base')
#load the adapter(s) as per the required task, provide an identifier for the adapter in load_as argument and activate it
model.load_adapter("allenai/specter2_aug2023refresh", source="hf", load_as="specter2_proximity", set_active=True)
papers = [{'title': 'BERT', 'abstract': 'We introduce a new language representation model called BERT'},
{'title': 'Attention is all you need', 'abstract': ' The dominant sequence transduction models are based on complex recurrent or convolutional neural networks'}]
# concatenate title and abstract
text_batch = [d['title'] + tokenizer.sep_token + (d.get('abstract') or '') for d in papers]
# preprocess the input
inputs = self.tokenizer(text_batch, padding=True, truncation=True,
return_tensors="pt", return_token_type_ids=False, max_length=512)
output = model(**inputs)
# take the first token in the batch as the embedding
embeddings = output.last_hidden_state[:, 0, :]
Downstream Use
For evaluation and downstream usage, please refer to https://github.com/allenai/scirepeval/blob/main/evaluation/INFERENCE.md.
Training Details
Training Data
The base model is trained on citation links between papers and the adapters are trained on 8 large scale tasks across the four formats. All the data is a part of SciRepEval benchmark and is available here.
The citation link are triplets in the form
{"query": {"title": ..., "abstract": ...}, "pos": {"title": ..., "abstract": ...}, "neg": {"title": ..., "abstract": ...}}
consisting of a query paper, a positive citation and a negative which can be from the same/different field of study as the query or citation of a citation.
Training Procedure
Please refer to the SPECTER paper.
Training Hyperparameters
The model is trained in two stages using SciRepEval:
- Base Model: First a base model is trained on the above citation triplets.
batch size = 1024, max input length = 512, learning rate = 2e-5, epochs = 2 warmup steps = 10% fp16
- Adapters: Thereafter, task format specific adapters are trained on the SciRepEval training tasks, where 600K triplets are sampled from above and added to the training data as well.
batch size = 256, max input length = 512, learning rate = 1e-4, epochs = 6 warmup = 1000 steps fp16
Evaluation
We evaluate the model on SciRepEval, a large scale eval benchmark for scientific embedding tasks which which has [SciDocs] as a subset. We also evaluate and establish a new SoTA on MDCR, a large scale citation recommendation benchmark.
Model | SciRepEval In-Train | SciRepEval Out-of-Train | SciRepEval Avg | MDCR(MAP, Recall@5) |
---|---|---|---|---|
BM-25 | n/a | n/a | n/a | (33.7, 28.5) |
SPECTER | 54.7 | 57.4 | 68.0 | (30.6, 25.5) |
SciNCL | 55.6 | 57.8 | 69.0 | (32.6, 27.3) |
SciRepEval-Adapters | 61.9 | 59.0 | 70.9 | (35.3, 29.6) |
SPECTER2-Adapters | 62.3 | 59.2 | 71.2 | (38.4, 33.0) |
Please cite the following works if you end up using SPECTER2:
@inproceedings{specter2020cohan,
title={{SPECTER: Document-level Representation Learning using Citation-informed Transformers}},
author={Arman Cohan and Sergey Feldman and Iz Beltagy and Doug Downey and Daniel S. Weld},
booktitle={ACL},
year={2020}
}
@inproceedings{Singh2022SciRepEvalAM,
title={SciRepEval: A Multi-Format Benchmark for Scientific Document Representations},
author={Amanpreet Singh and Mike D'Arcy and Arman Cohan and Doug Downey and Sergey Feldman},
booktitle={Conference on Empirical Methods in Natural Language Processing},
year={2022},
url={https://api.semanticscholar.org/CorpusID:254018137}
}
- Downloads last month
- 326