metadata

license: apache-2.0
datasets:
  - allenai/scirepeval
language:
  - en

SPECTER 2.0

SPECTER 2.0 is the successor to 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.

Model Details

Model Description

SPECTER 2.0 has been trained on over 6M triplets of scientific paper citations, which are available here. Post that it is trained on all the SciRepEval training tasks, with task format specific adapters.

Task Formats trained on:

Classification
Regression
Proximity
Adhoc Search

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 [optional]: allenai/scibert.

Model Sources [optional]

Repository: [https://github.com/allenai/SPECTER2_0] (https://github.com/allenai/SPECTER2_0)
Paper [optional]: https://api.semanticscholar.org/CorpusID:254018137
Demo [optional]: [Usage] (https://github.com/allenai/SPECTER2_0/blob/main/README.md)

Uses

Direct Use

Model	Type	Name and HF link
Base	Transformer	allenai/specter_plus_plus
Classification	Adapter	allenai/spp_classification
Regression	Adapter	allenai/spp_regression
Retrieval	Adapter	allenai/spp_proximity
Adhoc Query	Adapter	allenai/spp_adhoc_query

from transformers import AutoTokenizer, AutoModel

# load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained('allenai/specter_plus_plus')

#load base model
model = AutoModel.from_pretrained('allenai/specter_plus_plus')

#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/spp_adhoc_query", source="hf", load_as="adhoc_query", 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 [optional]

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)
SPECTER 2.0-base	56.3	58.0	69.2	(38.0, 32.4)
SPECTER 2.0-Adapters	62.3	59.2	71.2	(38.4, 33.0)

Please cite the following works if you end up using SPECTER 2.0:

SPECTER paper:

@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}
}

SciRepEval paper

@article{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},
  journal={ArXiv},
  year={2022},
  volume={abs/2211.13308}
}