# Adapter allenai/specter2_adhoc_query for allenai/specter2

An adapter for the allenai/specter2 model that was trained on the allenai/scirepeval dataset.

## Usage

First, install adapter-transformers:

pip install -U adapter-transformers


Note: adapter-transformers is a fork of transformers that acts as a drop-in replacement with adapter support. More

from transformers import AutoAdapterModel



## 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.

• Classification
• Regression
• Proximity

This is the adhoc search query specific adapter. For tasks where papers have to retrieved for a short textual query, use this adapter to encode the query and allenai/specter2_proximity to encode the candidates.

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
• Finetuned from model [optional]: allenai/scibert.

# Uses

## Direct Use

Model Type Name and HF link
Base Transformer allenai/specter2
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained('allenai/specter2')

model = AutoModel.from_pretrained('allenai/specter2')

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
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:

@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}
}