language:
- en
tags:
- mental-health
license: Apache 2.0
datasets:
- PubMed
Psych-Search
Model description
This model is an extension of allenai/scibert_scivocab_uncased. Continued pretraining was done using SciBERT as the base model using abstract text only from Pyschology and Psychiatry PubMed research. Training was done on approximately 3.5 million papers for 10 epochs and evaluated on a task similar to BioASQ Task A.
Intended uses & limitations
How to use
from transformers import AutoTokenizer, AutoModel
mname = "datawrestler/psych-search"
tokenizer = AutoTokenizer.from_pretrained(mname)
model = AutoModel.from_pretrained(mname)
Limitations and bias
This model was trained on all PubMed abstracts categorized under Psychology and Psychiatry. As of March 1, this corresponded to approximately 3.2 million papers that contained abstract text. Of these 3.2 million papers, relevant sparse categories were back translated to increase the representation of sparser mental health categories. This included backtranslating the following:
Training data
This model was trained on all PubMed abstracts categorized under Psychology and Psychiatry. As of March 1, this corresponded to approximately 3.2 million papers that contained abstract text. Of these 3.2 million papers, relevant sparse categories were back translated from english to french and from french to english to increase the representation of sparser mental health categories. This included backtranslating the following papers with the following categories:
- Female
- Adult
- Middle Aged
- Depressive Disorder
- Risk Factors
- Mental Disorders
- Child, Preschool
- Mental Health
In aggregate, this process added 557,980 additional papers to our training data.
Training procedure
Continued pretraining was on Psychology and Psychiatry PubMed papers for 10 epochs. Default parameters were used with the exception of gradient accumulation steps which was set at 4, with a per device train batch size of 32. 2 x Nvidia 3090's were used in the development of this model.
Eval results
To evaluate the utility of psych-search within the mental health domain, an evaluation task was constructed by finetuning psych-search for a task similar to BioASQ Task A. Here we perform large scale biomedical indexing using the MESH taxonomy associated with each paper underneath Psychology and Psychiatry. The evaluation metric is the micro F1 score across all second level descriptors under Psychology and Psychiatry. This corresponds to 38 different MESH categories used during evaluation.
| bert-base-uncased | SciBERT Scivocab Uncased | Psych-Search |
|---|---|---|
| 0.7348 | 0.7394 | 0.7415 |