BAT - Biomedical Augmentation for Text

Keywords: Data augmentation, Neuro-Symbolic AI, NLP, LLM, UMLS

A Toolkit for Biomedical Text Augmentation

Package Overview

This Python package consists of a Neuro-Symbolic pipeline, blending knowledge-driven and data-driven approaches.

Pipeline Components

Knowledge-Based perturbation (knowledge-driven): * Med-synonym replacement: Replaces medical terms with one of their formalized synonyms from structured domain knowledge (UMLS Metathesaurus). * General synonym replacement: Replaces terms with one of their general-purpose synonyms from Wordnet.

Transformer-Based perturbation (data-driven): * Back-translation: Translates text into an intermediate language and then back into the original language using multilingual MT models. * Contextual word prediction: Fills in masked single-token words within the input text based on the in-context predictions from BERT-based language models. * Rephrasing: Rewrites text using the capabilities of LLMs.

Requirements

1. Unified Medical Language System (UMLS) License:
2. Mandatory for using the Med-synonym replacement component.
3. Optional for the General synonym replacement.
4. LLM Functional Block:
5. A functional block with any preferred (open source or proprietary) LLM must be configured to use the Rephrasing component.
6. Alternatively, you can use the default gpt-4o-mini model by providing your personal API key.

Installation

1. Make sure you have the latest version of pip installed sh pip install --upgrade pip
2. Install BiomedicalAugmentation-for-Text through pip sh pip install --index-url https://test.pypi.org/simple/ --no-deps BiomedicalAugmentation-for-Text

Usage

Here is a minimal example of how the BAT package can be invoked with BiomedicalAugmentation-for-Text. 1. Through the AugmentedSample class: A compact and streamlined interface that integrates all components into a cohesive workflow. ```python from bioTextAugPackage.init import * import bioTextAugPackage.augmentedsample as augsample

config = Config() inputtext = "No lytic lesions are observed at the vertebral levels included in the scans. No signs of listhesis." augmentedsample = augsample.AugmentedSample(configparams=config, techniquetag="TB-backtranslation", srcdata=inputtext, srclang="english", nsynthdata=5) ans = augmentedsample.run() ```

1. By invoking individual functions: Provides more control and flexibility to apply specific components independently. ```python from bioTextAugPackage.init import * import bioTextAugPackage.transformerbasedfunctions as tb import bioTextAugPackage.metrics as metrics

config = Config() input_text = "No lytic lesions are observed at the vertebral levels included in the scans. No signs of listhesis."

srclang = "en" trglang = "fr"

mtmodelname1 = f"Helsinki-NLP/opus-mt-{srclang}-{trglang}" mtmodel1 = AutoModelForSeq2SeqLM.frompretrained(mtmodelname1) mttokenizer1 = AutoTokenizer.frompretrained(mtmodelname1)

mtmodelname2 = f"Helsinki-NLP/opus-mt-{trglang}-{srclang}" mtmodel2 = AutoModelForSeq2SeqLM.frompretrained(mtmodelname2) mttokenizer2 = AutoTokenizer.frompretrained(mtmodelname2, cleanuptokenization_spaces=True)

ans = tb.backtranslation(srctext=inputtext, model1=mtmodel1, tokenizer1=mttokenizer1, model2=mtmodel2, tokenizer2=mt_tokenizer2)

print(ans) overlapscore = metrics.computeoverlap(syntheticdata=ans[0], srcdata=inputtext, tokenizer=config.basetokenizer) similarityscore = metrics.computesimilarity(syntheticdata=ans[0], srcdata=inputtext, semodelname=config.semodelname) print(f"overlapscore: {overlapscore} - similarityscore: {similarity_score}") ```

A more extensive example, including advanced usage, can be found in this notebook.

Contacts and Useful Links

• Repository maintainer: Laura Bergomi
  

• Project Link: https://github.com/bmi-labmedinfo/BAT

• Package Link: https://test.pypi.org/project/BiomedicalAugmentation-for-Text/

License

Distributed under MIT License. See LICENSE