BioNLI: Generating a Biomedical NLI Dataset Using Lexico-semantic Constraints for Adversarial Examples

Bastan, Mohaddeseh; Surdeanu, Mihai; Balasubramanian, Niranjan

doi:10.18653/v1/2022.findings-emnlp.374

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Building on the expert-verified claims, melatonin-related abstracts were extensively analyzed. Employing a pattern-matching strategy, statements corresponding to the abstracts’ conclusions were identified 25 . These statements served as the foundation for subsequent data augmentation and paraphrasing steps.…”

Section: Data Set Preparation For Training and Validationmentioning

confidence: 99%

See 1 more Smart Citation

MelAnalyze: Fact-Checking Melatonin claims using Large Language Models and Natural Language Inference

Karkera,

Ghosh,

Escames

et al. 2024

Preprint

View full text Add to dashboard Cite

With the explosion of health related information in mainstream discourse, distinguishing accurate health-related claims from misinformation is important. Using computational tools and algorithms to help is key. Our focus in this paper is on the hormone Melatonin which is claimed to have broad health benefits and largely sold as a supplement. This paper introduces 'MelAnalyze,' a framework for using generative and transformer-based deep learning models adapted as a natural language inference (NLI) task, to semi-automate the fact-checking of general melatonin claims. MelAnalyze is built upon a comprehensive collection of melatonin-related scientific abstracts from PubMed for validation. The framework incorporates components for precise extraction of information from scientific literature, semantic similarity and NLI. At its core, MelAnalyze leverages pre trained NLI models that are fine-tuned on melatonin-specific claims along with semantic search based on vectorized representation of the articles. The best models, fine-tuned on LLaMA1 and RoBERTa, attain good precision, recall, and F1-scores of approximately 0.92. We also introduce a user-friendly web-based tool for fact-checking algorithm evaluation and use. In summary, we show MelAnalyze's role in empowering users and researchers to assess melatonin-related claims using evidence-based decision-making.

show abstract

Section: Data Set Preparation For Training and Validationmentioning

confidence: 99%

“…These statements served as the foundation for subsequent data augmentation and paraphrasing steps. To enhance diversity, a pre-trained NLP paraphrasing model was employed to generate paraphrased statement 26 and negation statements 25 .…”

Section: Data Set Preparation For Training and Validationmentioning

confidence: 99%

MelAnalyze: Fact-Checking Melatonin claims using Large Language Models and Natural Language Inference

Karkera,

Ghosh,

Escames

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Medc2l: Compound-Word Analysis and Inference System for Japanese Clinical Texts

Ishida,

Yanaka,

Bekki

2023

Journal of Natural Language Processing

View full text Add to dashboard Cite

The increasing number of clinical texts, such as electronic medical records and discharge summaries, has led to ongoing research on natural language processing in the medical field. Since medical compound words often appear in clinical texts, in-depth semantic analysis and natural language inference tasks for clinical text are challenging. In this study, we developed a semantic analysis and logical inference system for

show abstract

BioNLI: Generating a Biomedical NLI Dataset Using Lexico-semantic Constraints for Adversarial Examples

Cited by 2 publications

References 0 publications

MelAnalyze: Fact-Checking Melatonin claims using Large Language Models and Natural Language Inference

MelAnalyze: Fact-Checking Melatonin claims using Large Language Models and Natural Language Inference

Medc2l: Compound-Word Analysis and Inference System for Japanese Clinical Texts

Contact Info

Product

Resources

About