msadat3/SciNLI

The dataset and code for ACL 2022 paper "SciNLI: A Corpus for Natural Language Inference on Scientific Text" are released here.

22
/ 100
Experimental

This project provides a specialized dataset and tools for evaluating how well AI models understand the logical relationships between sentences in scientific papers. It takes pairs of sentences from NLP and computational linguistics research papers and labels their semantic relationship (e.g., entailment, contradiction, neutral). Researchers and developers working on AI models for scientific text analysis would use this to benchmark and improve their models' comprehension.

No commits in the last 6 months.

Use this if you are developing or evaluating Natural Language Understanding (NLU) models specifically for scientific literature and need a benchmark dataset tailored to the unique language and structure of academic papers.

Not ideal if your NLU tasks involve general conversational or everyday language, as this dataset is highly specialized for formal scientific text.

scientific-text-analysis natural-language-inference computational-linguistics-research academic-paper-analysis AI-model-evaluation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 7 / 25

How are scores calculated?

Stars

28

Forks

2

Language

Python

License

Last pushed

Oct 17, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/msadat3/SciNLI"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.