princeton-nlp/NLProofS
EMNLP 2022: Generating Natural Language Proofs with Verifier-Guided Search https://arxiv.org/abs/2205.12443
This project helps researchers and developers working with natural language inference by generating human-readable logical proofs. You provide a statement or claim and the system produces a series of logical steps, demonstrating how the conclusion is reached. This is ideal for those who need to understand the reasoning process behind an AI's judgment on textual entailment.
No commits in the last 6 months.
Use this if you need to generate step-by-step natural language explanations for why a given text supports a specific conclusion, especially in complex reasoning tasks.
Not ideal if you are looking for a general-purpose natural language generation tool or a system that works with unstructured, conversational text outside of formal logical reasoning.
Stars
86
Forks
15
Language
Python
License
MIT
Category
Last pushed
Sep 15, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/princeton-nlp/NLProofS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
nlpcloud/nlpcloud-python
NLP Cloud serves high performance pre-trained or custom models for NER, sentiment-analysis,...
ysymyth/ec-nl
[ICLR 2022] Linking Emergent and Natural Languages via Corpus Transfer
L-Zhe/CoRPG
Code for paper Document-Level Paraphrase Generation with Sentence Rewriting and Reordering by...
IBM/regen
official code for EMNLP21 paper
AndyChiangSH/CDGP
Code for Findings of EMNLP 2022 short paper "CDGP: Automatic Cloze Distractor Generation based...