Mitigating a language model's over-confidence with NLI predictions on Multi-NLI hypotheses with random word order using PAWS (paraphrase) and Winogrande (anaphora).
-
Updated
May 28, 2024 - Jupyter Notebook
Mitigating a language model's over-confidence with NLI predictions on Multi-NLI hypotheses with random word order using PAWS (paraphrase) and Winogrande (anaphora).
✨ Build AI interfaces that spark joy
Probing handling of verbal probabilities in NLP models
A PyTorch Based Deep Learning Quick Develop Framework. One-Stop for train/predict/server/demo
XNLIeu: a dataset for cross-lingual NLI in Basque
An AI assistant for a Learning Management System (LMS)
BERT and RoBERTa models fine-tuned on the MNLI dataset, optimized for binary entailment/non-entailment classification. Additionally, their performance is explored in handling figurative language.
PhoBERT: Pre-trained language models for Vietnamese (EMNLP-2020 Findings)
A Natural Language Inference (NLI) model based on Transformers (BERT and ALBERT)
Natural Language Understanding and Response engine. Semantic parser and execution engine. With DBPedia and SHRDLU demo's.
Testing Theory of Mind (ToM) in language models with epistemic logic
[EMNLP2022] BioNLI: Generating a Biomedical NLI Dataset Using Lexico-semantic Constraints for Adversarial Examples
Prove Ducth NLI problems of SICK-NL with LangPro
Tableau-based Theorem Prover for Natural Logic and Language
The dataset and code for ACL 2022 paper "SciNLI: A Corpus for Natural Language Inference on Scientific Text" are released here.
Welcome to the Neural Language Interface (NLI) Explain project! This repository is dedicated to exploring and explaining the decision-making process of BERT models in the context of Natural Language Inference (NLI) tasks. We employ Feature Interaction methods to shed light on why BERT makes specific predictions in NLI.
unsupervised creation of contradictory, entailing sentences from a given premise for SNLI tasks.
Assignments and projects from the interpretable natural language processing course offered at the University of Tehran.
Add a description, image, and links to the nli topic page so that developers can more easily learn about it.
To associate your repository with the nli topic, visit your repo's landing page and select "manage topics."