finetune the language model for task of natural language inference

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.

Bachelor Thesis comparing two Relation-Inference Datasets

Implementation of the semi-structured inference model in our ACL 2020 paper. INFOTABS: Inference on Tables as Semi-structured Data

Probing handling of verbal probabilities in NLP models

Lexical Entailment Augmented Network for Natural Language Inference

We augmented an already existing BERT Tiny Transformer network designed to train the Google NQ dataset to randomly sample some of the tokens in a question with its synonyms. The idea comes from the process of image data augmentation used in computer vision pipelines. This experiment directly tackles the concepts of Natural Language Inference and…

[EMNLP2022] BioNLI: Generating a Biomedical NLI Dataset Using Lexico-semantic Constraints for Adversarial Examples

Keras implementation of ESIM model for Natural Language Inference.

Project on a Natural Language Processing (NLP) task known as Natural Language Inference (NLI) for the Bahasa Indonesia language.

Re-implementation of BIMPM(Bilateral Multi-Perspective Matching for Natural Language Sentences)

This repository is an implementation of Paper "Robust Natural Language Inference Models with Example Forgetting", which studies importance of forgettable example in making robust NLI Models

NLI using BiLSTM and Logistic regression (using tf-idf features)

XNLIeu: a dataset for cross-lingual NLI in Basque

"Understanding Dataset Difficulty with V-Usable Information" (ICML 2022, outstanding paper) - AIC FEE CTU NLP group's customized version for NLI with XLM-RoBERTa Large in Czech language.

Assignments and projects from the interpretable natural language processing course offered at the University of Tehran.

Different demos of semantic parser models, plays related to different state-of-the-art models in converting natural language questions to structured queries such as SQL

Implementation of models in our EMNLP 2019 paper: A Logic-Driven Framework for Consistency of Neural Models

My honest solution to the Contradictory, My Dear Watson Kaggle competition focused at NLI.