Using Focal Loss to Fight Shallow Heuristics: An Empirical Analysis of Modulated Cross-Entropy in Natural Language Inference

Forth Assignment in ׳Deep Learning for Texts and Sequences' course by Prof. Yoav Goldberg at Bar-Ilan University

JSNLI (Japanese SNLI) dataset for huggingface datasets

I have prepared a Attention Model for Natural Language Inference.

Semantic Similarity on SNLI dataset using BERT as well as TF-IDF+BERT(Pooled) embeddings.

NLI (MNLI and SNLI) datasets

Investigation of how sampling strategies affect Selective Prediction performance in Multi Task Learning

The objective here is to study the plausibility of attention mechanisms in automatic language processing on an NLI (natural naguage inference) task, in transformers (BERT) architecture

In this repository, we deal with the task of implementing Natural Language Inferencing (NLI) using the SNLI dataset. Different methods such as BiLSTM, BiGRU, Attention models and Logistic Regression are experimented.