There are 1 repository under squad-dataset topic.
Important paper implementations for Question Answering using PyTorch
BERT based pretrained model using SQuAD 2.0 Dataset for Question-Answering
NLP-CHATBOT
Question answering system developed using seq2seq modeling - The SQuAD dataset.
Implementation of a Dynamic Coattention Network proposed by Xiong et al.(2017) for Question Answering, learning to find answers spans in a document, given a question, using the Stanford Question Answering Dataset (SQuAD2.0).
MRC question and answer approach using NLP and machine learning techniques
A context based question answering system trained on the SQUAD 2.0 dataset
A project about fine-tuning bert-base-uncased model for reading comprehension tasks.
Question Answering using BERT pre-trained model and fine-tuning it on various datasets (SQuAD, TriviaQA, NewsQ, Natural Questions, QuAC)
Sentence Bert for Question-Answering on COVID-19 Open Research Dataset (CORD-19)
Initially implement Document-Retrieval-System with SBERT embeddings and evaluate it in CORD-19 dataset. Afterwards, fine tune BERT model with SQuAD.v2 dataset so as to evaluate it in Question Answering task.
Sentiment Classifier using: Softmax-Regression, Feed-Forward Neural Network, Bidirectional stacked LSTM/GRU Recursive Neural Network, fine-tuning on BERT pre-trained model. Question Answering using BERT pre-trained model and fine-tuning it on various datasets (SQuAD, TriviaQA, NewsQ, Natural Questions, QuAC)
Machine Comprehension on Squad Dataset using Match-LSTM + Ans-Ptr Network
A personal implementation of "Adversarial Examples for Evaluating Reading Comprehension Systems".
Assignment for DS525 - Natural Language Processing
Tutorial of Question Answering using SQuAD in English and Spanish with BERT and BiDAF.
DistilBERT question-answering fine-tuned on SQuAD1.1
This project showcases how to fine-tune a HuggingFace model with the SQuAD dataset and create a Gradio interface for interactive question answering, enabling users to input context and questions and receive model-generated answers.