Data enrichment with experimental results of the paper 'Two is Better than Many? Binary Classification as an Effective Approach to Multi-Choice Question Answering'
-
Updated
Mar 19, 2024 - Python
8000
Data enrichment with experimental results of the paper 'Two is Better than Many? Binary Classification as an Effective Approach to Multi-Choice Question Answering'
Kaggle NLP competition - Top 2% solution (36/2060)
Solutions to US patents phrase matching Kaggle competition https://www.kaggle.com/competitions/us-patent-phrase-to-phrase-matching
This repository contains the code for submission made at SemEval 2022 Task 5: MAMI
Scraping paper data, preprocessed and trained using BERT variants, deployment and an integration to website
Can you spot automatically generated scientific excerpts?
Automated-Essay-Scoring-Systems-with-NLP-Models
Some experiments to compare the performances of some pre-trained transformer models on a basic sentiment regression task
A PyTorch Library for Sequence Labeling Tasks such as Named-entity Recognition or Part-of-speech Tagging
Finetuning Large Language Models
Multi-label toxic-comment classifier (DeBERTa v3, Kaggle Jigsaw Challenge) — portfolio demo.
The code of Hierarchical Multi-label Classification (HMC). It is a final course project of Natural Language Processing and Deep Learning, 2022 Fall.
Interactive Web app for multilingual question answering using state-of-the-art Transformer models (BERT, DistilBERT, RoBERTa, DeBERTa, and multilingual BERT) for English and Arabic. Compare answers, try sample data, and explore chatbot-ready features.
Document Clustering, Summarisation and Visualisation on 20NewsGroup
This project focuses on the Tachygraphy analysis i.e. Micro-Text analysis using Deep Learning techniques. The primary goal is to predict the simplified, expanded text from shorthand forms often found in casual digital communication. Additionally, the project aims to extract sentiments, emotions, personality traits, and other relevant information.
In this demo, we illustrate the the possibility of using Semantic Search + Recognising Textual Entailment with Gradio to build an automated fact checking tool
Implementing science-related multiple-choice question answering based on LLMs and RAG.
The implementation of DeBERTaV3-based commonsense question answering on CommonsenseQA.
Add a description, image, and links to the deberta topic page so that developers can more easily learn about it.
To associate your repository with the deberta topic, visit your repo's landing page and select "manage topics."