Arian Askari's Projects
Extensive Open-Source Guides for Android Developers
On Anonymous Commenting: A Greedy Approach to Balance Utilization and Anonymity for Instagram Users - Accepted at SIGIR 2019
This dataset contains human judgements about answer equivalence. The data is based on SQuAD (Stanford Question Answering Dataset), and contains 9k human judgements of answer candidates generated by Albert on the SQuAD train set, and an additional 14k human judgements for answer candidates produced by BiDAF, Luke, and XLNet on the SQuAD dev set.
The offial repository for Answer Retrieval in Legal Community Question Answering - accepted at ECIR 2024
My online CV
Repo accompanying paper for modeling fine grained similarity between documents.
Differentially Private Synthetic Data via Foundation Model APIs 2: Text
AVocaDo : Strategy for Adapting Vocabulary to Downstream Domain
A curated list of awesome papers related to pre-trained models for information retrieval (a.k.a., pretraining for IR).
Answer Equivalence BEM score example in PyTorch using Huggingface Tokenizer
Code for the IJCAI2020 submission: "BERT-PLI: Modeling Paragraph-Level Interactions for Legal Case Retrieval"
8-bit CUDA functions for PyTorch
:black_circle: A spaCy pipeline and model for NLP on unstructured legal text.
Evolution of word vectors from long, sparse, and 1-hot to short, dense, and context sensitive
A modular library built on top of Keras and TensorFlow to generate a caption in natural language for any input image.
A dataset for training/evaluating Question Answering Retrieval models on ChatGPT responses with the possibility to training/evaluating on real human responses.
Claude API Test Project
Contrastive Noise Embeddings (CNE) for dimensionality reduction and clustering
A simple Python sandbox for helpful LLM data agents
Simple Hacks for Google Colaboratory to boost your productivity and help you to perform daily tasks.
ColBERT25
Code to reproduce NeuralMind's submissions to COLIEE 2021
EMNLP 2021 - Pre-training architectures for dense retrieval