Arian Askari's repositories
EF_in_Legal_CQA
Expert Finding in Legal Community Question Answering - Accepted at ECIR 2022.
custom_linux_shell_with_cpp
Custom linux shell with cpp
persian_news_websites_crawler
Crawler (Scraper) for several well-known persian news for scraping public data
anonymous-comment
On Anonymous Commenting: A Greedy Approach to Balance Utilization and Anonymity for Instagram Users - Accepted at SIGIR 2019
avocado
AVocaDo : Strategy for Adapting Vocabulary to Downstream Domain
entity_tasks_deep
Implementation of CNN-based models for entity target type identification
answer-equivalence-dataset
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.
awesome-pretrained-models-for-information-retrieval
A curated list of awesome papers related to pre-trained models for information retrieval (a.k.a., pretraining for IR).
convert-tf
Impementation of ConveRT (Conversational Representations from Transformers) paper in Tensorflow.
detect-gpt
DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature
direct-preference-optimization
Reference implementation for DPO (Direct Preference Optimization)
Directional-Stimulus-Prompting
Codebase for the paper: "Guiding Large Language Models with Directional Stimulus Prompting"
dlkp
A deep learning library for identifying keyphrases from text
examples
Home for Elasticsearch examples available to everyone. It's a great way to get started.
finBERT
Financial Sentiment Analysis with BERT
GenRead
Code and Checkpoints for "Generate rather than Retrieve: Large Language Models are Strong Context Generators" in ICLR 2023.
inPars
Inquisitive Parrots for Search
lex-glue
LexGLUE: A Benchmark Dataset for Legal Language Understanding in English
Parrot_Paraphraser
A practical and feature-rich paraphrasing framework to augment human intents in text form to build robust NLU models for conversational engines. Created by Prithiviraj Damodaran. Open to pull requests and other forms of collaboration.
pke
Python Keyphrase Extraction module
RL4LMs
A modular RL library to fine-tune language models to human preferences
RLHF
Collection of links, tutorials and best practices of how to collect the data and build end-to-end RLHF system to finetune Generative AI models
rq-vae-transformer
The official implementation of Autoregressive Image Generation using Residual Quantization (CVPR '22)
sentence-transformers_for_msmarco
Multilingual Sentence & Image Embeddings with BERT