SproutRAG
SproutRAG is a retrieval-augmented generation stack built for structured, multi-granularity evidence. It combines hierarchical attention-based indexing with flexible retrieval, optional reranking, and generation pipelines.
Possibly Available
About
Amirhossein Abaskohi | Computer Science PhD Student @ UBC | امیرحسین عباسکوهی
Evidence-backed skills
Repositories
Automatic-Speech-recognition-for-Speech-Assessment-of-Persian-Preschool-Children
Preschool evaluation is crucial because it gives teachers and parents influential knowledge about children's growth and development. The COVID-19 pandemic has highlighted the necessity of online assessment for preschool children. One of the areas that should be tested is their ability to speak. Employing an Automatic Speech Recognition (ASR) system would not help since they are pre-trained on voices that differ from children's in terms of frequency and amplitude. Because most of these are pre-trained with data in a specific range of amplitude, their objectives do not make them ready for voices in different amplitudes. To overcome this issue, we added a new objective to the masking objective of the Wav2Vec 2.0 model called Random Frequency Pitch (RFP). In addition, we used our newly introduced dataset to fine-tune our model for Meaningless Words (MW) and Rapid Automatic Naming (RAN) tests. Using masking in concatenation with RFP outperforms the masking objective of Wav2Vec 2.0 by reaching a Word Error Rate (WER) of 1.35. Our new approach reaches a WER of 6.45 on the Persian section of the CommonVoice dataset. Furthermore, our novel methodology produces positive outcomes in zero- and few-shot scenarios.
Gossip-Protocol
This is an implementation of Gossip Protocol in c++ language.
SemEval2022-Task6-Sarcasm-Detection
Sarcasm is a term that refers to the use of words to mock, irritate, or amuse someone. It is commonly used on social media. The metaphorical and creative nature of sarcasm presents a significant difficulty for sentiment analysis systems based on affective computing. The technique and results of our team, UTNLP, in the SemEval-2022 shared task 6 on sarcasm detection are presented in this paper.
Beyond-Words-A-Multimodal-Exploration-of-Persuasion-in-Memes
Beyond Words: A Multimodal Exploration of Persuasion in Memes
MCompassRAG
MCompassRAG is a metadata-guided retrieval framework that uses topic-level signals as a semantic compass for paragraph-level RAG. It enriches chunks with topic metadata and trains a lightweight retriever through LLM-teacher distillation, enabling topic-aware retrieval at inference time.
LM-CPPF
The official implementation of the ACL 2023 paper, "Paraphrasing-Guided Data Augmentation for Contrastive Prompt-based Few-shot Fine-tuning".
Transformers-Tutorial
Welcome to my Transformers tutorial series! In this series, I'll be diving into the powerful Transformer architecture and its implementation in TensorFlow and PyTorch. Whether you're an experienced NLP practitioner or just starting out, I hope you'll find the series informative and engaging.
VAE-based-Joint-Image-and-Caption-Generation
This repository contains my research internship code at the University of Illinois Chicago under the supervision of Prof. Pedram Rooshenas.
PythonCodeGenerator
Here is a GAN model which is trained on the repositories of Github python projects to generate python code.
Voice-Recognition
This is a simple voice recognition system based on speech command dataset. This is done using CNNs.
ACM-Summer-School-2021-AI
This repository contains for ACM Summer School 2021's AI course's materials at the University of Tehran.