ijazulhaq1's Projects
Belief Revision based Caption Re-ranker with Visual Semantic Information. COLING 2022
Clustering sentence embeddings to extract message intent
Novel model and dataset for the task of humor detection
Data visualization course material
Reads CSV text files and uses a Tfidf vectoriser to semantically cluster like sentences, then uses a hierarchical clustering algorithm to assign the words to n clusters
🐍 Python samples for Google Workspace APIs
SGPT: GPT Sentence Embeddings for Semantic Search
Config files for my GitHub profile.
LaTeX UPC Phd Template. Oxford/Cambridge based LaTeX Phd template with ACL/CVPR conf template inspired modification.
Showing outliers and novelty detection in a datasets, from Scikit-learn
novelty one abstract to others of research papers
Python Natural Language Processing Cookbook, published by Packt
RDV-CNN model for document level novelty detection. Comparision of our model with baselines on three popular datasets.
Review: Deep Learning for Sentence Semantic Similarity
Semantic Relatedness Based Re-ranker for Text Spotting. EMNLP 2019
Comparison of methods based on pre-trained Word2Vec, GloVe and FastText vectors to measure the semantic similarity between sentence pairs
Methods used: Cosine Similarity with Glove, Smooth Inverse Frequency, Word Movers Difference, Sentence Embedding Models (Infersent and Google Sentence Encoder), ESIM with pre-trained FastText embedding. Best performing method on Quora Question pair dataset was an Ensemble method with 0.27 log-loss.
Exploring the simple sentence similarity measurements using word embeddings
Multilingual Sentence & Image Embeddings with BERT
Measuring pairwise sentence similarities using embeddings and clustering
Using simple nltk methods, this model uses stanford's glove.6B.100d word embeddings file and cosine similarity to summarize text from multiple sources on the same topic.
文本聚类(Kmeans、DBSCAN、LDA、Single-pass)
A text classification model based on textGCN and the WikiData knowledge graph
Textual Visual Semantic Dataset for Text Spotting. CVPRW 2020
Code for post blog
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Usage of BERT models for text clustering techniques using sentence embeddings
Visual Re-ranking with Natural Language Understanding for Text Spotting. ACCV18