Papers by Mohammed J Zaki

5 papers
HG2Vec: Improved Word Embeddings from Dictionary and Thesaurus Based Heterogeneous Graph (2022.coling-1)

Copied to clipboard

Challenge: Existing models that learn word embeddings rely on a large corpus of data . however, these models require massive time and space for data pre-processing and training .
Approach: They propose a model that learns word embeddings utilizing only dictionaries and thesauri . they exploit a new context-focused loss model that models transitive relationships between word pairs .
Outcome: The proposed model reaches the state-of-art on multiple word similarity and relatedness benchmarks.
Multi-Sense Embeddings for Language Models and Knowledge Distillation (2025.findings-acl)

Copied to clipboard

Challenge: Transformer-based large language models generate different representations for the same token depending on context . however, words and tokens typically have only a limited number of senses . a knowledge distillation method can be used to learn a smaller student model .
Approach: They propose a multi-sense embedding method that uses a clustering algorithm to generate a sense embeddable dictionary.
Outcome: The proposed method offers significant space and inference time savings while maintaining competitive performance.
GVdoc - Graph-based Visual DOcument Classification (2023.findings-acl)

Copied to clipboard

Challenge: Visual document classifiers have shown impressive performance on in-distribution test sets, but they have a hard time classifying out-of-difference examples.
Approach: They propose a graph-based document classification model that generates a document graph based on its layout and trains a neural network to learn node and graph embeddings.
Outcome: The proposed model outperforms state-of-the-art models on out-of distribution data while maintaining comparable performance on in-distribution data.
Food Knowledge Representation Learning with Adversarial Substitution (2022.aacl-main)

Copied to clipboard

Challenge: Knowledge graph embedding (KGE) has been well-studied in general domains, but has not been examined for food computing.
Approach: They propose to use a pre-trained language model to encode entities and relations, emphasizing contextual information in food KGs.
Outcome: The proposed method is able to generate high quality substitutions over a food knowledge graph and provide generalized substitutions to meet different user needs.
KERL: Knowledge-Enhanced Personalized Recipe Recommendation using Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Recent advances in large language models and the abundance of food data have led to studies to improve food understanding using LLMs.
Approach: They propose a unified system that leverages food KGs and LLMs to provide personalized food recommendations and generate recipes with associated micro-nutritional information.
Outcome: The proposed system outperforms existing methods in food recommendation, recipe generation and nutritional analysis.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations