25 citations · 36 across the 13 of their papers we have counts for
6 papers · 1 filter
IERL: Interpretable Ensemble Representation Learning -- Combining CrowdSourced Knowledge and Distributed Semantic Representations
Yuxin Zi, Kaushik Roy, Vignesh Narayanan +2
Large Language Models (LLMs) encode meanings of words in the form of distributed semantics. Distributed semantics capture common statistical patterns among language tokens (words,…
Knowledge-Infused Self Attention Transformers
Kaushik Roy, Yuxin Zi, Vignesh Narayanan +2
Transformer-based language models have achieved impressive success in various natural language processing tasks due to their ability to capture complex dependencies and contextual…
Process Knowledge-infused Learning for Clinician-friendly Explanations
Kaushik Roy, Yuxin Zi, Manas Gaur +4
Language models have the potential to assess mental health using social media data. By analyzing online posts and conversations, these models can detect patterns indicating mental…
Cook-Gen: Robust Generative Modeling of Cooking Actions from Recipes
Revathy Venkataramanan, Kaushik Roy, Kanak Raj +4
As people become more aware of their food choices, food computation models have become increasingly popular in assisting people in maintaining healthy eating habits. For example, f…
Knowledge Graph Guided Semantic Evaluation of Language Models For User Trust
Kaushik Roy, Tarun Garg, Vedant Palit +3
A fundamental question in natural language processing is - what kind of language structure and semantics is the language model capturing? Graph formats such as knowledge graphs are…
KSAT: Knowledge-infused Self Attention Transformer -- Integrating Multiple Domain-Specific Contexts
Kaushik Roy, Yuxin Zi, Vignesh Narayanan +2
Domain-specific language understanding requires integrating multiple pieces of relevant contextual information. For example, we see both suicide and depression-related behavior (mu…