Papers by Yash Saxena

2 papers
IMRNNs: An Efficient Method for Interpretable Dense Retrieval via Embedding Modulation (2026.findings-eacl)

Copied to clipboard

Challenge: Existing dense retrieval methods rely on static embeddings that obscure bidirectional relationship between queries and documents.
Approach: They propose a framework that augments any black-box dense retrievers with dynamic, bidirectional modulation at inference time.
Outcome: a new framework augments any dense retriever with dynamic, bidirectional modulation at inference time.
Schema Aware Semantic Reasoning for Interpreting Natural Language Queries in Enterprise Settings (2020.coling-main)

Copied to clipboard

Challenge: Using ontology reasoning to understand natural language is a challenge for QA systems . a recent study shows that ontologies can improve natural language understanding .
Approach: They propose to use ontology reasoning to translate natural language interpretation into a sequence of solvable tasks by an ontologist.
Outcome: The proposed framework achieves better natural language understanding with a 30% accuracy improvement over the current state of natural language query interfaces.

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