Papers by Kee Kiat Koo

2 papers
Deep Metric Learning to Hierarchically Rank - An Application in Product Retrieval (2023.emnlp-industry)

Copied to clipboard

Challenge: e-commerce search engines use customer behavior signals to augment lexical matching and improve search relevance.
Approach: They propose a method to identify duplicate and near-duplicate products across stores . they use Hierarchical Ranked Multi Similarity Loss to learn hierarchical metric space .
Outcome: The proposed model outperforms baselines in terms of catalog coverage and precision of the mappings.
Structured Object Language Modeling (SO-LM): Native Structured Objects Generation Conforming to Complex Schemas with Self-Supervised Denoising (2024.emnlp-industry)

Copied to clipboard

Challenge: Structured objects generation is a challenging problem for existing Large Language Models.
Approach: They propose a self-supervised method to train an LLM to perform the task natively without prompt-engineering.
Outcome: The proposed method matches or outperforms prompt-engineered state-of-the-art models while being more cost-efficient.

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