Papers by Choon Hui Teo
A Representation Sharpening Framework for Zero Shot Dense Retrieval (2026.eacl-long)
Copied to clipboard
| Challenge: | Zero-shot dense retrieval requires generic, pretrained DRs, which struggle to represent semantic differences between similar documents. |
| Approach: | They propose a training-free representation sharpening framework that augments a document’s representation with information that helps differentiate it from similar documents in the corpus. |
| Outcome: | The proposed framework is compatible with prior approaches to zero-shot dense retrieval and consistently improves their performance. |
Learning to Rewrite Negation Queries in Product Search (2025.coling-industry)
Copied to clipboard
| Challenge: | Negations in product search are often used to articulate unwanted product features or components. |
| Approach: | They propose a query rewriting approach to enhance product search performance . they use large language models to extract query reawrites from product text . their results pave the way for further research on enhancing search performance of queries with negations . |
| Outcome: | The proposed approach improves search performance by 3.17% for queries with negations. |
MICO: Selective Search with Mutual Information Co-training (2022.coling-1)
Copied to clipboard
| Challenge: | Selective search is designed to reduce the latency and computation in modern large-scale search systems. |
| Approach: | They propose a mutual information CO-training framework for selective search with minimal supervision using the search logs. |
| Outcome: | The proposed framework outperforms existing competitive benchmarks on multiple metrics and significantly outperformed existing baselines. |