Papers by Nishant Yadav
Efficient k-NN Search with Cross-Encoders using Adaptive Multi-Round CUR Decomposition (2023.findings-emnlp)
Copied to clipboard
| Challenge: | ANNCUR uses a cross-encoder only to perform k-NN search, but the approximation of the distances is often detrimental to the retrieval of top-k items. |
| Approach: | They propose a method that minimizes approximation error for k-nearest neighbor searches . they propose to use a cross-encoder only to perform k NN search . |
| Outcome: | The proposed method reduces approximation error for top-k neighbors by up to 70% . iteratively performs k-NN search using the available anchors, then adds them to the next set . |
Clustering-based Inference for Biomedical Entity Linking (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing approaches to linking entities ignore relationships between entities in biomedical knowledge bases. |
| Approach: | They propose a model which can link mentions of unseen entities using learned representations of entities. |
| Outcome: | The proposed model improves on the largest publicly available biomedical dataset by 3.0 points of accuracy and 2.3 points of reliability. |
Efficient Nearest Neighbor Search for Cross-Encoder Models using Matrix Factorization (2022.emnlp-main)
Copied to clipboard
| Challenge: | Efficient k-nearest neighbor search is a fundamental task, foundational for many problems in NLP. |
| Approach: | They propose an approach that avoids the use of a dual-encoder for retrieval, relying solely on the cross-encoding model. |
| Outcome: | Empirically, for k > 10, our approach provides test-time recall-vs-computational cost trade-offs superior to the current widely-used methods that re-rank items retrieved using a dual-encoder or TF-IDF. |
Clustering-based Sampling for Few-Shot Cross-Domain Keyphrase Extraction (2024.findings-eacl)
Copied to clipboard
| Challenge: | Scientific domain-specific pre-training has led to state-of-the-art keyphrase extraction performance with a majority of benchmarks being within the domain. |
| Approach: | They propose to leverage topic information available in the data to build a clustering-based sampling approach that facilitates selecting a few samples to label from the target domain . |
| Outcome: | The proposed approach leads to 26.35 points in performance when compared to selecting few-shot samples uniformly at random. |