3 papers
cs.IR2026
The Wisdom of Many Queries: Complexity-Diversity Principle for Dense Retriever Training
Xincan Feng, Noriki Nishida, Yusuke Sakai +1
Synthetic query generation has become essential for training dense retrievers, yet prior methods generate one query per document, focusing solely on query quality. We are the first…
cs.LG2026
When Does Embedding Magnitude Matter? A Cross-Task Functional-Symmetry Framework
Xincan Feng, Taro Watanabe
Cosine similarity normalizes both sides; dot product normalizes neither. We propose a 2x2 framework that independently controls query-side and document-side normalization, exposing…
cs.CL2024
Unified Interpretation of Smoothing Methods for Negative Sampling Loss Functions in Knowledge Graph Embedding
Xincan Feng, Hidetaka Kamigaito, Katsuhiko Hayashi +1
Knowledge Graphs (KGs) are fundamental resources in knowledge-intensive tasks in NLP. Due to the limitation of manually creating KGs, KG Completion (KGC) has an important role in a…