End-to-end Neural Ad-hoc Ranking With Kernel Pooling

Abstract

This paper proposes K-NRM, a kernel based neural model for document ranking. Given a query and a set of documents, K-NRM uses a translation matrix that models word-level similarities via word embeddings, a new kernel-pooling technique that uses kernels to extract multi-level soft match features, and a learning-to-rank layer that combines those features into the final ranking score. The whole model is trained end-to-end. The ranking layer learns desired feature patterns from the pairwise ranking loss. The kernels transfer the feature patterns into soft-match targets at each similarity level and enforce them on the translation matrix. The word embeddings are tuned accordingly so that they can produce the desired soft matches. Experiments on a commercial search engine's query log demonstrate the improvements of K-NRM over prior feature-based and neural-based states-of-the-art, and explain the source of K-NRM's advantage: Its kernel-guided embedding encodes a similarity metric tailored for

Stats

• citations336
• S2 citations—
• github stars0
• HF likes0
• heat score18.96
• arxiv keyxiong2017end

Related papers

• Neural Ranking Models For Document Retrieval (2021)11.08
• Neural Ranking Models With Multiple Document Fields (2017)12.74
• Incorporating Query Term Independence Assumption For Efficient Retrieval And Ranking Using Deep Neural Networks (2019)0.00
• QDER: Query-specific Document And Entity Representations For Multi-vector Document Re-ranking (2025)0.00
• Improving Neural Ranking Models With Traditional IR Methods (2023)0.00
• A Deep Look Into Neural Ranking Models For Information Retrieval (2019)17.73
• Evaluation Of Field-aware Neural Ranking Models For Recipe Search (2021)0.00
• Learning To Match Using Local And Distributed Representations Of Text For Web Search (2016)18.09