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 matching query words to document words, and provides effective multi-level soft matches. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1145/3077136.3080809 | Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval |
Keywords | DocType | Volume |
Ranking, Neural IR, Kernel Pooling, Relevance Model, Embedding | Conference | abs/1706.06613 |
Citations | PageRank | References |
79 | 2.05 | 22 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chen-Yan Xiong | 1 | 405 | 30.82 |
Zhuyun Dai | 2 | 178 | 10.99 |
James P. Callan | 3 | 6237 | 833.28 |
Zhiyuan Liu | 4 | 2037 | 123.68 |
Russell Power | 5 | 606 | 22.82 |