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

Neural networks provide new possibilities to automatically learn complex language patterns and query-document relations. Neural IR models have achieved promising results in learning querydocument relevance patterns, but few explorations have been done on understanding the text content of a query or a document. This paper studies leveraging a recently-proposed contextual neural language model, BERT, to provide deeper text understanding for IR. Experimental results demonstrate that the contextual text representations from BERT are more effective than traditional word embeddings. Compared to bag-of-words retrieval models, the contextual language model can better leverage language structures, bringing large improvements on queries written in natural languages. Combining the text understanding ability with search knowledge leads to an enhanced pre-trained BERT model that can benefit related search tasks where training data are limited.

The proliferation of searchable text databases on corporate networks and the Internet causes a database selection problem for many people. Algorithms such a s gGlOSS and CORI can automatically select which text databases to search for a given information need, but only if given a set of resource descriptions that accurately represent the contents of each database. The existing techniques for acquiring resource descriptions have signi cant limitations when used in wide area networks controlled by m a n y parties.This paper presents query-based sampling, a new technique for acquiring accurate resource descriptions. Query-basedsampling does not require the cooperationof resource providers nor does it require that resource providers use a particular search engine or representation technique. An extensive set of experimental results demonstrates that accurate resource descriptions are created, that computation and communication costs are reasonable, and that the resource descriptions do in fact enable accurate automatic database selection.

A m ulti-database model of distributed information retrieval is presented, in which people are assumed to have access to many searchable text databases. In such a n e n vironment, full-text information retrieval consists of discovering database contents, ranking databases by their expected ability to satisfy the query, s e a r c hing a small number of databases, and merging results returned by di erent databases. This paper presents algorithms for each task. It also discusses how to reorganize conventional test collections into multi-database testbeds, and evaluation methodologies for multi-database experiments. A broad and diverse group of experimental results is presented to demonstrate that the algorithms are e ective, e cient, robust, and scalable.