|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
This paper provides a unified account of two schools of thinking in information retrieval modelling: the generative retrieval focusing on predicting relevant documents given a query, and the discriminative retrieval focusing on predicting relevancy given a query-document pair.
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.
We explore several new models for document relevance ranking, building upon the Deep Relevance Matching Model (DRMM) of Guo et al. (2016).
#10 best model for Ad-Hoc Information Retrieval on TREC Robust04
Models such as latent semantic analysis and those based on neural embeddings learn distributed representations of text, and match the query against the document in the latent semantic space.
In this work, we propose a standalone neural ranking model (SNRM) by introducing a sparsity property to learn a latent sparse representation for each query and document.
#3 best model for Ad-Hoc Information Retrieval on TREC Robust04
We call this joint approach CEDR (Contextualized Embeddings for Document Ranking).
Neural IR models, such as DRMM and PACRR, have achieved strong results by successfully capturing relevance matching signals.