Multi-stage ranking pipelines have been a practical solution in modern search systems,
where the first-stage retrieval is to return a subset of candidate documents and latter stages …

This paper provides an extensive and thorough overview of the models and techniques
utilized in the first and second stages of the typical information retrieval processing chain …

This paper outlines a conceptual framework for understanding recent developments in
information retrieval and natural language processing that attempts to integrate dense and …

Recent advances in neural language models have contributed new methods for learning
distributed vector representations of words (also called word embeddings). Two such …

Recently, neural networks have been successfully employed to improve upon state-of-the-
art effectiveness in ad-hoc retrieval tasks via machine-learned ranking functions. While …

A new methodology based on language models retrieves product features and opinions
from a collection of free-text customer reviews about a product or service. The proposal …

Case law retrieval is the retrieval of judicial decisions relevant to a legal question. Case law
retrieval comprises a significant amount of a lawyer's time, and is important to ensure …

Traditional retrieval models such as BM25 or language models have been engineered
based on search heuristics that later have been formalized into axioms. The axiomatic …

We consider the problem of re-ranking the top-k documents returned by a retrieval system
given some search query. This setting is common to learning-to-rank scenarios, and it is …

Thee KL divergence is the most commonly used measure for comparing query and
document language models in the language modeling framework to ad hoc retrieval. Since …