Pre-trained transformer models, such as BERT and T5, have shown to be highly effective at
ad hoc passage and document ranking. Due to the inherent sequence length limits of these …

As an alternative to question answering methods based on feature engineering, deep
learning approaches such as convolutional neural networks (CNNs) and Long Short-Term …

Retrieving finer grained text units such as passages or sentences as answers for non-factoid
Web queries is becoming increasingly important for applications such as mobile Web …

Unlike traditional learning to rank models that depend on hand-crafted features, neural
representation learning models learn higher level features for the ranking task by training on …

We formulate a document summarization method to extract passage-level answers for non-
factoid queries, referred to as answer-biased summaries. We propose to use external …

We investigated how users evaluate passage-length answers for non-factoid questions. We
conduct a study where answers were presented to users, sometimes shown with automatic …

We present Contextual Discourse Vectors (CDV), a distributed document representation for
efficient answer retrieval from long healthcare documents. Our approach is based on …

Finding answer passages from the Web is a challenging task. One major difficulty is to
retrieve sentences that may not have many terms in common with the question. In this paper …

Information retrieval systems are evolving from document retrieval to answer retrieval. Web
search logs provide large amounts of data about how people interact with ranked lists of …

Digital mathematical libraries (DMLs) such as arXiv, Numdam, and EuDML contain mainly
documents from STEM fields, where mathematical formulae are often more important than …