Neural information retrieval (IR) has greatly advanced search and other knowledge- intensive language tasks. While many neural IR methods encode queries and documents …
Abstract Knowledge-intensive language tasks require NLP systems to both provide the correct answer and retrieve supporting evidence for it in a given corpus. Autoregressive …
Text retrieval is a long-standing research topic on information seeking, where a system is required to return relevant information resources to user's queries in natural language. From …
The goal of text ranking is to generate an ordered list of texts retrieved from a corpus in response to a query. Although the most common formulation of text ranking is search …
Neural retrievers based on dense representations combined with Approximate Nearest Neighbors search have recently received a lot of attention, owing their success to distillation …
Abstract Evaluation in Information Retrieval (IR) relies on post-hoc empirical procedures, which are time-consuming and expensive operations. To alleviate this, Query Performance …
L Wang, N Yang, F Wei - arXiv preprint arXiv:2303.07678, 2023 - arxiv.org
This paper introduces a simple yet effective query expansion approach, denoted as query2doc, to improve both sparse and dense retrieval systems. The proposed method first …
In neural Information Retrieval (IR), ongoing research is directed towards improving the first retriever in ranking pipelines. Learning dense embeddings to conduct retrieval using …
MIRACL is a multilingual dataset for ad hoc retrieval across 18 languages that collectively encompass over three billion native speakers around the world. This resource is designed to …