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 …
Y Sun, S Wang, S Feng, S Ding, C Pang… - arXiv preprint arXiv …, 2021 - arxiv.org
Pre-trained models have achieved state-of-the-art results in various Natural Language Processing (NLP) tasks. Recent works such as T5 and GPT-3 have shown that scaling up …
Much recent research on information retrieval has focused on how to transfer from one task (typically with abundant supervised data) to various other tasks where supervision is limited …
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 …
Y Qu, Y Ding, J Liu, K Liu, R Ren, WX Zhao… - arXiv preprint arXiv …, 2020 - arxiv.org
In open-domain question answering, dense passage retrieval has become a new paradigm to retrieve relevant passages for finding answers. Typically, the dual-encoder architecture is …
L Xiong, C Xiong, Y Li, KF Tang, J Liu… - arXiv preprint arXiv …, 2020 - arxiv.org
Conducting text retrieval in a dense learned representation space has many intriguing advantages over sparse retrieval. Yet the effectiveness of dense retrieval (DR) often requires …
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 …
O Khattab, M Zaharia - Proceedings of the 43rd International ACM SIGIR …, 2020 - dl.acm.org
Recent progress in Natural Language Understanding (NLU) is driving fast-paced advances in Information Retrieval (IR), largely owed to fine-tuning deep language models (LMs) for …
Z Yang - arXiv preprint arXiv:1906.08237, 2019 - fq.pkwyx.com
With the capability of modeling bidirectional contexts, denoising autoencoding based pretraining like BERT achieves better performance than pretraining approaches based on …