[图书][B] Pretrained transformers for text ranking: Bert and beyond

J Lin, R Nogueira, A Yates - 2022 - books.google.com
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 …

Learning passage impacts for inverted indexes

A Mallia, O Khattab, T Suel, N Tonellotto - Proceedings of the 44th …, 2021 - dl.acm.org
Neural information retrieval systems typically use a cascading pipeline, in which a first-stage
model retrieves a candidate set of documents and one or more subsequent stages re-rank …

Reduce, reuse, recycle: Green information retrieval research

H Scells, S Zhuang, G Zuccon - … of the 45th International ACM SIGIR …, 2022 - dl.acm.org
Recent advances in Information Retrieval utilise energy-intensive hardware to produce state-
of-the-art results. In areas of research highly related to Information Retrieval, such as Natural …

CC-News-En: A large English news corpus

J Mackenzie, R Benham, M Petri, JR Trippas… - Proceedings of the 29th …, 2020 - dl.acm.org
We describe a static, open-access news corpus using data from the Common Crawl
Foundation, who provide free, publicly available web archives, including a continuous crawl …

Efficient document-at-a-time and score-at-a-time query evaluation for learned sparse representations

J Mackenzie, A Trotman, J Lin - ACM Transactions on Information …, 2023 - dl.acm.org
Researchers have had much recent success with ranking models based on so-called
learned sparse representations generated by transformers. One crucial advantage of this …

Faster learned sparse retrieval with block-max pruning

A Mallia, T Suel, N Tonellotto - … of the 47th International ACM SIGIR …, 2024 - dl.acm.org
Learned sparse retrieval systems aim to combine the effectiveness of contextualized
language models with the scalability of conventional data structures such as inverted …

Faster learned sparse retrieval with guided traversal

A Mallia, J Mackenzie, T Suel, N Tonellotto - Proceedings of the 45th …, 2022 - dl.acm.org
Neural information retrieval architectures based on transformers such as BERT are able to
significantly improve system effectiveness over traditional sparse models such as BM25 …

SpaDE: Improving sparse representations using a dual document encoder for first-stage retrieval

E Choi, S Lee, M Choi, H Ko, YI Song… - Proceedings of the 31st …, 2022 - dl.acm.org
Sparse document representations have been widely used to retrieve relevant documents via
exact lexical matching. Owing to the pre-computed inverted index, it supports fast ad-hoc …

Wacky weights in learned sparse representations and the revenge of score-at-a-time query evaluation

J Mackenzie, A Trotman, J Lin - arxiv preprint arxiv:2110.11540, 2021 - arxiv.org
Recent advances in retrieval models based on learned sparse representations generated by
transformers have led us to, once again, consider score-at-a-time query evaluation …

Streamlining Evaluation with ir-measures

S MacAvaney, C Macdonald, I Ounis - European Conference on …, 2022 - Springer
We present ir-measures, a new tool that makes it convenient to calculate a diverse set of
evaluation measures used in information retrieval. Rather than implementing its own …