[图书][B] Pretrained transformers for text ranking: Bert and beyond
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 …
response to a query. Although the most common formulation of text ranking is search …
REALTIME QA: what's the answer right now?
We introduce RealTime QA, a dynamic question answering (QA) platform that announces
questions and evaluates systems on a regular basis (weekly in this version). RealTime QA …
questions and evaluates systems on a regular basis (weekly in this version). RealTime QA …
A system for efficient high-recall retrieval
The goal of high-recall information retrieval (HRIR) is to find all or nearly all relevant
documents for a search topic. In this paper, we present the design of our system that affords …
documents for a search topic. In this paper, we present the design of our system that affords …
A proposed conceptual framework for a representational approach to information retrieval
J Lin - ACM SIGIR Forum, 2022 - dl.acm.org
This paper outlines a conceptual framework for understanding recent developments in
information retrieval and natural language processing that attempts to integrate dense and …
information retrieval and natural language processing that attempts to integrate dense and …
CC-News-En: A large English news corpus
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 …
Foundation, who provide free, publicly available web archives, including a continuous crawl …
TREC incident streams: Finding actionable information on social media
The Text Retrieval Conference (TREC) Incident Streams track is a new initiative that aims to
mature social media-based emergency response technology. This initiative advances the …
mature social media-based emergency response technology. This initiative advances the …
A survey on evaluation of summarization methods
The increasing volume of textual information on any topic requires its compression to allow
humans to digest it. This implies detecting the most important information and condensing it …
humans to digest it. This implies detecting the most important information and condensing it …
Online policies for efficient volunteer crowdsourcing
V Manshadi, S Rodilitz - Proceedings of the 21st ACM Conference on …, 2020 - dl.acm.org
Nonprofit crowdsourcing platforms such as food recovery organizations rely on volunteers to
perform time-sensitive tasks. Thus, their success crucially depends on efficient volunteer …
perform time-sensitive tasks. Thus, their success crucially depends on efficient volunteer …
Abstractive timeline summarization
J Steen, K Markert - Proceedings of the 2nd Workshop on New …, 2019 - aclanthology.org
Timeline summarization (TLS) automatically identifies key dates of major events and
provides short descriptions of what happened on these dates. Previous approaches to TLS …
provides short descriptions of what happened on these dates. Previous approaches to TLS …
TSSuBERT: How to sum up multiple years of reading in a few tweets
The development of deep neural networks and the emergence of pre-trained language
models such as BERT allow to increase performance on many NLP tasks. However, these …
models such as BERT allow to increase performance on many NLP tasks. However, these …