Efficiently teaching an effective dense retriever with balanced topic aware sampling
A vital step towards the widespread adoption of neural retrieval models is their resource
efficiency throughout the training, indexing and query workflows. The neural IR community …
efficiency throughout the training, indexing and query workflows. The neural IR community …
[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 …
Colbert: Efficient and effective passage search via contextualized late interaction over bert
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 …
in Information Retrieval (IR), largely owed to fine-tuning deep language models (LMs) for …
Document ranking with a pretrained sequence-to-sequence model
This work proposes a novel adaptation of a pretrained sequence-to-sequence model to the
task of document ranking. Our approach is fundamentally different from a commonly …
task of document ranking. Our approach is fundamentally different from a commonly …
Automated fact-checking for assisting human fact-checkers
The reporting and the analysis of current events around the globe has expanded from
professional, editor-lead journalism all the way to citizen journalism. Nowadays, politicians …
professional, editor-lead journalism all the way to citizen journalism. Nowadays, politicians …
Multi-stage document ranking with BERT
The advent of deep neural networks pre-trained via language modeling tasks has spurred a
number of successful applications in natural language processing. This work explores one …
number of successful applications in natural language processing. This work explores one …
Improving efficient neural ranking models with cross-architecture knowledge distillation
Retrieval and ranking models are the backbone of many applications such as web search,
open domain QA, or text-based recommender systems. The latency of neural ranking …
open domain QA, or text-based recommender systems. The latency of neural ranking …
Pretrained transformers for text ranking: BERT and beyond
A Yates, R Nogueira, J Lin - Proceedings of the 14th ACM International …, 2021 - dl.acm.org
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 …
The expando-mono-duo design pattern for text ranking with pretrained sequence-to-sequence models
We propose a design pattern for tackling text ranking problems, dubbed" Expando-Mono-
Duo", that has been empirically validated for a number of ad hoc retrieval tasks in different …
Duo", that has been empirically validated for a number of ad hoc retrieval tasks in different …
[PDF][PDF] BERT-PLI: Modeling paragraph-level interactions for legal case retrieval.
Legal case retrieval is a specialized IR task that involves retrieving supporting cases given a
query case. Compared with traditional ad-hoc text retrieval, the legal case retrieval task is …
query case. Compared with traditional ad-hoc text retrieval, the legal case retrieval task is …