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 …

The advent of transformer-based models such as BERT has led to the rise of neural ranking
models. These models have improved the effectiveness of retrieval systems well beyond that …

Two key assumptions shape the usual view of ranked retrieval:(1) that the searcher can
choose words for their query that might appear in the documents that they wish to see, and …

Pretrained multilingual text encoders based on neural transformer architectures, such as
multilingual BERT (mBERT) and XLM, have recently become a default paradigm for cross …

Benefiting from transformer-based pre-trained language models, neural ranking models
have made significant progress. More recently, the advent of multilingual pre-trained …

Pretrained language models have improved effectiveness on numerous tasks, including ad-
hoc retrieval. Recent work has shown that continuing to pretrain a language model with …

Existing research on cross-lingual retrieval cannot take good advantage of large-scale
pretrained language models such as multilingual BERT and XLM. We hypothesize that the …

The advent of multilingual language models has generated a resurgence of interest in cross-
lingual information retrieval (CLIR), which is the task of searching documents in one …

In today's digital age, accessing information across language barriers poses a significant
challenge, with conventional search systems often struggling to interpret and retrieve …

In this work, we explore a Multilingual Information Retrieval (MLIR) task, where the collection
includes documents in multiple languages. We demonstrate that applying state-of-the-art …