With the recent progress made in network and computing technology, the ubiquity of data,
and textual repositories freely available, the scientific practice evolves towards a more data …

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 …

We present CLIRMatrix, a massively large collection of bilingual and multilingual datasets
for Cross-Lingual Information Retrieval extracted automatically from Wikipedia. CLIRMatrix …

Multiple neural language models have been developed recently, eg, BERT and XLNet, and
achieved impressive results in various NLP tasks including sentence classification, question …

We introduce Smart Shuffling, a cross-lingual embedding (CLE) method that draws from
statistical word alignment approaches to leverage dictionaries, producing dense …

Abstract Cross-Lingual Information Retrieval (CLIR) aims to rank the documents written in a
language different from the user's query. The intrinsic gap between different languages is an …

Probabilistic Structured Queries (PSQ) is a cross-language information retrieval (CLIR)
method that uses translation probabilities statistically derived from aligned corpora. PSQ is a …

Acoustic keyword spotting (KWS) plays a pivotal role in the voice-activated systems of
artificial intelligence (AI), allowing for hands-free interactions between humans and smart …

In monolingual retrieval, sparse representations learned atop BERT-style models offer a
complementary approach to the unsupervised BM25 model. Inspired by this line of work, we …

We propose a weakly supervised neural model for Ad-hoc Cross-lingual Information
Retrieval (CLIR) from low-resource languages. Low resource languages often lack …