Similarity has always been a key aspect in computer science and statistics. Any time two
element vectors are compared, many different similarity approaches can be used …

Deep learning--based models have surpassed classical machine learning--based
approaches in various text classification tasks, including sentiment analysis, news …

Text embeddings are useful features in many applications such as semantic search and
computing text similarity. Previous work typically trains models customized for different use …

It has been shown that dual encoders trained on one domain often fail to generalize to other
domains for retrieval tasks. One widespread belief is that the bottleneck layer of a dual …

Much recent research on information retrieval has focused on how to transfer from one task
(typically with abundant supervised data) to various other tasks where supervision is limited …

Open-domain question answering relies on efficient passage retrieval to select candidate
contexts, where traditional sparse vector space models, such as TF-IDF or BM25, are the de …

Link prediction for knowledge graphs is the task of predicting missing relationships between
entities. Previous work on link prediction has focused on shallow, fast models which can …

We present an end-to-end differentiable training method for retrieval-augmented open-
domain question answering systems that combine information from multiple retrieved …

In open question answering (QA), the answer to a question is produced by retrieving and
then analyzing documents that might contain answers to the question. Most open QA …

Dense retrieval has become a prominent method to obtain relevant context or world
knowledge in open-domain NLP tasks. When we use a learned dense retriever on a …