Open-domain Question Answering (OpenQA) is an important task in Natural Language
Processing (NLP), which aims to answer a question in the form of natural language based …

Machine reading comprehension (MRC), which requires a machine to answer questions
based on a given context, has attracted increasing attention with the incorporation of various …

Abstract The Visual Question Answering (VQA) task aspires to provide a meaningful testbed
for the development of AI models that can jointly reason over visual and natural language …

Generative models for open domain question answering have proven to be competitive,
without resorting to external knowledge. While promising, this approach requires to use …

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 …

Open domain question answering (OpenQA) tasks have been recently attracting more and
more attention from the natural language processing (NLP) community. In this work, we …

We study the problem of injecting knowledge into large pre-trained models like BERT and
RoBERTa. Existing methods typically update the original parameters of pre-trained models …

Recent work on open domain question answering (QA) assumes strong supervision of the
supporting evidence and/or assumes a blackbox information retrieval (IR) system to retrieve …

Lexical matching remains the de facto evaluation method for open-domain question
answering (QA). Unfortunately, lexical matching fails completely when a plausible candidate …

One of the most challenging question types in VQA is when answering the question requires
outside knowledge not present in the image. In this work we study open-domain knowledge …