Open-Domain Question Answering
173 papers with code • 10 benchmarks • 24 datasets
Open-domain question answering is the task of question answering on open-domain datasets such as Wikipedia.
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
We evaluate a number of noising approaches, finding the best performance by both randomly shuffling the order of the original sentences and using a novel in-filling scheme, where spans of text are replaced with a single mask token.
Machine comprehension (MC), answering a query about a given context paragraph, requires modeling complex interactions between the context and the query.
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 facto method.
We introduce an approach for open-domain question answering (QA) that retrieves and reads a passage graph, where vertices are passages of text and edges represent relationships that are derived from an external knowledge base or co-occurrence in the same article.
Generative models for open domain question answering have proven to be competitive, without resorting to external knowledge.
Language model pre-training has been shown to capture a surprising amount of world knowledge, crucial for NLP tasks such as question answering.