Open-Domain Question Answering
91 papers with code • 11 benchmarks • 17 datasets
Open-domain question answering is the task of question answering on open-domain datasets such as Wikipedia.
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.
Ranked #6 on Passage Retrieval on Natural Questions
Large Transformer models routinely achieve state-of-the-art results on a number of tasks but training these models can be prohibitively costly, especially on long sequences.
Ranked #2 on Question Answering on Quasart-T
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.
In this paper, we illustrate how to fine-tune the entire Retrieval Augment Generation (RAG) architecture in an end-to-end manner.
Ranked #1 on Question Answering on SQuAD
This paper proposes to tackle open- domain question answering using Wikipedia as the unique knowledge source: the answer to any factoid question is a text span in a Wikipedia article.
Ranked #1 on Open-Domain Question Answering on SQuAD1.1
Recently, pre-trained models have achieved state-of-the-art results in various language understanding tasks, which indicates that pre-training on large-scale corpora may play a crucial role in natural language processing.
Language model pre-training has been shown to capture a surprising amount of world knowledge, crucial for NLP tasks such as question answering.
Ranked #9 on Question Answering on Natural Questions (short)
We also explore two approaches for end-to-end supervised training of the reader and retriever components in OpenQA models.
Machine comprehension (MC), answering a query about a given context paragraph, requires modeling complex interactions between the context and the query.
Ranked #4 on Question Answering on CNN / Daily Mail
Open-domain question answering can be reformulated as a phrase retrieval problem, without the need for processing documents on-demand during inference (Seo et al., 2019).
Ranked #1 on Question Answering on Natural Questions (long)