5 citations · 17 across the 6 of their papers we have counts for
6 papers
Pre-computed memory or on-the-fly encoding? A hybrid approach to retrieval augmentation makes the most of your compute
Michiel de Jong, Yury Zemlyanskiy, Nicholas FitzGerald +4
Retrieval-augmented language models such as Fusion-in-Decoder are powerful, setting the state of the art on a variety of knowledge-intensive tasks. However, they are also expensive…
FiDO: Fusion-in-Decoder optimized for stronger performance and faster inference
Michiel de Jong, Yury Zemlyanskiy, Joshua Ainslie +4
Fusion-in-Decoder (FiD) is a powerful retrieval-augmented language model that sets the state-of-the-art on many knowledge-intensive NLP tasks. However, the architecture used for Fi…
Correcting Diverse Factual Errors in Abstractive Summarization via Post-Editing and Language Model Infilling
Vidhisha Balachandran, Hannaneh Hajishirzi, William W. Cohen +1
Abstractive summarization models often generate inconsistent summaries containing factual errors or hallucinated content. Recent works focus on correcting factual errors in generat…
Augmenting Pre-trained Language Models with QA-Memory for Open-Domain Question Answering
Wenhu Chen, Pat Verga, Michiel de Jong +2
Retrieval augmented language models have recently become the standard for knowledge intensive tasks. Rather than relying purely on latent semantics within the parameters of large n…
Mention Memory: incorporating textual knowledge into Transformers through entity mention attention
Michiel de Jong, Yury Zemlyanskiy, Nicholas FitzGerald +2
Natural language understanding tasks such as open-domain question answering often require retrieving and assimilating factual information from multiple sources. We propose to addre…
Multilingual Fact Linking
Keshav Kolluru, Martin Rezk, Pat Verga +2
Knowledge-intensive NLP tasks can benefit from linking natural language text with facts from a Knowledge Graph (KG). Although facts themselves are language-agnostic, the fact label…