We review the EfficientQA competition from NeurIPS 2020. The competition focused on open-
domain question answering (QA), where systems take natural language questions as input …

Open domain question answering (ODQA) is a longstanding task aimed at answering factual
questions from a large knowledge corpus without any explicit evidence in natural language …

We propose DrBoost, a dense retrieval ensemble inspired by boosting. DrBoost is trained in
stages: each component model is learned sequentially and specialized by focusing only on …

Despite the advancements made with the retrieve-then-read pipeline on open-domain
question answering task, current methods still face challenges stemming from term …

Building dense retrievers requires a series of standard procedures, including training and
validating neural models and creating indexes for efficient search. However, these …

Dense retrievers encode queries and documents and map them in an embedding space
using pre-trained language models. These embeddings need to be high-dimensional to fit …

Dense retrievers utilize pretrained language models to encode queries and documents as
high-dimensional embeddings for retrieval. Nevertheless, these high-dimensional …

In open domain question answering systems, Dense Passage Retriever (DPR) has become
a popular approach to retrieving relevant passages for finding answers. However, the …