Perception of toxicity evolves over time and often differs between
geogr...
Prior work has shown that it is possible to expand pretrained Masked Lan...
We study the problem of retrieval with instructions, where users of a
re...
Evaluation of text generation to date has primarily focused on content
c...
Textual content is often the output of a collaborative writing process: ...
Large language models have shown impressive few-shot results on a wide r...
Verifiability is a core content policy of Wikipedia: claims that are lik...
Knowledge-intensive language tasks require NLP systems to both provide t...
Users and organizations are generating ever-increasing amounts of privat...
In order to address the increasing demands of real-world applications, t...
We propose DrBoost, a dense retrieval ensemble inspired by boosting. DrB...
Despite their recent popularity and well known advantages, dense retriev...
We investigate the dynamics of increasing the number of model parameters...
Recent work on Open Domain Question Answering has shown that there is a ...
Pre-training on larger datasets with ever increasing model size is now a...
Open-domain Question Answering models which directly leverage question-a...
We review the EfficientQA competition from NeurIPS 2020. The competition...
We propose a simple and efficient multi-hop dense retrieval approach for...
Challenging problems such as open-domain question answering, fact checki...
Ideally Open-Domain Question Answering models should exhibit a number of...
Large pre-trained language models have been shown to store factual knowl...
When pre-trained on large unsupervised textual corpora, language models ...
We aim to improve question answering (QA) by decomposing hard questions ...
Question answering (QA) models have shown rapid progress enabled by the
...
Recent progress in pretraining language models on large textual corpora ...
Obtaining training data for Question Answering (QA) is time-consuming an...
Most work in machine reading focuses on question answering problems wher...