3.1k citations · 3.3k across the 12 of their papers we have counts for
14 papers
Subtraction Gets You More: Gap-Aware Retrieval for Multimodal Multi-Hop QA
Sunah O, Jay-Yoon Lee
In multimodal multi-hop question answering, we focus on the initial retrieval stage via two distinct tasks: (1) evidence set completion, retrieving missing evidence given context,…
Arcee's MergeKit: A Toolkit for Merging Large Language Models
Charles Goddard, Shamane Siriwardhana, Malikeh Ehghaghi +5
The rapid expansion of the open-source language model landscape presents an opportunity to merge the competencies of these model checkpoints by combining their parameters. Advances…
CM3: A Causal Masked Multimodal Model of the Internet
Armen Aghajanyan, Bernie Huang, Candace Ross +8
We introduce CM3, a family of causally masked generative models trained over a large corpus of structured multi-modal documents that can contain both text and image tokens. Our new…
The Web Is Your Oyster - Knowledge-Intensive NLP against a Very Large Web Corpus
Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin +8
In order to address increasing demands of real-world applications, the research for knowledge-intensive NLP (KI-NLP) should advance by capturing the challenges of a truly open-doma…
Discourse-Aware Soft Prompting for Text Generation
Marjan Ghazvininejad, Vladimir Karpukhin, Vera Gor +1
Current efficient fine-tuning methods (e.g., adapters, prefix-tuning, etc.) have optimized conditional text generation via training a small set of extra parameters of the neural la…
Domain-matched Pre-training Tasks for Dense Retrieval
Barlas Oğuz, Kushal Lakhotia, Anchit Gupta +8
Pre-training on larger datasets with ever increasing model size is now a proven recipe for increased performance across almost all NLP tasks. A notable exception is information ret…
NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
Sewon Min, Jordan Boyd-Graber, Chris Alberti +50
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 and…
Multi-task Retrieval for Knowledge-Intensive Tasks
Jean Maillard, Vladimir Karpukhin, Fabio Petroni +4
Retrieving relevant contexts from a large corpus is a crucial step for tasks such as open-domain question answering and fact checking. Although neural retrieval outperforms traditi…
Joint Verification and Reranking for Open Fact Checking Over Tables
Michael Schlichtkrull, Vladimir Karpukhin, Barlas Oğuz +3
Structured information is an important knowledge source for automatic verification of factual claims. Nevertheless, the majority of existing research into this task has focused on…
UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering
Barlas Oguz, Xilun Chen, Vladimir Karpukhin +6
We study open-domain question answering with structured, unstructured and semi-structured knowledge sources, including text, tables, lists and knowledge bases. Departing from prior…
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Patrick Lewis, Ethan Perez, Aleksandra Piktus +9
Large pre-trained language models have been shown to store factual knowledge in their parameters, and achieve state-of-the-art results when fine-tuned on downstream NLP tasks. Howe…
Aligned Cross Entropy for Non-Autoregressive Machine Translation
Marjan Ghazvininejad, Vladimir Karpukhin, Luke Zettlemoyer +1
Non-autoregressive machine translation models significantly speed up decoding by allowing for parallel prediction of the entire target sequence. However, modeling word order is mor…
Dense Passage Retrieval for Open-Domain Question Answering
Vladimir Karpukhin, Barlas Oğuz, Sewon Min +5
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…
Training on Synthetic Noise Improves Robustness to Natural Noise in Machine Translation
Vladimir Karpukhin, Omer Levy, Jacob Eisenstein +1
We consider the problem of making machine translation more robust to character-level variation at the source side, such as typos. Existing methods achieve greater coverage by apply…