Sebastian Riedel

research

∙ 07/03/2023

Improving Language Plasticity via Pretraining with Active Forgetting

Pretrained language models (PLMs) are today the primary model for natura...

0 Yihong Chen, et al. ∙

research

∙ 06/30/2023

Exact dimension reduction for rough differential equations

In this paper, practically computable low-order approximations of potent...

0 Martin Redmann, et al. ∙

research

∙ 02/20/2023

Can discrete information extraction prompts generalize across language models?

We study whether automatically-induced prompts that effectively extract ...

0 Nathanaël Carraz Rakotonirina, et al. ∙

research

∙ 11/16/2022

Task-aware Retrieval with Instructions

We study the problem of retrieval with instructions, where users of a re...

0 Akari Asai, et al. ∙

research

∙ 10/30/2022

An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks

Access to external knowledge is essential for many natural language proc...

0 Yuxiang WU, et al. ∙

research

∙ 10/13/2022

Query Expansion Using Contextual Clue Sampling with Language Models

Query expansion is an effective approach for mitigating vocabulary misma...

0 Linqing Liu, et al. ∙

research

∙ 09/27/2022

EditEval: An Instruction-Based Benchmark for Text Improvements

Evaluation of text generation to date has primarily focused on content c...

15 Jane Dwivedi-Yu, et al. ∙

research

∙ 08/24/2022

PEER: A Collaborative Language Model

Textual content is often the output of a collaborative writing process: ...

11 Timo Schick, et al. ∙

research

∙ 08/05/2022

Few-shot Learning with Retrieval Augmented Language Models

Large language models have shown impressive few-shot results on a wide r...

10 Gautier Izacard, et al. ∙

research

∙ 07/20/2022

ReFactorGNNs: Revisiting Factorisation-based Models from a Message-Passing Perspective

Factorisation-based Models (FMs), such as DistMult, have enjoyed endurin...

4 Yihong Chen, et al. ∙

research

∙ 07/08/2022

Improving Wikipedia Verifiability with AI

Verifiability is a core content policy of Wikipedia: claims that are lik...

12 Fabio Petroni, et al. ∙

research

∙ 05/25/2022

EDIN: An End-to-end Benchmark and Pipeline for Unknown Entity Discovery and Indexing

Existing work on Entity Linking mostly assumes that the reference knowle...

0 Nora Kassner, et al. ∙

research

∙ 05/12/2022

Lifting the Curse of Multilinguality by Pre-training Modular Transformers

Multilingual pre-trained models are known to suffer from the curse of mu...

4 Jonas Pfeiffer, et al. ∙

research

∙ 05/12/2022

Open Vocabulary Extreme Classification Using Generative Models

The extreme multi-label classification (XMC) task aims at tagging conten...

0 Daniel Simig, et al. ∙

research

∙ 04/22/2022

Autoregressive Search Engines: Generating Substrings as Document Identifiers

Knowledge-intensive language tasks require NLP systems to both provide t...

0 Michele Bevilacqua, et al. ∙

research

∙ 12/18/2021

The Web Is Your Oyster – Knowledge-Intensive NLP against a Very Large Web Corpus

In order to address the increasing demands of real-world applications, t...

0 Aleksandra Piktus, et al. ∙

research

∙ 12/16/2021

Towards Unsupervised Dense Information Retrieval with Contrastive Learning

Information retrieval is an important component in natural language proc...

0 Gautier Izacard, et al. ∙

research

∙ 12/16/2021

Models in the Loop: Aiding Crowdworkers with Generative Annotation Assistants

In Dynamic Adversarial Data Collection (DADC), human annotators are task...

0 Max Bartolo, et al. ∙

research

∙ 12/14/2021

Boosted Dense Retriever

We propose DrBoost, a dense retrieval ensemble inspired by boosting. DrB...

0 Patrick Lewis, et al. ∙

research

∙ 10/08/2021

A Few More Examples May Be Worth Billions of Parameters

We investigate the dynamics of increasing the number of model parameters...

0 Yuval Kirstain, et al. ∙

research

∙ 10/06/2021

Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations

Learning good representations on multi-relational graphs is essential to...

6 Yihong Chen, et al. ∙

research

∙ 09/02/2021

Challenges in Generalization in Open Domain Question Answering

Recent work on Open Domain Question Answering has shown that there is a ...

0 Linqing Liu, et al. ∙

research

∙ 08/25/2021

ProoFVer: Natural Logic Theorem Proving for Fact Verification

We propose ProoFVer, a proof system for fact verification using natural ...

0 Amrith Krishna, et al. ∙

research

∙ 07/28/2021

Domain-matched Pre-training Tasks for Dense Retrieval

Pre-training on larger datasets with ever increasing model size is now a...

0 Barlas Oguz, et al. ∙

research

∙ 07/05/2021

Training Adaptive Computation for Open-Domain Question Answering with Computational Constraints

Adaptive Computation (AC) has been shown to be effective in improving th...

0 Yuxiang WU, et al. ∙

research

∙ 06/24/2021

Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models

Prompting language models (LMs) with training examples and task descript...

0 Robert L. Logan IV, et al. ∙

research

∙ 06/02/2021

Database Reasoning Over Text

Neural models have shown impressive performance gains in answering queri...

22 James Thorne, et al. ∙

research

∙ 04/18/2021

Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity

When primed with only a handful of training samples, very large pretrain...

8 Yao Lu, et al. ∙

research

∙ 04/18/2021

Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation

Despite the availability of very large datasets and pretrained models, s...

0 Max Bartolo, et al. ∙

research

∙ 03/23/2021

Multilingual Autoregressive Entity Linking

We present mGENRE, a sequence-to-sequence system for the Multilingual En...

0 Nicola De Cao, et al. ∙

research

∙ 03/10/2021

Combining Learning from Demonstration with Learning by Exploration to Facilitate Contact-Rich Tasks

Collaborative robots are expected to be able to work alongside humans an...

0 Yunlei Shi, et al. ∙

research

∙ 02/13/2021

PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them

Open-domain Question Answering models which directly leverage question-a...

0 Patrick Lewis, et al. ∙

research

∙ 01/01/2021

NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned

We review the EfficientQA competition from NeurIPS 2020. The competition...

15 Sewon Min, et al. ∙

research

∙ 12/30/2020

A Memory Efficient Baseline for Open Domain Question Answering

Recently, retrieval systems based on dense representations have led to i...

0 Gautier Izacard, et al. ∙

research

∙ 12/30/2020

Joint Verification and Reranking for Open Fact Checking Over Tables

Structured information is an important knowledge source for automatic ve...

0 Michael Schlichtkrull, et al. ∙

research

∙ 11/10/2020

Generating Fact Checking Briefs

Fact checking at scale is difficult – while the number of active fact ch...

0 Angela Fan, et al. ∙

research

∙ 11/10/2020

Don't Read Too Much into It: Adaptive Computation for Open-Domain Question Answering

Most approaches to Open-Domain Question Answering consist of a light-wei...

1 Yuxiang WU, et al. ∙

research

∙ 10/25/2020

Proactive Action Visual Residual Reinforcement Learning for Contact-Rich Tasks Using a Torque-Controlled Robot

Contact-rich manipulation tasks are commonly found in modern manufacturi...

0 Yunlei Shi, et al. ∙

research

∙ 10/14/2020

Neural Databases

In recent years, neural networks have shown impressive performance gains...

1 James Thorne, et al. ∙

research

∙ 10/02/2020

Autoregressive Entity Retrieval

Entities are at the center of how we represent and aggregate knowledge. ...

5 Nicola De Cao, et al. ∙

research

∙ 09/27/2020

Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval

We propose a simple and efficient multi-hop dense retrieval approach for...

0 Wenhan Xiong, et al. ∙

research

∙ 09/04/2020

KILT: a Benchmark for Knowledge Intensive Language Tasks

Challenging problems such as open-domain question answering, fact checki...

6 Fabio Petroni, et al. ∙

research

∙ 08/06/2020

Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets

Ideally Open-Domain Question Answering models should exhibit a number of...

14 Patrick Lewis, et al. ∙

research

∙ 07/13/2020

Learning Reasoning Strategies in End-to-End Differentiable Proving

Attempts to render deep learning models interpretable, data-efficient, a...

42 Pasquale Minervini, et al. ∙

research

∙ 06/24/2020

Semi-implicit Taylor schemes for stiff rough differential equations

We study a class of semi-implicit Taylor-type numerical methods that are...

0 Sebastian Riedel, et al. ∙

research

∙ 06/01/2020

Concept Matching for Low-Resource Classification

We propose a model to tackle classification tasks in the presence of ver...

7 Federico Errica, et al. ∙

research

∙ 05/22/2020

Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

Large pre-trained language models have been shown to store factual knowl...

0 Patrick Lewis, et al. ∙

research

∙ 05/17/2020

TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data

Recent years have witnessed the burgeoning of pretrained language models...

0 Pengcheng Yin, et al. ∙

research

∙ 05/10/2020

How Context Affects Language Models' Factual Predictions

When pre-trained on large unsupervised textual corpora, language models ...

0 Fabio Petroni, et al. ∙

research

∙ 04/29/2020

AxCell: Automatic Extraction of Results from Machine Learning Papers

Tracking progress in machine learning has become increasingly difficult ...

2 Marcin Kardas, et al. ∙

Sebastian Riedel

Featured Co-authors