Sebastian Riedel

Represent, Aggregate, and Constrain: A Novel Architecture for Machine Reading from Noisy Sources

2016 · arXiv (Cornell University)

In order to extract event information from text, a machine reading model must learn to accurately read and interpret the ways in which that information is expressed. But it must also, as the human reader …

Question Answering Resources Applied to Slot-Filling.

2018 · arXiv (Cornell University)

We investigate the utility of pre-existing question answering models and data for a recently proposed relation extraction task. We find that in the low-resource and zero-shot cases, such resources are surprisingly useful. Moreover, the resulting …

MLQA: Evaluating Cross-lingual Extractive Question Answering

2020

Question answering (QA) models have shown rapid progress enabled by the availability of large, high-quality benchmark datasets. Such annotated datasets are difficult and costly to collect, and rarely exist in languages other than English, making …

Joint Verification and Reranking for Open Fact Checking Over Tables

2021

Michael Sejr Schlichtkrull, Vladimir Karpukhin, Barlas Oguz, Mike Lewis, Wen-tau Yih, Sebastian Riedel. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing …

Lifting the Curse of Multilinguality by Pre-training Modular Transformers

2022 · arXiv (Cornell University)

Multilingual pre-trained models are known to suffer from the curse of multilinguality, which causes per-language performance to drop as they cover more languages. We address this issue by introducing language-specific modules, which allows us to …

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

2021 · arXiv (Cornell University)

Prompting language models (LMs) with training examples and task descriptions has been seen as critical to recent successes in few-shot learning. In this work, we show that finetuning LMs in the few-shot setting can considerably …

Clinical Text Prediction with Numerically Grounded Conditional Language\n Models

2016 · arXiv (Cornell University)

Assisted text input techniques can save time and effort and improve text\nquality. In this paper, we investigate how grounded and conditional extensions\nto standard neural language models can bring improvements in the tasks of word\nprediction and …

Injecting Logical Background Knowledge into Embeddings for Relation Extraction

2015

Matrix factorization approaches to relation extraction provide several attractive features: they support distant supervision, handle open schemas, and leverage unlabeled data. Unfortunately, these methods share a shortcoming with all other distantly supervised approaches: they cannot …

Adversarially Regularising Neural

2018

Adversarial examples are inputs to machine learning models designed to cause the model to make a mistake. They are useful for understanding the shortcomings of machine learning models, interpreting their results, and for regularisation. In …

UCL Machine Reading Group: Four Factor Framework For Fact Finding (HexaF)

2018

In this paper we describe our 2 nd place FEVER shared-task system that achieved a FEVER score of 62.52% on the provisional test set (without additional human evaluation), and 65.41% on the development set. Our …

Neural Architectures for Fine-grained Entity Type Classification

2017

Sonse Shimaoka, Pontus Stenetorp, Kentaro Inui, Sebastian Riedel. Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers. 2017.

Zero-Shot Transfer Learning for Event Extraction

2018

Most previous supervised event extraction methods have relied on features derived from manual annotations, and thus cannot be applied to new event types without extra annotation effort. We take a fresh look at event extraction …

Language Models as Knowledge Bases?

2019

Fabio Petroni, Tim Rocktäschel, Sebastian Riedel, Patrick Lewis, Anton Bakhtin, Yuxiang Wu, Alexander Miller. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language …

Affordance-Compiled Intelligence: Observable-Only Cognitive Impedance Matching for No-Meta LLM-Integrated Systems

2026 · arXiv (Cornell University)

Affordance-Compiled Intelligence develops Cognitive Impedance Matching Theory (CIMT), an observable-only and no-meta protected compiler theory for LLM-integrated systems. The paper studies how a fixed model-policy can exhibit different operational capability when the surrounding world is …

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

2022 · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

When primed with only a handful of training samples, very large, pretrained language models such as GPT-3 have shown competitive results when compared to fully-supervised, fine-tuned, large, pretrained language models. We demonstrate that the order …

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

2022 · Findings of the Association for Computational Linguistics: ACL 2022

Prompting language models (LMs) with training examples and task descriptions has been seen as critical to recent successes in few-shot learning. In this work, we show that finetuning LMs in the few-shot setting can considerably …

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

2021 · arXiv (Cornell University)

When primed with only a handful of training samples, very large, pretrained language models such as GPT-3 have shown competitive results when compared to fully-supervised, fine-tuned, large, pretrained language models. We demonstrate that the order …