papers

Publications (8)

cs.CL2023

Evaluating end-to-end entity linking on domain-specific knowledge bases: Learning about ancient technologies from museum collections

Sebastian Cadavid-Sanchez, Khalil Kacem, Rafael Aparecido Martins Frade +4

To study social, economic, and historical questions, researchers in the social sciences and humanities have started to use increasingly large unstructured textual datasets. While r…

cs.CL2023

Understanding In-Context Learning via Supportive Pretraining Data

Xiaochuang Han, Daniel Simig, Todor Mihaylov +3

In-context learning (ICL) improves language models' performance on a variety of NLP tasks by simply demonstrating a handful of examples at inference time. It is not well understood…

cs.CL2023

D4: Improving LLM Pretraining via Document De-Duplication and Diversification

Kushal Tirumala, Daniel Simig, Armen Aghajanyan +1

Over recent years, an increasing amount of compute and data has been poured into training large language models (LLMs), usually by doing one-pass learning on as many tokens as poss…

cs.CL2022

Open Vocabulary Extreme Classification Using Generative Models

Daniel Simig, Fabio Petroni, Pouya Yanki +4

The extreme multi-label classification (XMC) task aims at tagging content with a subset of labels from an extremely large label set. The label vocabulary is typically defined in ad…

cs.CL2022

Few-shot Learning with Multilingual Language Models

Xi Victoria Lin, Todor Mihaylov, Mikel Artetxe +18

Large-scale generative language models such as GPT-3 are competitive few-shot learners. While these models are known to be able to jointly represent many different languages, their…

cs.CL2022

Text Characterization Toolkit

Daniel Simig, Tianlu Wang, Verna Dankers +4

In NLP, models are usually evaluated by reporting single-number performance scores on a number of readily available benchmarks, without much deeper analysis. Here, we argue that -…