Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Rücklé, Andreas"'
Autor:
Lee, Ji-Ung, Puerto, Haritz, van Aken, Betty, Arase, Yuki, Forde, Jessica Zosa, Derczynski, Leon, Rücklé, Andreas, Gurevych, Iryna, Schwartz, Roy, Strubell, Emma, Dodge, Jesse
Many recent improvements in NLP stem from the development and use of large pre-trained language models (PLMs) with billions of parameters. Large model sizes makes computational cost one of the main limiting factors for training and evaluating such mo
Externí odkaz:
http://arxiv.org/abs/2306.16900
Autor:
Rücklé, Andreas
The amount of information published on the Internet is growing steadily. Accessing the vast knowledge in them more effectively is a fundamental goal of many tasks in natural language processing. In this thesis, we address this challenge from the pers
Externí odkaz:
https://tuprints.ulb.tu-darmstadt.de/18508/1/representation-learning-and-learning-from-limited-labeled-data-for-cqa.pdf
Existing neural information retrieval (IR) models have often been studied in homogeneous and narrow settings, which has considerably limited insights into their out-of-distribution (OOD) generalization capabilities. To address this, and to facilitate
Externí odkaz:
http://arxiv.org/abs/2104.08663
In this paper, we introduce SciGen, a new challenge dataset for the task of reasoning-aware data-to-text generation consisting of tables from scientific articles and their corresponding descriptions. Describing scientific tables goes beyond the surfa
Externí odkaz:
http://arxiv.org/abs/2104.08296
Intermediate task fine-tuning has been shown to culminate in large transfer gains across many NLP tasks. With an abundance of candidate datasets as well as pre-trained language models, it has become infeasible to run the cross-product of all combinat
Externí odkaz:
http://arxiv.org/abs/2104.08247
Question answering systems should help users to access knowledge on a broad range of topics and to answer a wide array of different questions. Most systems fall short of this expectation as they are only specialized in one particular setting, e.g., a
Externí odkaz:
http://arxiv.org/abs/2104.07081
Autor:
Rücklé, Andreas, Geigle, Gregor, Glockner, Max, Beck, Tilman, Pfeiffer, Jonas, Reimers, Nils, Gurevych, Iryna
Massively pre-trained transformer models are computationally expensive to fine-tune, slow for inference, and have large storage requirements. Recent approaches tackle these shortcomings by training smaller models, dynamically reducing the model size,
Externí odkaz:
http://arxiv.org/abs/2010.11918
Existing NLP datasets contain various biases that models can easily exploit to achieve high performances on the corresponding evaluation sets. However, focusing on dataset-specific biases limits their ability to learn more generalizable knowledge abo
Externí odkaz:
http://arxiv.org/abs/2010.03338
We study the zero-shot transfer capabilities of text matching models on a massive scale, by self-supervised training on 140 source domains from community question answering forums in English. We investigate the model performances on nine benchmarks o
Externí odkaz:
http://arxiv.org/abs/2010.00980
Autor:
Pfeiffer, Jonas, Rücklé, Andreas, Poth, Clifton, Kamath, Aishwarya, Vulić, Ivan, Ruder, Sebastian, Cho, Kyunghyun, Gurevych, Iryna
The current modus operandi in NLP involves downloading and fine-tuning pre-trained models consisting of millions or billions of parameters. Storing and sharing such large trained models is expensive, slow, and time-consuming, which impedes progress t
Externí odkaz:
http://arxiv.org/abs/2007.07779