13.11.2020
MCML at EMNLP 2020
Two Accepted Papers (2 Findings)
Conference on Empirical Methods in Natural Language Processing, Virtual, Nov 16-20, 2020
We are happy to announce that MCML researchers have contributed a total of 2 papers to EMNLP 2020: 2 Finding papers. Congrats to our researchers!
Findings Track (2 papers)
N. Kassner • H. Schütze
BERT-kNN: Adding a kNN Search Component to Pretrained Language Models for Better QA.
Findings @EMNLP 2020 - Findings of the Conference on Empirical Methods in Natural Language Processing. Virtual, Nov 16-20, 2020. DOI
BERT-kNN: Adding a kNN Search Component to Pretrained Language Models for Better QA.
Findings @EMNLP 2020 - Findings of the Conference on Empirical Methods in Natural Language Processing. Virtual, Nov 16-20, 2020. DOI
M. J. Sabet • P. Dufter • F. Yvon • H. Schütze
SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings.
Findings @EMNLP 2020 - Findings of the Conference on Empirical Methods in Natural Language Processing. Virtual, Nov 16-20, 2020. DOI
SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings.
Findings @EMNLP 2020 - Findings of the Conference on Empirical Methods in Natural Language Processing. Virtual, Nov 16-20, 2020. DOI
Related
10.03.2026
Reinhard Heckel Featured in FAZ
MCML PI Reinhard Heckel, featured in FAZ, explains how better data boosts AI performance and reduces bias.
05.03.2026
Foundations of Diffusion: One Map for Images and Text
Unified diffusion theory for images and text, bridging continuous and discrete models in one clear framework for generative AI.
