Topbots

JANUARY 30, 2023

In the past, the Deep Learning community solved the data shortage with self-supervision — pre-training LLMs using next-token prediction, a learning signal that is available “for free” since it is inherent to any text. Association for Computational Linguistics. [2] Association for Computational Linguistics. [4]

Large Language Models 52

Large Language Models Computational Linguistics LLM Natural Language Processing 52

Sebastian Ruder

NOVEMBER 14, 2022

This post is partially based on a keynote I gave at the Deep Learning Indaba 2022. These include groups focusing on linguistic regions such as Masakhane for African languages, AmericasNLP for native American languages, IndoNLP for Indonesian languages, GhanaNLP and HausaNLP , among others. In Proceedings of NIPS 2017.

Natural Language Processing 52

Natural Language Processing NLP Computational Linguistics BERT 52

NLP People

JANUARY 2, 2019

Hundreds of researchers, students, recruiters, and business professionals came to Brussels this November to learn about recent advances, and share their own findings, in computational linguistics and Natural Language Processing (NLP). 3-Is Automatic Post-Editing (APE) a Thing? 7-Have we Finally Solved Machine Translation?

BERT 52

BERT Natural Language Processing Computational Linguistics NLP 52

The Stanford AI Lab Blog

JANUARY 21, 2022

Deep learning has enabled improvements in the capabilities of robots on a range of problems such as grasping 1 and locomotion 2 in recent years. Deep contextualized word representations. Conference of the North American Chapter of the Association for Computational Linguistics. ↩ Devlin, J., Neumann, M.,

Robotics 40

Robotics Computational Linguistics BERT Computer Vision 40

The Stanford AI Lab Blog

OCTOBER 13, 2021

Deep learning face attributes in the wild. In Proceedings of the IEEE International Conference on Computer Vision, pp. In Association for Computational Linguistics (ACL), pp. SelectiveNet: A deep neural network with an integrated reject option. Selective classification for deep neural networks.

Neural Network 40

Neural Network Machine Learning Computational Linguistics Deep Learning 40

Sebastian Ruder

JANUARY 24, 2022

Transactions of the Association for Computational Linguistics, 9, 978–994. Transactions of the Association for Computational Linguistics, 9, 570–585. MetaICL: Learning to Learn In Context. In Proceedings of NIPS 2017. link] ↩︎ Hendricks, L. Schneider, R., Alayrac, J.

NLP 52

NLP ML BERT Computational Linguistics 52

ML Review

MARCH 5, 2019

vector: Probing sentence embeddings for linguistic properties. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (Vol. S., & Dean, J. Distributed Representations of Words and Phrases and their Compositionality. In NIPS (pp. 3111–3119). Bojanowski, P.,

AI 40

AI AI Computer Vision Computational Linguistics 40