Paperpile

Referenced Papers (17)

Curriculum learning

Yoshua Bengio, Jérôme Louradour, Ronan Collobert, Jason Weston

, 2009

"Cited as the foundational work on curriculum learning, a method inspired by human learning to improve model convergence and performance."

Referenced at: 01:12

On the power of curriculum learning in training deep networks

Guy Hacohen, Daphna Weinshall

arXiv [cs.LG], 2019

"Cited as an example of curriculum learning being applied in the domain of computer vision."

Referenced at: 01:12

Learning from children: Improving image-caption pretraining via curriculum

Hammad A Ayyubi, Rahul Lokesh, Alireza Zareian, Bo Wu, Shih-Fu Chang

arXiv [cs.CV], 2023

"Cited as an example of curriculum learning being applied in multimodal settings."

Referenced at: 01:12

Competence-based curriculum learning for neural machine translation

Emmanouil Antonios Platanios, Otilia Stretcu, Graham Neubig, Barnabas Poczos, Tom M Mitchell

arXiv [cs.CL], 2019

"Cited for their work on sentence length and word rarity as difficulty metrics for curriculum learning in NLP."

Referenced at: 08:01

On curriculum learning for commonsense reasoning

Adyasha Maharana, Mohit Bansal

, 2022

"Cited as a work applying curriculum learning in NLP, specifically in areas like machine translation and common sense reasoning."

Referenced at: 08:02

Curriculum learning for language modeling

Daniel Campos

arXiv [cs.CL], 2021

"Cited as a work applying curriculum learning in NLP, specifically in areas like machine translation and common sense reasoning."

Referenced at: 08:02

Less is more: Pre-training cross-lingual Small-Scale Language Models with cognitively-plausible curriculum learning strategies

Suchir Salhan, Richard Diehl Martinez, Zébulon Goriely, Paula Buttery

arXiv [cs.CL], 2024

"Cited as a work applying curriculum learning in NLP, specifically in areas like machine translation and common sense reasoning."

Referenced at: 08:02

Findings of the 2016 conference on machine translation

Ondřej Bojar, Rajen Chatterjee, Christian Federmann, Yvette Graham, Barry Haddow, Matthias Huck

, 2016

"Cited for machine translation benchmarks that show curriculum learning benefits transformers but not RNNs."

Referenced at: 09:38

How many words does ChatGPT know? The answer is ChatWords

Gonzalo Martínez, Javier Conde, Pedro Reviriego, Elena Merino-Gómez, José Alberto Hernández, Fabrizio Lombardi

arXiv [cs.CL], 2023

"Cited as a work that showed curriculum learning does not consistently improve model performance over NLP benchmarks."

Referenced at: 12:33

The open images dataset V4

Alina Kuznetsova, Hassan Rom, Neil Alldrin, Jasper Uijlings, Ivan Krasin, Jordi Pont-Tuset

Int. J. Comput. Vis., 2020

"Cited as the source for the 'Localized Narratives' image caption dataset, used in the multimodal track of the BabyLM challenge."

Referenced at: 16:31

Improved Training with Curriculum GANs

Rishi Sharma, Shane Barratt, Stefano Ermon, Vijay Pande

arXiv [cs.LG], 2018

"Cited as the source for the 'Conceptual Captions 3M' image caption dataset, used in the multimodal track of the BabyLM challenge."

Referenced at: 16:31

The CHILDES Project: Tools for Analyzing Talk (third edition): Volume I: Transcription format and programs, Volume II: The database

Brian MacWhinney

Comput. Linguist. Assoc. Comput. Linguist., 2000

"Cited as the source for the 'CHILDES' child-directed speech dataset, used in the multimodal track of the BabyLM challenge."

Referenced at: 16:31

A standardized Project Gutenberg corpus for statistical analysis of natural language and quantitative linguistics

Martin Gerlach, Francesc Font-Clos

arXiv [cs.CL], 2018

"Cited as the source for the 'Project Gutenberg (children's stories)' written English dataset, used in the multimodal track of the BabyLM challenge."

Referenced at: 16:31

Dialogue act modeling for automatic tagging and recognition of conversational speech

Andreas Stolcke, Klaus Ries, Noah Coccaro, Elizabeth Shriberg, Rebecca Bates, Daniel Jurafsky

Comput. Linguist. Assoc. Comput. Linguist., 2000

"Cited as the source for the 'Switchboard Dialog Act Corpus' dialogue dataset, used in the multimodal track of the BabyLM challenge."

Referenced at: 16:31

Winoground: Probing vision and language models for visio-linguistic compositionality

Tristan Thrush, Ryan Jiang, Max Bartolo, Amanpreet Singh, Adina Williams, Douwe Kiela

arXiv [cs.CV], 2022

"Cited as the source for the 'Winground' multimodal dataset, used for evaluating compositional understanding."

Referenced at: 24:54

Making the V in VQA matter: Elevating the role of image understanding in Visual Question Answering

Yash Goyal, Tejas Khot, Douglas Summers-Stay, Dhruv Batra, Devi Parikh

arXiv [cs.CV], 2016

"Cited as the source for the 'VQAv2' visual question answering dataset, used for evaluating model performance in answering questions given a picture."

Referenced at: 24:54

SSR: Alignment-aware modality Connector for speech language models

Weiting Tan, Hirofumi Inaguma, Ning Dong, Paden Tomasello, Xutai Ma

arXiv [cs.CL], 2024

"Cited as the source for the 'DevBench' multimodal dataset, which contains tasks related to lexical visual vocabulary, receptive grammar, and semantic odd-one-out."

Referenced at: 26:55