paper-with-me

홈 › Papers

Curriculum learning for language modeling

2021-08-04 · Daniel Campos

Language Models like ELMo and BERT have provided robust representations of natural language, which serve as the language understanding component for a diverse range of downstream tasks.Curriculum learning is a method that employs a structured training regime instead, which has been leveraged in computer vision and machine translation to improve model training speed and model performance. While language models have proven transformational for the natural language processing community, these models have proven expensive, energy-intensive, and challenging to train. In this work, we explore the effect of curriculum learning on language model pretraining using various linguistically motivated curricula and evaluate transfer performance on the GLUE Benchmark. Despite a broad variety of training methodologies and experiments we do not find compelling evidence that curriculum learning methods improve language model training.

📄 PDF Abstract BibTeX arXiv:2108.02170

Code (1)

spacemanidol/CurriculumLearningForLanguageModels 공식 구현 tf

Tasks

Language ModelingLanguage ModellingMachine TranslationTranslation

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Tanh Activation 설명 없음
Sigmoid Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Multi-Head Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

Curriculum Design for Code-switching: Experiments with Language Identification and Language Modeling with Deep Neural Networks

2017-12-01 · WS 2017 12 · Monojit Choudhury, Kalika Bali, Sunayana Sitaram, Ashutosh Baheti
Language IdentificationLanguage ModelingLanguage Modelling

Exploring Strategies for Modeling Sign Language Phonology

2023-09-30 · Lee Kezar, Riley Carlin, Tejas Srinivasan, Zed Sehyr 외

Like speech, signs are composed of discrete, recombinable features called phonemes. Prior work shows that models which can recognize phonemes are better at sign recognition, motivating deeper exploration into strategies …

Efficient Pre-training of Masked Language Model via Concept-based Curriculum Masking

2022-12-15 · Mingyu Lee, Jun-Hyung Park, Junho Kim, Kang-Min Kim 외

Masked language modeling (MLM) has been widely used for pre-training effective bidirectional representations, but incurs substantial training costs. In this paper, we propose a novel concept-based curriculum masking (CCM…

Language ModelingLanguage ModellingMasked Language Modeling

Task-Informed Anti-Curriculum by Masking Improves Downstream Performance on Text

2025-02-18 · Andrei Jarca, Florinel Alin Croitoru, Radu Tudor Ionescu

Masked language modeling has become a widely adopted unsupervised technique to pre-train language models. However, the process of selecting tokens for masking is random, and the percentage of masked tokens is typically f…

Authorship AttributionLanguage ModelingLanguage ModellingMasked Language Modeling+4

CLIMB: Curriculum Learning for Infant-inspired Model Building

2023-11-15 · Richard Diehl Martinez, Zebulon Goriely, Hope McGovern, Christopher Davis 외

We describe our team's contribution to the STRICT-SMALL track of the BabyLM Challenge. The challenge requires training a language model from scratch using only a relatively small training dataset of ten million words. We…

Language ModelingLanguage ModellingMasked Language Modelingmodel