paper-with-me

홈 › Papers

Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimates

2021-01-20 · EACL 2021 2 · Artem Shelmanov, Dmitri Puzyrev, Lyubov Kupriyanova, Denis Belyakov, Daniil Larionov, Nikita Khromov, Olga Kozlova, Ekaterina Artemova, Dmitry V. Dylov, Alexander Panchenko

Annotating training data for sequence tagging of texts is usually very time-consuming. Recent advances in transfer learning for natural language processing in conjunction with active learning open the possibility to significantly reduce the necessary annotation budget. We are the first to thoroughly investigate this powerful combination for the sequence tagging task. We conduct an extensive empirical study of various Bayesian uncertainty estimation methods and Monte Carlo dropout options for deep pre-trained models in the active learning framework and find the best combinations for different types of models. Besides, we also demonstrate that to acquire instances during active learning, a full-size Transformer can be substituted with a distilled version, which yields better computational performance and reduces obstacles for applying deep active learning in practice.

📄 PDF Abstract BibTeX arXiv:2101.08133

Code (0)

등록된 구현이 없습니다.

Tasks

Active LearningTransfer Learning

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Monte Carlo Dropout 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
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

A Bayesian Approach for Sequence Tagging with Crowds

2018-11-02 · IJCNLP 2019 11 · Edwin Simpson, Iryna Gurevych

Current methods for sequence tagging, a core task in NLP, are data hungry, which motivates the use of crowdsourcing as a cheap way to obtain labelled data. However, annotators are often unreliable and current aggregation…

Active LearningArgument Miningnamed-entity-recognitionNamed Entity Recognition+1

AlpacaTag: An Active Learning-based Crowd Annotation Framework for Sequence Tagging

2019-07-01 · ACL 2019 7 · Bill Yuchen Lin, Dong-Ho Lee, Frank F. Xu, Ouyu Lan 외

We introduce an open-source web-based data annotation framework (AlpacaTag) for sequence tagging tasks such as named-entity recognition (NER). The distinctive advantages of AlpacaTag are three-fold. 1) Active intelligent…

Active Learningnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+1

Multivariate Bayesian Last Layer for Regression: Uncertainty Quantification and Disentanglement

2024-05-02 · Han Wang, Eiji Kawasaki, Guillaume Damblin, Geoffrey Daniel

We present new Bayesian Last Layer models in the setting of multivariate regression under heteroscedastic noise, and propose an optimization algorithm for parameter learning. Bayesian Last Layer combines Bayesian modelli…

DisentanglementregressionUncertainty Quantification

Deep Bayesian Active Learning, A Brief Survey on Recent Advances

2020-12-15 · Salman Mohamadi, Hamidreza Amindavar

Active learning frameworks offer efficient data annotation without remarkable accuracy degradation. In other words, active learning starts training the model with a small size of labeled data while exploring the space of…

Active LearningSurvey

Diffusion Policy with Bayesian Expert Selection for Active Multi-Target Tracking

2026-04-03 · Haotian Xiang, Qin Lu, Yaakov Bar-Shalom arxiv

Active multi-target tracking requires a mobile robot to balance exploration for undetected targets with exploitation of uncertain tracked ones. Diffusion policies have emerged as a powerful approach for capturing diverse…