Deep Semi-Supervised Learning with Linguistically Motivated Sequence Labeling Task Hierarchies

2016-12-29 · Jonathan Godwin, Pontus Stenetorp, Sebastian Riedel

In this paper we present a novel Neural Network algorithm for conducting semi-supervised learning for sequence labeling tasks arranged in a linguistically motivated hierarchy. This relationship is exploited to regularise the representations of supervised tasks by backpropagating the error of the unsupervised task through the supervised tasks. We introduce a neural network where lower layers are supervised by junior downstream tasks and the final layer task is an auxiliary unsupervised task. The architecture shows improvements of up to two percentage points F1 for Chunking compared to a plausible baseline.

📄 PDF Abstract BibTeX arXiv:1612.09113

Code (0)

등록된 구현이 없습니다.

Tasks

Chunking

SeqVAT: Virtual Adversarial Training for Semi-Supervised Sequence Labeling

2020-07-01 · ACL 2020 6 · Luoxin Chen, Weitong Ruan, Xinyue Liu, Jianhua Lu

Virtual adversarial training (VAT) is a powerful technique to improve model robustness in both supervised and semi-supervised settings. It is effective and can be easily adopted on lots of image classification and text c…

Chunking General Classification image-classification Image Classification+6

Deep Anomaly Detection under Labeling Budget Constraints

2023-02-15 · Aodong Li, Chen Qiu, Marius Kloft, Padhraic Smyth 외

Selecting informative data points for expert feedback can significantly improve the performance of anomaly detection (AD) in various contexts, such as medical diagnostics or fraud detection. In this paper, we determine a…

Anomaly Detection Fraud Detection

North S\'ami morphological segmentation with low-resource semi-supervised sequence labeling

2019-01-01 · WS 2019 1 · Stig-Arne Gr{\"o}nroos, S{\'a}mi Virpioja, Mikko Kurimo

Selective Pseudo-Labeling with Reinforcement Learning for Semi-Supervised Domain Adaptation

2020-12-07 · Bingyu Liu, Yuhong Guo, Jieping Ye, Weihong Deng

Recent domain adaptation methods have demonstrated impressive improvement on unsupervised domain adaptation problems. However, in the semi-supervised domain adaptation (SSDA) setting where the target domain has a few lab…

Domain Adaptation Q-Learning reinforcement-learning Reinforcement Learning (RL)+2

LIMIT-BERT : Linguistic Informed Multi-Task BERT

2019-10-31 · Junru Zhou, Zhuosheng Zhang, Hai Zhao, Shuailiang Zhang

In this paper, we present a Linguistic Informed Multi-Task BERT (LIMIT-BERT) for learning language representations across multiple linguistic tasks by Multi-Task Learning (MTL). LIMIT-BERT includes five key linguistic sy…

Multi-Task Learning POS Semantic Parsing Semantic Role Labeling