Feature-Dependent Confusion Matrices for Low-Resource NER Labeling with Noisy Labels (2019-10-14T00:00:00.000000Z)

TL;DR

To the best of the knowledge, this approach is the first to leverage feature-dependent noise modeling with pre-initialized confusion matrices and improve upon other confusion-matrix based methods by up to 9%.

Abstract

In low-resource settings, the performance of supervised labeling models can be improved with automatically annotated or distantly supervised data, which is cheap to create but often noisy. Previous works have shown that significant improvements can be reached by injecting information about the confusion between clean and noisy labels in this additional training data into the classifier training. However, for noise estimation, these approaches either do not take the input features (in our case word embeddings) into account, or they need to learn the noise modeling from scratch which can be difficult in a low-resource setting. We propose to cluster the training data using the input features and then compute different confusion matrices for each cluster. To the best of our knowledge, our approach is the first to leverage feature-dependent noise modeling with pre-initialized confusion matrices. We evaluate on low-resource named entity recognition settings in several languages, showing that our methods improve upon other confusion-matrix based methods by up to 9%.

Authors

D. Klakow

11 papers

Lukas Lange

4 papers

Michael A. Hedderich

2 papers

TL;DR

Abstract

Authors

References29 items

Handling Noisy Labels for Robustly Learning from Self-Training Data for Low-Resource Sequence Labeling

Multilingual NER Transfer for Low-resource Languages

Distantly Supervised NER with Partial Annotation Learning and Reinforcement Learning

Training a Neural Network in a Low-Resource Setting on Automatically Annotated Noisy Data

Training a neural network based on unreliable human annotation of medical images

Learning Word Vectors for 157 Languages

Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noise

Learning with Noise: Enhance Distantly Supervised Relation Extraction with Dynamic Transition Matrix

Learning from Noisy Large-Scale Datasets with Minimal Supervision

Training deep neural-networks using a noise adaptation layer

Making Deep Neural Networks Robust to Label Noise: A Loss Correction Approach

Learning when to trust distant supervision: An application to low-resource POS tagging using cross-lingual projection

Training deep neural-networks based on unreliable labels

Incorporating Nesterov Momentum into Adam

Learning from massive noisy labeled data for image classification

Training Convolutional Networks with Noisy Labels

Classification in the Presence of Label Noise: A Survey

Named Entity Recognition in Estonian

Learning to Label Aerial Images from Noisy Data

Design Challenges and Misconceptions in Named Entity Recognition

Introduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition

Introduction to the CoNLL-2002 Shared Task: Language-Independent Named Entity Recognition

Class-Based n-gram Models of Natural Language

Least squares quantization in PCM

Maximum Likelihood Estimation of Observer Error‐Rates Using the EM Algorithm

LIII. On lines and planes of closest fit to systems of points in space

Language independent named entity recognition using distant supervision

Europarl: A Parallel Corpus for Statistical Machine Translation

On lines and planes of closest fit to systems of points in space. The London, Edinburgh, and Dublin Philosophical Magazine

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names