@inproceedings{lange-etal-2019-feature,
title = {Feature-Dependent Confusion Matrices for Low-Resource NER Labeling with Noisy Labels},
author = {Lukas Lange and Michael Hedderich and Dietrich Klakow},
editor = {Kentaro Inui and Jing Jiang and Vincent Ng and Xiaojun Wan},
url = {https://aclanthology.org/D19-1362/},
doi = {https://doi.org/10.18653/v1/D19-1362},
year = {2019},
date = {2019},
booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)},
pages = {3552-3557},
publisher = {Association for Computational Linguistics},
address = {Hong Kong, China},
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%.},
pubstate = {published},
type = {inproceedings}
}