SepLL: Separating Latent Class Labels from Weak Supervision Noise

SepLL: Separating Latent Class Labels from Weak Supervision Noise

Abstract

In the weakly supervised learning paradigm, labeling functions automatically assign heuristic, often noisy, labels to data samples. In this work, we provide a method for learning from weak labels by separating two types of complementary information associated with the labeling functions: information related to the target label and information specific to one labeling function only. Both types of information are reflected to different degrees by all labeled instances. In contrast to previous works that aimed at correcting or removing wrongly labeled instances, we learn a branched deep model that uses all data as-is, but splits the labeling function information in the latent space. Specifically, we propose the end-to-end model SepLL which extends a transformer classifier by introducing a latent space for labeling function specific and task-specific information. The learning signal is only given by the labeling functions matches, no pre-processing or label model is required for our method. Notably, the task prediction is made from the latent layer without any direct task signal. Experiments on Wrench text classification tasks show that our model is competitive with the state-of-the-art, and yields a new best average performance.

Grafik Top
Authors
  • Stephan, Andreas
  • Kougia, Vasiliki
  • Roth, Benjamin
Grafik Top
Shortfacts
Category
Paper in Conference Proceedings or in Workshop Proceedings (Paper)
Event Title
Findings of the Association for Computational Linguistics: EMNLP 2022
Divisions
Data Mining and Machine Learning
Subjects
Kuenstliche Intelligenz
Event Location
Abu Dhabi, United Arab Emirates
Event Type
Conference
Event Dates
7-11 Dec 2022
Publisher
Association for Computational Linguistics
Date
December 2023
Export
Grafik Top