KnowMAN: Weakly Supervised Multinomial Adversarial Networks

KnowMAN: Weakly Supervised Multinomial Adversarial Networks

Abstract

The absence of labeled data for training neu- ral models is often addressed by leveraging knowledge about the specific task, resulting in heuristic but noisy labels. The knowledge is captured in labeling functions, which detect certain regularities or patterns in the training samples and annotate corresponding labels for training. This process of weakly supervised training may result in an over-reliance on the signals captured by the labeling functions and hinder models to exploit other signals or to generalize well. We propose KnowMAN, an adversarial scheme that enables to control in- fluence of signals associated with specific la- beling functions. KnowMAN forces the net- work to learn representations that are invari- ant to those signals and to pick up other sig- nals that are more generally associated with an output label. KnowMAN strongly improves results compared to direct weakly supervised learning with a pre-trained transformer lan- guage model and a feature-based baseline

Grafik Top
Authors
  • März, Luisa
  • Asgari, Ehsaneddin
  • Braune, Fabienne
  • Zimmermann, Franziska
  • Roth, Benjamin
Grafik Top
Shortfacts
Category
Paper in Conference Proceedings or in Workshop Proceedings (Paper)
Event Title
The 2021 Conference on Empirical Methods in Natural Language Processing
Divisions
Data Mining and Machine Learning
Subjects
Kuenstliche Intelligenz
Sprachverarbeitung
Event Location
Online
Event Type
Conference
Event Dates
November 7-11, 2021
Date
7 November 2021
Export
Grafik Top