KnowMAN: Weakly Supervised Multinomial Adversarial Networks

  title={KnowMAN: Weakly Supervised Multinomial Adversarial Networks},
  author={Luisa M{\"a}rz and Ehsaneddin Asgari and Fabienne Braune and Franziska Zimmermann and Benjamin Roth},
The absence of labeled data for training neural 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… 

Figures and Tables from this paper


Adversarial Training Methods for Semi-Supervised Text Classification
This work extends adversarial and virtual adversarial training to the text domain by applying perturbations to the word embeddings in a recurrent neural network rather than to the original input itself.
DSGAN: Generative Adversarial Training for Distant Supervision Relation Extraction
An adversarial learning framework is introduced, which is named DSGAN, to learn a sentence-level true-positive generator, Inspired by Generative Adversarial Networks, that regard the positive samples generated by the generator as the negative samples to train the discriminator.
Adversarial learning for distant supervised relation extraction
Recently, many researchers have concentrated on using neural networks to learn features for Distant Supervised Relation Extraction (DSRE). These approaches generally use a softmax classifier with
Multinomial Adversarial Networks for Multi-Domain Text Classification
A multinomial adversarial network (MAN) to tackle the real-world problem of multi-domain text classification (MDTC) in which labeled data may exist for multiple domains, but in insufficient amounts to train effective classifiers for one or more of the domains.
Snorkel: Rapid Training Data Creation with Weak Supervision
Snorkel is a first-of-its-kind system that enables users to train state- of- the-art models without hand labeling any training data and proposes an optimizer for automating tradeoff decisions that gives up to 1.8× speedup per pipeline execution.
Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classification
An Adversarial Deep Averaging Network (ADAN1) is proposed to transfer the knowledge learned from labeled data on a resource-rich source language to low-resource languages where only unlabeled data exist.
Multi-Source Cross-Lingual Model Transfer: Learning What to Share
This model leverages adversarial networks to learn language-invariant features, and mixture-of-experts models to dynamically exploit the similarity between the target language and each individual source language to further boost target language performance.
Adversarial Training for Relation Extraction
Experimental results demonstrate that adversarial training is generally effective for both CNN and RNN models and significantly improves the precision of predicted relations.
Neural Relation Extraction with Selective Attention over Instances
A sentence-level attention-based model for relation extraction that employs convolutional neural networks to embed the semantics of sentences and dynamically reduce the weights of those noisy instances.
Reducing Wrong Labels in Distant Supervision for Relation Extraction
A novel generative model is presented that directly models the heuristic labeling process of distant supervision and predicts whether assigned labels are correct or wrong via its hidden variables.