Disentangled Representations
Related Papers
A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations
AbstractLearning disentangled representations of textual data is essential for many natural language tasks such as fair classification, style transfer and sentence generation, among others. The existent dominant approaches in the …...
Disentangling Representations of Text by Masking Transformers
AbstractRepresentations from large pretrained models such as BERT encode a range of features into monolithic vectors, affording strong predictive accuracy across a range of downstream tasks. In this paper we …...
Disentangling Categorization in Multi-agent Emergent Communication
AbstractThe emergence of language between artificial agents is a recent focus of computational linguistics, as it offers a synthetic substrate for reasoning about human language evolution. From the perspective of …...
Learning Disentangled Textual Representations via Statistical Measures of Similarity
AbstractWhen working with textual data, a natural application of disentangled representations is the fair classification where the goal is to make predictions without being biased (or influenced) by sensible attributes …...