SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2204.00511 · ACL · 2022

Learning Disentangled Representations of Negation and Uncertainty

Chrysoula Zerva, Sophia Ananiadou, Makoto Miwa, Jake Vasilakes

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Negation and uncertainty modeling are longstanding tasks in natural language processing. Linguistic theory postulates that expressions of negation and uncertainty are semantically independent from each other and the content they modify. However, previous works on representation learning do not explicitly model this independence. We therefore attempt to disentangle the representations of negation, uncertainty, and content using a Variational Autoencoder 1 . We find that simply supervising the latent representations results in good disentanglement, but auxiliary objectives based on adversarial learning and mutual information minimization can provide additional disentanglement gains.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2204.00511")
get_code_for_paper("2204.00511")
have("2204.00511")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2204.00511.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2204.00511.svg)](https://syntology.ai/paper/2204.00511)

Connect an agent — have() is free.