SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.05108 · 2021

Attention-based Contrastive Learning for Winograd Schemas

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

Self-supervised learning has recently attracted considerable attention in the NLP community for its ability to learn discriminative features using a contrastive objective. This paper investigates whether contrastive learning can be extended to Transfomer attention to tackling the Winograd Schema Challenge. To this end, we propose a novel self-supervised framework, leveraging a contrastive loss directly at the level of self-attention. Experimental analysis of our attention-based models on multiple datasets demonstrates superior commonsense reasoning capabilities. The proposed approach outperforms all comparable unsupervised approaches while occasionally surpassing supervised ones.

For agents

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

get_harvested_code_for_paper("2109.05108")
get_code_for_paper("2109.05108")
have("2109.05108")

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

curl https://syntology.ai/api/ran/2109.05108.json

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

[![Syntology run record](https://syntology.ai/api/ran/2109.05108.svg)](https://syntology.ai/paper/2109.05108)

Connect an agent — have() is free.