SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.12941 · ACL Findings · 2021

RetroGAN: A Cyclic Post-Specialization System for Improving Out-of-Knowledge and Rare Word Representations

Peter Chin, Pedro Colon-Hernandez, Yida Xin, Henry Lieberman, Catherine Havasi, Cynthia Breazeal

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

Retrofitting is a technique used to move word vectors closer together or further apart in their space to reflect their relationships in a Knowledge Base (KB). However, retrofitting only works on concepts that are present in that KB. RetroGAN uses a pair of Generative Adversarial Networks (GANs) to learn a oneto-one mapping between concepts and their retrofitted counterparts. It applies that mapping (post-specializes) to handle concepts that do not appear in the original KB in a manner similar to how some natural language systems handle out-of-vocabulary entries. We test our system on three word-similarity benchmarks and a downstream sentence simplification task, and achieve the state of the art (CARD-660). Altogether, our results demonstrate our system's effectiveness for out-of-knowledge and rare word generalization.

For agents

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

get_harvested_code_for_paper("2108.12941")
get_code_for_paper("2108.12941")
have("2108.12941")

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

curl https://syntology.ai/api/ran/2108.12941.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.12941.svg)](https://syntology.ai/paper/2108.12941)

Connect an agent — have() is free.