SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2008.10875 · 2020

ETC-NLG: End-to-end Topic-Conditioned Natural Language Generation

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

Plug-and-play language models (PPLMs) enable topic-conditioned natural language generation by pairing large pre-trained generators with attribute models used to steer the predicted token distribution towards the selected topic. Despite their computational efficiency, PPLMs require large amounts of labeled texts to effectively balance generation fluency and proper conditioning, making them unsuitable for low-resource settings. We present ETC-NLG, an approach leveraging topic modeling annotations to enable fully-unsupervised End-to-end Topic-Conditioned Natural Language Generation over emergent topics in unlabeled document collections. We first test the effectiveness of our approach in a low-resource setting for Italian, evaluating the conditioning for both topic models and gold annotations. We then perform a comparative evaluation of ETC-NLG for Italian and English using a parallel corpus. Finally, we propose an automatic approach to estimate the effectiveness of conditioning on the generated utterances.

For agents

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

get_harvested_code_for_paper("2008.10875")
get_code_for_paper("2008.10875")
have("2008.10875")

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

curl https://syntology.ai/api/ran/2008.10875.json

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

[![Syntology run record](https://syntology.ai/api/ran/2008.10875.svg)](https://syntology.ai/paper/2008.10875)

Connect an agent — have() is free.