SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1911.03373 · 2019

A Good Sample is Hard to Find: Noise Injection Sampling and Self-Training for Neural Language Generation Models

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

Deep neural networks (DNN) are quickly becoming the de facto standard modeling method for many natural language generation (NLG) tasks. In order for such models to truly be useful, they must be capable of correctly generating utterances for novel meaning representations (MRs) at test time. In practice, even sophisticated DNNs with various forms of semantic control frequently fail to generate utterances faithful to the input MR. In this paper, we propose an architecture agnostic self-training method to sample novel MR/text utterance pairs to augment the original training data. Remarkably, after training on the augmented data, even simple encoder-decoder models with greedy decoding are capable of generating semantically correct utterances that are as good as state-of-the-art outputs in both automatic and human evaluations of quality.

For agents

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

get_harvested_code_for_paper("1911.03373")
get_code_for_paper("1911.03373")
have("1911.03373")

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

curl https://syntology.ai/api/ran/1911.03373.json

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

[![Syntology run record](https://syntology.ai/api/ran/1911.03373.svg)](https://syntology.ai/paper/1911.03373)

Connect an agent — have() is free.