SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.06577 · 2020

Have Your Text and Use It Too! End-to-End Neural Data-to-Text Generation with Semantic Fidelity

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

End-to-end neural data-to-text (D2T) generation has recently emerged as an alternative to pipeline-based architectures. However, it has faced challenges in generalizing to new domains and generating semantically consistent text. In this work, we present DataTuner, a neural, end-to-end data-to-text generation system that makes minimal assumptions about the data representation and the target domain. We take a two-stage generation-reranking approach, combining a fine-tuned language model with a semantic fidelity classifier. Each of our components is learnt end-to-end without the need for dataset-specific heuristics, entity delexicalization, or post-processing. We show that DataTuner achieves state of the art results on the automated metrics across four major D2T datasets (LDC2017T10, WebNLG, ViGGO, and Cleaned E2E), with a fluency assessed by human annotators nearing or exceeding the human-written reference texts. We further demonstrate that the model-based semantic fidelity scorer in DataTuner is a better assessment tool compared to traditional, heuristic-based measures. Our generated text has a significantly better semantic fidelity than the state of the art across all four datasets

For agents

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

get_harvested_code_for_paper("2004.06577")
get_code_for_paper("2004.06577")
have("2004.06577")

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

curl https://syntology.ai/api/ran/2004.06577.json

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

[![Syntology run record](https://syntology.ai/api/ran/2004.06577.svg)](https://syntology.ai/paper/2004.06577)

Connect an agent — have() is free.