Towards Content Transfer through Grounded Text Generation

by   Shrimai Prabhumoye, et al.
Carnegie Mellon University

Recent work in neural generation has attracted significant interest in controlling the form of text, such as style, persona, and politeness. However, there has been less work on controlling neural text generation for content. This paper introduces the notion of Content Transfer for long-form text generation, where the task is to generate a next sentence in a document that both fits its context and is grounded in a content-rich external textual source such as a news story. Our experiments on Wikipedia data show significant improvements against competitive baselines. As another contribution of this paper, we release a benchmark dataset of 640k Wikipedia referenced sentences paired with the source articles to encourage exploration of this new task.


page 1

page 8


Time-aware Prompting for Text Generation

In this paper, we study the effects of incorporating timestamps, such as...

Neural Text Generation from Structured Data with Application to the Biography Domain

This paper introduces a neural model for concept-to-text generation that...

Mapping Process for the Task: Wikidata Statements to Text as Wikipedia Sentences

Acknowledged as one of the most successful online cooperative projects i...

A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation

Large pretrained generative models like GPT-3 often suffer from hallucin...

Generating Wikipedia Article Sections from Diverse Data Sources

Datasets for data-to-text generation typically focus either on multi-dom...

FRUIT: Faithfully Reflecting Updated Information in Text

Textual knowledge bases such as Wikipedia require considerable effort to...

Unsupervised Neural Stylistic Text Generation using Transfer learning and Adapters

Research has shown that personality is a key driver to improve engagemen...

Please sign up or login with your details

Forgot password? Click here to reset