# Headline Generation: Learning from Decomposable Document Titles

Source: [Headline Generation: Learning from Decomposable Document Titles](<https://www.sota2.com/research/paper/68fa65ba1e209131cea0be48>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:33:37.375Z

Authors: Oleg Vasilyev, Tom Grek, John Bohannon

Published: 2019-04-17T19:03:07.000Z

## Abstract

We propose a novel method for generating titles for unstructured text documents. We reframe the problem as a sequential question-answering task. A deep neural network is trained on document-title pairs with decomposable titles, meaning that the vocabulary of the title is a subset of the vocabulary of the document. To train the model we use a corpus of millions of publicly available document-title pairs: news articles and headlines. We present the results of a randomized double-blind trial in which subjects were unaware of which titles were human or machine-generated. When trained on approximately 1.5 million news articles, the model generates headlines that humans judge to be as good or better than the original human-written headlines in the majority of cases.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1904.08455>)

[PDF](<https://arxiv.org/pdf/1904.08455.pdf>)
