Headline Generation: Learning from Decomposable Document Titles
This addresses the challenge of automated headline generation for news and similar documents, offering a potentially scalable solution, though it appears incremental as it builds on existing neural methods with a novel framing.
The paper tackles the problem of generating titles for unstructured text documents by reframing it as a sequential question-answering task, achieving results where a model trained on 1.5 million news articles produces headlines judged as good or better than human-written ones in most cases.
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.