Headline Generation: Learning from Decomposable Document Titles
| Autor: | Vasilyev, Oleg, Grek, Tom, Bohannon, John |
|---|---|
| Rok vydání: | 2019 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | 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. Comment: 10 pages, 9 figures, 1 table. v3: Better figures, tables and descriptions - by reviewer Anna Venancio-Marques |
| Databáze: | arXiv |
| Externí odkaz: |
|