Learning to generate one-sentence biographies from Wikidata
Autor: | Ben Hachey, Will Radford, Andrew Chisholm |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2017 |
Předmět: |
FOS: Computer and information sciences
Computer Science - Computation and Language business.industry Computer science 02 engineering and technology 010501 environmental sciences computer.software_genre 01 natural sciences Preference Recurrent neural network Hallucinating 0202 electrical engineering electronic engineering information engineering Selection (linguistics) 020201 artificial intelligence & image processing Artificial intelligence business Baseline (configuration management) Computation and Language (cs.CL) computer Sentence Natural language processing 0105 earth and related environmental sciences |
Zdroj: | EACL (1) |
Popis: | We investigate the generation of one-sentence Wikipedia biographies from facts derived from Wikidata slot-value pairs. We train a recurrent neural network sequence-to-sequence model with attention to select facts and generate textual summaries. Our model incorporates a novel secondary objective that helps ensure it generates sentences that contain the input facts. The model achieves a BLEU score of 41, improving significantly upon the vanilla sequence-to-sequence model and scoring roughly twice that of a simple template baseline. Human preference evaluation suggests the model is nearly as good as the Wikipedia reference. Manual analysis explores content selection, suggesting the model can trade the ability to infer knowledge against the risk of hallucinating incorrect information. |
Databáze: | OpenAIRE |
Externí odkaz: |