Statistical language modelling for automatic story generation
| Autor: | Elena Lloret, Cristina Barros, Marta Vicente |
|---|---|
| Přispěvatelé: | Universidad de Alicante. Departamento de Lenguajes y Sistemas Informáticos, Procesamiento del Lenguaje y Sistemas de Información (GPLSI) |
| Rok vydání: | 2018 |
| Předmět: |
Statistics and Probability
Surface realisation General Engineering 02 engineering and technology Natural language generation Document planning Language modelling Artificial Intelligence 020204 information systems Lenguajes y Sistemas Informáticos 0202 electrical engineering electronic engineering information engineering Automatic story generation 020201 artificial intelligence & image processing Sociology Humanities |
| Zdroj: | RUA. Repositorio Institucional de la Universidad de Alicante Universidad de Alicante (UA) |
| ISSN: | 1875-8967 1064-1246 2015-6510 |
| DOI: | 10.3233/jifs-169491 |
| Popis: | This paper proposes an end-to-end Natural Language Generation approach to automatically create fiction stories using statistical language models. The proposed approach integrates the stages of macroplanning and the surface realisation, necessary to determine the content to write about together with the structure of the story, and the syntactic and lexical realisation of sentences to be generated, respectively. Moreover, the use of language models within the stages allows the generation task to be more flexible, as far as the adaptation of the approach to different languages, domains and textual genres is concerned. In order to validate our approach, two evaluations were performed. On the one hand, the influence of integrating position-specific language modelling in the macroplanning stage into the surface realisation module was evaluated. On the other hand, a user evaluation was performed to analyse the generated stories in a qualitative manner. Although there is still room for improvement, the results obtained from the first evaluation in conjunction with the user evaluation feedback shows that the combination of the aforementioned stages in an end-to-end approach is appropriate and have positive effects in the resulting generated text. This research work has been partially funded by the Generalitat Valenciana, through the grant ACIF/2016/501 and the project “DIIM2.0: Desarrollo de técnicas Inteligentes e Interactivas de Minería y generación de información sobre la web 2.0” (PROMETEOII/2014/001); by the Spanish Government through projects RESCATA (Representación canónica y transformaciones de los textos aplicado a las Tecnologías del Lenguaje Humano, Ref. TIN2015-65100-R) and REDES (Reconocimiento de Entidades Digitales: Enriquecimiento y Seguimiento, Ref TIN2015-65136-C2-2-R), as well as by Ayudas Fundación BBVA a equipos de investigación científica, through the project “Análisis de Sentimientos Aplicado a la Prevención del Suicidio en las Redes Sociales (ASAP)”. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|