Exploring Lexical-Semantic Knowledge in the Generation of Novel Riddles in Portuguese
Исследование лексико-семантических знаний при создании новых загадок на португальском языке
2018-01-01
SCID: 54.1/rueqa69q
Discuss with AI
Portuguese riddle generationconcept featureshuman evaluationlexical-semantic knowledgenatural language generation
Figures from the paper
Abstract (AI)
We describe an effort towards the automatic generation of novel riddles in Portuguese, ultimately with humour value.Riddle generation fits in the common architecture of a NLG system and may follow different models, described here, all based on features of a concept, acquired from a lexical-semantic knowledge base.Generated riddles were manually assessed by humans, who rated them as fairly interpretable, surprising, and novel, even if with low humour potential.
Key Findings
1
Human evaluators rated the generated riddles as fairly interpretable, surprising, and novel.
2
Several riddle-generation models are implemented within a common natural language generation architecture.
3
The generated riddles showed limited humour potential despite positive ratings for interpretability, surprise, and novelty.
4
The models generate riddles using features of concepts acquired from a lexical-semantic knowledge base.
5
The study investigates automatic generation of novel Portuguese riddles, with the broader goal of producing humorous content.
Research Object
Automatically generated novel riddles in Portuguese
Research Subject
Lexical-semantic knowledge and feature-based NLG models for generating riddles, evaluated for interpretability, surprise, novelty, and humour potential
Publication Details
Publication Date
2018-01-01
Journal
Publisher
ISSN
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest