Metagraph Based Approach for Neural Text Question Generation
| Autor: | Marina Belyanova, Sergey Chernobrovkin, Igor Latkin, Yuriy E. Gapanyuk |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Structure (mathematical logic)
Computer science business.industry media_common.quotation_subject computer.software_genre Field (computer science) Task (project management) Question generation Multipartite graph Quality (business) Artificial intelligence Architecture business computer Natural language processing Sentence media_common |
| Zdroj: | Lecture Notes in Computer Science ISBN: 9783030726096 AIST |
| DOI: | 10.1007/978-3-030-72610-2_6 |
| Popis: | The paper considers the task of generating questions by given text. The generation of high-quality questions allows us to solve many problems, for example, in the field of teaching – for the automatic creation of tests for training materials or the enrichment of interaction techniques for question-answering systems. Leading research in this area shows that models based on the Seq2Seq architecture achieve the best quality. However, such models do not use the hidden structure of the text, which is essential for generating semantically correct questions. New works on this topic use additional data in the form of the graphs, representing the dependencies of the words in a sentence. In this article, an approach that uses a metagraph model of text as the initial structure for storing and enriching data with additional information and semantic relationships is considered. After generating a metagraph model of the text, the metagraph is decomposed into a multipartite graph, which allows its usage in existing models for generating text questions without losing information about the additional hierarchical and semantical dependencies of the text. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|