Keywords-To-Text Synthesis Using Recurrent Neural Network - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2018

Keywords-To-Text Synthesis Using Recurrent Neural Network


This paper concerns an application of Recurrent Neural Networks to text synthesis in the word level, with the help of keywords. First, a Parts Of Speech tagging library is employed to extract verbs and nouns from the texts used in our work, a part of which are then considered, after automatic eliminations, as the aforementioned keywords. Our ultimate aim is to train a Recurrent Neural Network to map the keyword sequence of a text to the entire text. Successive reformulations of the keyword and full text word sequences are performed, so that they can serve as the input and target of the network as efficiently as possible. The predicted texts are understandable enough, and their performance depends on the problem difficulty, determined by the percentage of full text words that are considered as keywords (ranging from 1/3 to 1/2), and the training memory cost, mainly affected by the network architecture.
Fichier principal
Vignette du fichier
467708_1_En_8_Chapter.pdf (474.67 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01821033 , version 1 (22-06-2018)


Attribution - CC BY 4.0



Nikolaos Kolokas, Anastasios Drosou, Dimitrios Tzovaras. Keywords-To-Text Synthesis Using Recurrent Neural Network. 14th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), May 2018, Rhodes, Greece. pp.85-96, ⟨10.1007/978-3-319-92007-8_8⟩. ⟨hal-01821033⟩
336 View
140 Download



Gmail Facebook Twitter LinkedIn More