Towards an evolutionary-based approach for natural language processing

Luca Manzoni, Domagoj Jakobovic, Luca Mariot, Stjepan Picek, Mauro Castelli

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

2 Downloads (Pure)


Tasks related to Natural Language Processing (NLP) have recently been the focus of a large research endeavor by the machine learning community. The increased interest in this area is mainly due to the success of deep learning methods. Genetic Programming (GP), however, was not under the spotlight with respect to NLP tasks. Here, we propose a first proof-of-concept that combines GP with the well established NLP tool word2vec for the next word prediction task. The main idea is that, once words have been moved into a vector space, traditional GP operators can successfully work on vectors, thus producing meaningful words as the output. To assess the suitability of this approach, we perform an experimental evaluation on a set of existing newspaper headlines. Individuals resulting from this (pre-)training phase can be employed as the initial population in other NLP tasks, like sentence generation, which will be the focus of future investigations, possibly employing adversarial co-evolutionary approaches.

Original languageEnglish
Title of host publicationGECCO 2020
Subtitle of host publicationProceedings of the 2020 Genetic and Evolutionary Computation Conference
Place of PublicationNew York
PublisherAssociation for Computing Machinery (ACM)
Number of pages9
ISBN (Print)978-1-4503-7128-5
Publication statusPublished - 2020
Event2020 Genetic and Evolutionary Computation Conference, GECCO 2020 - Cancun, Mexico
Duration: 8 Jul 202012 Jul 2020


Conference2020 Genetic and Evolutionary Computation Conference, GECCO 2020


  • Genetic programming
  • Natural language processing
  • Next word prediction

Fingerprint Dive into the research topics of 'Towards an evolutionary-based approach for natural language processing'. Together they form a unique fingerprint.

Cite this