Automatic Generation of Natural Language Explanations

Felipe Soares Da Costa, Sixun Ouyang, Peter Dolog, Aonghus Lawlor

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

56 Citations (Scopus)


An interesting challenge for explainable recommender systems is to provide successful interpretation of recommendations using structured sentences. It is well known that user-generated reviews, have strong influence on the users' decision. Recent techniques exploit user reviews to generate natural language explanations. In this paper, we propose a character-level attention-enhanced long short-term memory model to generate natural language explanations. We empirically evaluated this network using two real-world review datasets. The generated text present readable and similar to a real user's writing, due to the ability of reproducing negation, misspellings, and domain-specific vocabulary.
Original languageEnglish
Title of host publicationProceedings of the 23rd International Conference on Intelligent User Interfaces
PublisherAssociation for Computing Machinery
Publication date8 Mar 2018
Article number57
ISBN (Electronic)978-1-4503-5571-1
Publication statusPublished - 8 Mar 2018
EventInternational Conference on Intelligent User Interfaces - Hitotsubashi Hall (National Center of Sciences Building), Tokyo, Japan
Duration: 7 Mar 201811 Mar 2018
Conference number: 23


ConferenceInternational Conference on Intelligent User Interfaces
LocationHitotsubashi Hall (National Center of Sciences Building)
Internet address


  • Explainability
  • Explanations
  • Natural language generation
  • Neural network
  • Recommender systems


Dive into the research topics of 'Automatic Generation of Natural Language Explanations'. Together they form a unique fingerprint.

Cite this