Published December 18, 2020 | Version v1
Conference paper Open

The Natural Language Pipeline, Neural Text Generation and Explainability

  • 1. CNRS/LORIA, Université de Lorraine
  • 2. Utrecht University

Description

End-to-end encoder-decoder approaches to data-to-text generation are often black boxes whose predictions are difficult to explain. Breaking up the end-to-end model into sub-modules is a natural way to address this problem. The traditional pre-neural Natural Language Generation (NLG) pipeline provides a framework for breaking up the end-to-end encoder-decoder. We survey recent papers that integrate traditional NLG submodules in neural approaches and analyse their explainability. Our survey is a first step towards building explainable neural NLG models.

Files

2020.nl4xai-1.5.pdf

Files (162.2 kB)

Name Size Download all
md5:2c4cb94327d5283ea1a34e16731ec896
162.2 kB Preview Download

Additional details

Funding

European Commission
NL4XAI – Interactive Natural Language Technology for Explainable Artificial Intelligence 860621