NeuralREG: An end-to-end approach to referring expression generation
TL
TL;DR
This paper presents a new approach (NeuralREG), relying on deep neural networks, which makes decisions about form and content in one go without explicit feature extraction, using a delexicalized version of the WebNLG corpus.
Abstract
Traditionally, Referring Expression Generation (REG) models first decide on the form and then on the content of references to discourse entities in text, typically relying on features such as salience and grammatical function. In this paper, we present a new approach (NeuralREG), relying on deep neural networks, which makes decisions about form and content in one go without explicit feature extraction. Using a delexicalized version of the WebNLG corpus, we show that the neural model substantially improves over two strong baselines.
References37 items
1
The WebNLG Challenge: Generating Text from RDF Data
2
Linguistic realisation as machine translation: Comparing different MT models for AMR-to-text generation
3
Creating Training Corpora for NLG Micro-Planners
4
MAG: A Multilingual, Knowledge-base Agnostic and Deterministic Entity Linking Approach
5