Anastasia Shimorina

TL;DR: This paper proposes the corpus generation framework as a novel method for creating challenging data sets from which NLG models can be learned which are capable of handling the complex interactions occurring during in micro-planning between lexicalisation, aggregation, surface realisation, referring expression generation and sentence segmentation.

TL;DR: The microplanning task is introduced, data preparation, evaluation methodology, participant results and a brief description of the participating systems are provided.

TL;DR: This paper proposed a new sentence simplification task (Split-and-Rephrase) where the aim is to split a complex sentence into a meaning preserving sequence of shorter sentences, which can be used as a preprocessing step which facilitates and improves the performance of parsers, semantic role labelers and machine translation systems.

TL;DR: GEM as discussed by the authors is a living benchmark for natural language generation (NLG), its Evaluation and Metrics, which provides an environment in which models can easily be applied to a wide set of tasks and in which evaluation strategies can be tested.

TL;DR: It is shown that rare items strongly impact performance and that combining delexicalisation and copying yields the strongest improvement; that copying underperforms for rare and unseen items and that the impact of these two mechanisms greatly varies depending on how the dataset is constructed and on how it is split into train, dev and test.