2018 · 24 citations · 21 references
ComputingComputer ScienceComputational LinguisticsMachine LearningNatural Language ProcessingGenerative ModelingInformation ExtractionLanguage ModelingLanguage ModelsNatural Language GenerationText GenerationAutomated Text GenerationData-to-text GenerationMarkov Chain Text GenerationParallel Data MiningTrigger Processing
Data2Text Studio is a platform for automated text generation from structured data. It is equipped with a Semi-HMMs model to extract high-quality templates and corresponding trigger conditions from parallel data automatically, which improves the interactivity and interpretability of the generated text. In addition, several easy-to-use tools are provided for developers to edit templates of pre-trained models, and APIs are released for developers to call the pre-trained model to generate texts in third-party applications. We conduct experiments on ROTOWIRE datasets for template extraction and text generation. The results show that our model achieves improvements on both tasks.
21
Building Natural-Language Generation Systems
Ehud Reiter · ArXiv.org · 1996 · 1.3K citations · Full text
Challenges in Data-to-Document Generation
Sam Wiseman, Stuart M. Shieber, Alexander M. Rush · 2017 · 499 citations · Full text
Learning semantic correspondences with less supervision
Percy Liang, Michael I. Jordan, Dan Klein · 2009 · 311 citations · Full text