One approach for multilingual data-to-text generation is to translate grammatical configurations upfront from the source language into each target language. These configurations are then used by a surface realizer and in document planning stages to generate output. In this paper, we describe a rule-based NLG implementation of this approach where the configuration is translated by Neural Machine Translation (NMT) combined with a one-time human review, and introduce a cross-language grammar dependency model to create a multilingual NLG system that generates text from the source data, scaling the generation phase without a human in the loop. Additionally, we introduce a method for human post-editing evaluation on the automatically translated text. Our evaluation on the SportSett:Basketball dataset shows that our NLG system performs well, underlining its grammatical correctness in translation tasks.

In natural language generation (NLG), insight mining is seen as a data-to-text task, where data is mined for interesting patterns and verbalised into 'insight' statements. An 'over-generate and rank' paradigm is intuitively used to generate such insights. The multidimensionality and subjectivity of this process make it challenging. This paper introduces a schema-driven method to generate actionable insights from data to drive growth and change. It also introduces a technique to rank the insights to align with user interests based on their feedback. We show preliminary qualitative results of the insights generated using our technique and demonstrate its ability to adapt to feedback.

Summary This year the International Conference on Natural Language Generation (INLG) will feature an award for the paper with the best evaluation. The purpose of this award is to provide an incentive for NLG researchers to pay more attention to the way they assess the output of their systems. This essay provides a short introduction to evaluation in NLG, explaining key terms and distinctions. How can I evaluate my system? It is hard to say in general how you should evaluate your NLG system.

We present a data resource which can be useful for research purposes on language grounding tasks in the context of geographical referring expression generation. The resource is composed of two data sets that encompass 25 different geographical descriptors and a set of associated graphical representations, drawn as polygons on a map by two groups of human subjects: teenage students and expert meteorologists.

Prof. Ehud Reiter is the Chief Scientist of Arria NLG, and also a Professor of Computing Science at the University of Aberdeen. He has worked on natural language generation for the past 30 years, and has published 125 peer-reviewed academic papers and been awarded 5 patents; he also is the author of a widely used NLG textbook. In his university role he has been involved in several medical projects, and has published papers in British Medical Journal and other leading medical journals.

In what ways could NLG be used in healthcare? What will NLG mean for patients? NLG can be used to empower patients, so that they understand their medical conditions and can make better choices about their healthcare. NLG can also help patients do a better job of looking after themselves: this includes lifestyle changes, self-management of chronic conditions, and complying with treatment regimes. For example, many diabetics have sensors which measure blood sugar levels, but they struggle to use this information to manage their diabetes because often they don't understand it, and can overreact and indeed panic when they see their blood sugar change.

Artificial Intelligence has made huge advances in recent years in many areas, including language processing, vision, and machine learning; we are also seeing the emergence of platforms that integrate different kinds of AI, such as IBM Watson (Arria is a Watson ecosystem partner). Within medicine, I see a lot of excitement about using many aspects of AI; of course Natural Language Generation (NLG), but also using predictive analytics to anticipate potential problems, using machine learning to build diagnostic algorithms, using natural language processing to identify relevant research findings, using computer vision to analyze scans, and using robotics to assist surgeons and other clinicians. Natural Language Generation (NLG) software systems generate narratives that summarize, explain, and communicate complex data sets to people. The huge amount of data available in the modern world can overwhelm people; NLG humanizes the flood of data so that it helps rather than overwhelms people. NLG systems use data analysis and artificial intelligence techniques to analyze complex data sets, and computational linguistic techniques to communicate the results of the analysis in a high-quality narrative text.