This paper surveys the current state of the art in Natural Language Generation (NLG),
defined as the task of generating text or speech from non-linguistic input. A survey of NLG is …

Currently, there is little agreement as to how Natural Language Generation (NLG) systems
should be evaluated, with a particularly high degree of variation in the way that human …

Text style transfer is an important task in natural language generation, which aims to control
certain attributes in the generated text, such as politeness, emotion, humor, and many …

Recent neural models have shown significant progress on the problem of generating short
descriptive texts conditioned on a small number of database records. In this work, we …

Charts are commonly used for exploring data and communicating insights. Generating
natural language summaries from charts can be very helpful for people in inferring key …

This paper introduces a neural model for concept-to-text generation that scales to large, rich
domains. We experiment with a new dataset of biographies from Wikipedia that is an order …

With software automatically producing texts in natural language from structured data, the
evolution of natural language generation (NLG) is changing traditional news production. The …

A central challenge in semantic parsing is handling the myriad ways in which knowledge
base predicates can be expressed. Traditionally, semantic parsers are trained primarily from …

Time series is an important class of temporal data objects and it can be easily obtained from
scientific and financial applications. A time series is a collection of observations made …

Malicious crowdsourcing forums are gaining traction as sources of spreading misinformation
online, but are limited by the costs of hiring and managing human workers. In this paper, we …