• Publications
  • Influence
SimpleNLG: A Realisation Engine for Practical Applications
TLDR
This paper describes SimpleNLG, a realisation engine for English which aims to provide simple and robust interfaces to generate syntactic structures and linearise them. Expand
  • 351
  • 52
  • PDF
Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation
TLDR
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. Expand
  • 326
  • 19
  • PDF
In pursuit of satisfaction and the prevention of embarrassment: affective state in group recommender systems
TLDR
This paper deals in depth with some of the emotions that play a role in a group recommender system, which recommends sequences of items to a group of users. Expand
  • 154
  • 13
  • PDF
Evaluating algorithms for the Generation of Referring Expressions using a balanced corpus
TLDR
We describe a corpus-based evaluation methodology, applied to a number of classic algorithms in this area. Expand
  • 107
  • 13
  • PDF
The TUNA-REG Challenge 2009: Overview and Evaluation Results
TLDR
The GREC Task at REG '08 required participating systems to select coreference chains to the main subject of short encyclopaedic texts collected from Wikipedia. Expand
  • 104
  • 13
  • PDF
Factors causing overspecification in definite descriptions
TLDR
In the current paper, we study the production of definite target descriptions, and explore several factors that might influence the amount of information that is included in these descriptions. Expand
  • 84
  • 12
  • PDF
The TUNA Challenge 2008: Overview and Evaluation Results
TLDR
The TUNA Challenge 2008 built on the foundations laid in the ASGRE 2007 Challenge (Belz and Gatt, 2007), which consisted of a single shared task, based on a subset of the T UNA Corpus. Expand
  • 48
  • 12
  • PDF
Best practices for the human evaluation of automatically generated text
TLDR
This paper provides an overview of how human evaluation is currently conducted, and presents a set of best practices, grounded in the literature. Expand
  • 46
  • 6
  • PDF
Generation of Referring Expressions: Assessing the Incremental Algorithm
TLDR
A substantial amount of recent work in natural language generation has focused on the generation of ''one-shot'' referring expressions whose only aim is to identify a target referent. Expand
  • 80
  • 5
  • PDF
Automatic generation of textual summaries from neonatal intensive care data
TLDR
We present a prototype, called BT-45, which generates textual summaries of about 45 minutes of continuous physiological signals and discrete events (e.g.: equipment settings and drug administration) in the Intensive Care Unit (ICU). Expand
  • 125
  • 4