• Publications
  • Influence
The First Surface Realisation Shared Task: Overview and Evaluation Results
TLDR
The Surface Realisation (SR) Task was a new task at Generation Challenges 2011, and had two tracks: (1) Shallow: mapping from shallow input representations to realisations; and (2) Deep: mapping to deep input representations. Expand
  • 104
  • 20
  • PDF
An Investigation into the Validity of Some Metrics for Automatically Evaluating Natural Language Generation Systems
TLDR
We present empirical studies of how well some metrics which are popular in other areas of NLP (notably BLEU and ROUGE) correlate with human judgments in the domain of computer generated weather forecasts. Expand
  • 144
  • 15
  • PDF
Comparing Automatic and Human Evaluation of NLG Systems
TLDR
We consider the evaluation problem in Natural Language Generation (NLG) and present results for evaluating several NLG systems with similar functionality, including a knowledge-based generator and several statistical systems. Expand
  • 166
  • 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
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
  • 50
  • 12
  • PDF
Automatic generation of weather forecast texts using comprehensive probabilistic generation-space models
  • A. Belz
  • Computer Science
  • Natural Language Engineering
  • 1 October 2008
TLDR
This paper reports experiments in which pcru – a generation framework that combines probabilistic generation methodology with a comprehensive model of the generation space – was used to semi-automatically create five different versions of a weather forecast generator. Expand
  • 166
  • 10
  • PDF
Natural Language Generation
TLDR
An overview of recent work on psycholinguistic modeling of language production together with some key empirical findings, state-of-the-art experimental techniques, and their historical roots. Expand
  • 101
  • 8
The First Multilingual Surface Realisation Shared Task (SR’18): Overview and Evaluation Results
TLDR
We report results from the SR’18 Shared Task, a new multilingual surface realisation task organised as part of the ACL’2018 Workshop on Multilingual Surface Realisation. Expand
  • 53
  • 7
  • PDF
The Attribute Selection for GRE Challenge: Overview and Evaluation Results
TLDR
Six teams submitted a total of 22 systems.All submitted systems were tested automat-ically for minimality, uniqueness and ‘hu-manlikeness’. Expand
  • 51
  • 5
  • PDF
Introducing Shared Tasks to NLG: The TUNA Shared Task Evaluation Challenges
TLDR
We discuss the role of different evaluation methods in assessing the output quality of Referring Expression Generation algorithms, and on the relationship between such methods. Expand
  • 51
  • 4
...
1
2
3
4
5
...