Albert Gatt

Publications
Influence

SimpleNLG: A Realisation Engine for Practical Applications

Albert Gatt, Ehud Reiter
Computer Science, Chemistry
ENLG
30 March 2009

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

Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation

Albert Gatt, E. Krahmer
Computer Science
J. Artif. Intell. Res.
29 March 2017

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

In pursuit of satisfaction and the prevention of embarrassment: affective state in group recommender systems

J. Masthoff, Albert Gatt
Computer Science
User Modeling and User-Adapted Interaction
1 September 2006

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

Evaluating algorithms for the Generation of Referring Expressions using a balanced corpus

Albert Gatt, I. V. D. Sluis, Kees van Deemter
Computer Science
ENLG
17 June 2007

We describe a corpus-based evaluation methodology, applied to a number of classic algorithms in this area. Expand

The TUNA-REG Challenge 2009: Overview and Evaluation Results

Albert Gatt, A. Belz, Eric Kow
Computer Science
ENLG
30 March 2009

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

Factors causing overspecification in definite descriptions

R. Koolen, Albert Gatt, M. Goudbeek, E. Krahmer
Computer Science, Chemistry
1 October 2011

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

The TUNA Challenge 2008: Overview and Evaluation Results

Albert Gatt, A. Belz, Eric Kow
Computer Science
INLG
2008

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

Best practices for the human evaluation of automatically generated text

C. Lee, Albert Gatt, Emiel van Miltenburg, S. Wubben, E. Krahmer
Computer Science
INLG
1 October 2019

This paper provides an overview of how human evaluation is currently conducted, and presents a set of best practices, grounded in the literature. Expand

Generation of Referring Expressions: Assessing the Incremental Algorithm

Kees van Deemter, Albert Gatt, I. V. D. Sluis, R. Power
Computer Science, Medicine
Cogn. Sci.
1 July 2012

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

Automatic generation of textual summaries from neonatal intensive care data

François Portet, Ehud Reiter, +4 authors C. Sykes
Computer Science
1 May 2009

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

Recommended Authors