A Comparative Evaluation Methodology for NLG in Interactive Systems

被引:0
|
作者
Hastie, Helen [1 ]
Belz, Anja
机构
[1] Heriot Watt Univ, Edinburgh EH14 4AS, Midlothian, Scotland
关键词
Natural Language Generation; Evaluation Methodologies; Interactive Systems;
D O I
暂无
中图分类号
H0 [语言学];
学科分类号
030303 ; 0501 ; 050102 ;
摘要
Interactive systems have become an increasingly important type of application for deployment of NLG technology over recent years. At present, we do not yet have commonly agreed terminology or methodology for evaluating NLG within interactive systems. In this paper, we take steps towards addressing this gap by presenting a set of principles for designing new evaluations in our comparative evaluation methodology. We start with presenting a categorisation framework, giving an overview of different categories of evaluation measures, in order to provide standard terminology for categorising existing and new evaluation techniques. Background on existing evaluation methodologies for NLG and interactive systems is presented. The comparative evaluation methodology is presented. Finally, a methodology for comparative evaluation of NLG components embedded within interactive systems is presented in terms of the comparative evaluation methodology, using a specific task for illustrative purposes.
引用
收藏
页码:4004 / 4011
页数:8
相关论文
共 50 条
  • [1] A Survey of Evaluation Metrics Used for NLG Systems
    Sai, Ananya B.
    Mohankumar, Akash Kumar
    Khapra, Mitesh M.
    ACM COMPUTING SURVEYS, 2023, 55 (02)
  • [2] SINotas: the Evaluation of a NLG Application
    de Araujo, Roberto P. A.
    de Oliveira, Rafael L.
    de Novais, Eder M.
    Tadeu, Thiago D.
    Pereira, Daniel B.
    Paraboni, Ivandre
    LREC 2010 - SEVENTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION, 2010, : 2388 - 2391
  • [3] Methodology to Support the Use of Interactive Systems
    Silva, J. L.
    Silva, J. C.
    PROCEEDINGS OF THE 2014 9TH IBERIAN CONFERENCE ON INFORMATION SYSTEMS AND TECHNOLOGIES (CISTI 2014), 2014,
  • [4] Human Evaluation of Creative NLG Systems: An Interdisciplinary Survey on Recent Papers
    Hamalainen, Mika
    Alnajjar, Khalid
    1ST WORKSHOP ON NATURAL LANGUAGE GENERATION, EVALUATION, AND METRICS (GEM 2021), 2021, : 84 - 95
  • [5] A task-oriented non-interactive evaluation methodology for information retrieval systems
    Reid J.
    Information Retrieval, 2000, 2 (1): : 115 - 129
  • [6] On the User-Centric Comparative Remote Evaluation of Interactive Video Search Systems
    Rossetto, Luca
    Gasser, Ralph
    Heller, Silvan
    Parian-Scherb, Mahnaz
    Sauter, Loris
    Spiess, Florian
    Schuldt, Heiko
    Peska, Ladislav
    Soucek, Tomas
    Kratochvil, Miroslav
    Mejzlik, Frantisek
    Vesely, Patrik
    Lokoc, Jakub
    IEEE MULTIMEDIA, 2021, 28 (04) : 18 - 28
  • [7] A comparative evaluation of interactive segmentation algorithms
    McGuinness, Kevin
    O'Connor, Noel E.
    PATTERN RECOGNITION, 2010, 43 (02) : 434 - 444
  • [8] A tool for comparative evaluation in an interactive environment
    Jones, S
    Vechtomova, O
    Robertson, S
    JOURNAL OF INFORMATION SCIENCE, 2002, 28 (06) : 493 - 503
  • [9] Comparative Study of Interactive Systems in a Museum
    Michael, Despina
    Pelekanos, Nectarios
    Chrysanthou, Isabelle
    Zaharias, Panagiotis
    Hadjigavriel, Loukia L.
    Chrysanthou, Yiorgos
    DIGITAL HERITAGE, 2010, 6436 : 250 - +
  • [10] Interactive learning systems evaluation
    Deeson, E
    BRITISH JOURNAL OF EDUCATIONAL TECHNOLOGY, 2004, 35 (02) : 249 - 250