A Snapshot of NLG Evaluation Practices 2005 - 2014
作者： Dimitra Gkatzia , Saad Mahamood
DOI: 10.18653/V1/W15-4708
关键词:
摘要: In this paper we present a snapshot of endto-end NLG system evaluations as presented in conference and journal papers1 over the last ten years order to better understand nature type that have been undertaken. We find researchers tend favour specific evaluation methods, their approaches are also correlated with publication venue. further discuss what factors may influence types used for given system.
aclweb.org参考文章(6)
Somayajulu Sripada, Ehud Reiter, Should Corpora Texts Be Gold Standards for NLG international conference on natural language generation. pp. 97- 104 ,(2002)
Anja Belz, Ehud Reiter, Comparing automatic and human evaluation of NLG systems conference of the european chapter of the association for computational linguistics. pp. 313- 320 ,(2006)
Ehud Reiter, Anja Belz, An investigation into the validity of some metrics for automatically evaluating natural language generation systems Computational Linguistics. ,vol. 35, pp. 529- 558 ,(2009) , 10.1162/COLI.2009.35.4.35405
Mary Ellen Foster, Automated metrics that agree with human judgements on generated output for an embodied conversational agent international conference on natural language generation. pp. 95- 103 ,(2008) , 10.3115/1708322.1708341
Jukka M. Toivanen, Antoine Doucet, Hannu Toivonen, Alessandro Valitutti, "Let Everything Turn Well in Your Wife": Generation of Adult Humor Using Lexical Constraints meeting of the association for computational linguistics. pp. 243- 248 ,(2013)
Anja Belz, Helen Hastie, A Comparative Evaluation Methodology for NLG in Interactive Systems language resources and evaluation. pp. 4004- 4011 ,(2014)