Data-driven Natural Language Generation: Paving the Road to Success

Jekaterina Novikova, Ondrej Dusek, Verena Rieser

Research output: Contribution to conferencePaper

Abstract

We argue that there are currently two major bottlenecks to the commercial use of statistical machine learning approaches for natural language generation (NLG): (a) The lack of reliable automatic evaluation metrics for NLG, and (b) The scarcity of high quality in-domain corpora. We address the first problem by thoroughly analysing current evaluation metrics and motivating the need for a new, more reliable metric. The second problem is addressed by presenting a novel framework for developing and evaluating a high quality corpus for NLG training.
Original languageEnglish
Number of pages3
Publication statusPublished - 30 Jul 2017
EventFirst WiNLP Workshop - Vancouver, Canada
Duration: 30 Jul 201730 Jul 2017
http://www.winlp.org/winlp-workshop/

Workshop

WorkshopFirst WiNLP Workshop
Abbreviated titleWiNLP
CountryCanada
CityVancouver
Period30/07/1730/07/17
Internet address

Keywords

  • natural language generation
  • natural language processing

Fingerprint Dive into the research topics of 'Data-driven Natural Language Generation: Paving the Road to Success'. Together they form a unique fingerprint.

  • Cite this

    Novikova, J., Dusek, O., & Rieser, V. (2017). Data-driven Natural Language Generation: Paving the Road to Success. Paper presented at First WiNLP Workshop, Vancouver, Canada. https://arxiv.org/abs/1706.09433