Skip to content

Ehud Reiter's Blog

Ehud's thoughts about Natural Language Generation. Also see my book on NLG.

  • Home
  • Blog Index
  • About
  • What is NLG
  • Publications
  • Resources
  • University
  • Book
  • Contact

Author: ehudreiter

Uncategorized

Accuracy, Fluency, and Utility

Oct 8, 2019Oct 8, 2019 ehudreiter6 Comments

Texts produced by NLG systems can be evaluated in terms of accuracy (content is correct), fluency (text is readable), and utility (text is useful). I discuss these three “dimensions” of NLG evaluation.

Uncategorized

Generated Texts Must Be Accurate!

Sep 26, 2019Sep 26, 2019 ehudreiter12 Comments

I’ve been shocked by the fact that many neural NLG researchers dont seem to care that their systems produce texts which contain many factual mistakes and hallucinations. NLG users expect accurate texts, and will not use systems which produce inaccurate texts, not matter how well the texts are written,

Uncategorized

The Brexit Mess

Sep 11, 2019Sep 12, 2019 ehudreiterLeave a comment

I am getting so fed up with UK politics that I will break my “no politics” rule in this blog and express my frustration with the Brexit mess and the way politicians have handled it.

Uncategorized

I’m Impressed by Capetown Uni’s Diversity

Aug 30, 2019 ehudreiterLeave a comment

I’m impressed by the diversity of NLG researchers at Capetown, from a gender, race, and disability perspective. An inspiration the rest of us!

Uncategorized

ML is Used More if it Does Not Limit Control

Aug 15, 2019 ehudreiterLeave a comment

When we try to use ML in commercial NLG contexts, one of the challenges is that NLG developers want to be able to customise, configure, and control their systems. So we need ML approaches which do not stop devs from configuring things they are likely to want to change.

Uncategorized

Do We Encourage Researchers to Use Inappropriate Data Sets?

Aug 1, 2019 ehudreiter17 Comments

I’m beginning to think that in some ways the NLP community *encourages* researchers to use poor-quality or otherwise inappropriate data sets. Which is a truly depressing thought…

Uncategorized

NLG and Explainable AI

Jul 19, 2019Jul 22, 2019 ehudreiter2 Comments

Some thoughts on key NLG challenges in explainable AI: evaluation, conceptual alignment, narrative. Comments are welcome!

Uncategorized

Why isnt Research Software such as BabyTalk Used?

Jul 8, 2019Jul 8, 2019 ehudreiter2 Comments

Most research software does not enter everyday operational use. In part because research projects usually do not worry about issues such as maintainability, regulatory approval, and change management, which are essential to the long-term success of commercial software.

Uncategorized

What Makes a Good Narrative?

Jun 24, 2019 ehudreiter4 Comments

Some thoughts on the properties texts need to have in order to be good non-fictional narratives, and speculations on how we might generate such texts.

Uncategorized

Cycling Through Wales, England, and my Wife’s Family History

Jun 3, 2019 ehudreiter1 Comment

A travelogue about my recent cycling holiday, in Wales and England, where I saw many places related to my wife’s family history,

Posts navigation

Older Posts
Newer posts
  • LinkedIn
  • Twitter

News: Come to my retirement symposium on NLG evaluation! https://retroeval.github.io/

Top Posts & Pages

  • Do LLMs cheat on benchmarks
  • Good diagrams for research papers
  • What LLMs cannot do
  • What is NLG
  • "Will I Pass my PhD Viva"
  • Challenges in Evaluating LLMs
  • MQM shows the power of a gold-standard evaluation
  • About
  • Publish in Journals!
  • Questions from readers of my book
Blog at WordPress.com.
Ehud Reiter's Blog
Blog at WordPress.com.
  • Subscribe Subscribed
    • Ehud Reiter's Blog
    • Join 102 other subscribers.
    • Already have a WordPress.com account? Log in now.
    • Ehud Reiter's Blog
    • Subscribe Subscribed
    • Sign up
    • Log in
    • Report this content
    • View site in Reader
    • Manage subscriptions
    • Collapse this bar
 

Loading Comments...