Skip to content

Ehud Reiter's Blog

Ehud's thoughts and observations about Natural Language Generation

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

Category: building NLG systems

building NLG systems

Can ChatGPT do Data-to-Text?

Jan 23, 2023 ehudreiterLeave a comment

Last week I played around with using chatGPT for data-to-text, and to be honest overall I was disappointed. A few people have asked me about this, so I’ve written up some of my notes here.

building NLG systems

chatGPT: Great science, unclear commercials, hate the hype

Dec 29, 2022Dec 29, 2022 ehudreiter4 Comments

I get asked a lot about chatGPT, so I thought I’d write a blog explaining my views, which focus on its impact on data-to-text NLG. Basically I think chatGPT is really exciting science which shows major progress on many of the challenges in neural NLG. However, commercial potential is unclear, and the media hype is annoying…

building NLG systems

Simple vs Complex Models

Oct 26, 2022Oct 26, 2022 ehudreiter1 Comment

I was very impressed by a recent talk about the power of simple white-box models in tasks such as medical diagnosis. I’d love to see more work on simple models in NLP and NLG!

building NLG systems

Summarisation datasets should contain summaries!

Oct 13, 2022Oct 13, 2022 ehudreiter1 Comment

Thge most populat datasets used in summarisation (CNN/DailyMail and XSum) do not actually contain summaries. I find this worrying. Surely the best way to make make progress on summarisation is to use actual summarisation datasets, even if these are less convenient from a “leaderboard” perspective.

building NLG systems

Language is diverse!

Sep 20, 2022Sep 20, 2022 ehudreiterLeave a comment

Language is diverse, and different syntax, vocabulary, document structures, etc are used in different domains and genres. NLG developers and researchers need to keep this in mind if they are trying to develop generic NLG components.

building NLG systems

Using language models to improve rule/template NLG

Sep 8, 2022 ehudreiter1 Comment

I am excited by the idea of using a neural language model to improve the output of rule/template NLG. Many academics probably regard this as a boring use of LMs (see my previous blog), but I think it could be very useful in many real world applications.

building NLG systems

Boring uses of language models

Aug 24, 2022Sep 8, 2022 ehudreiter1 Comment

There is lots of excitement and hype about “gee whiz” uses of language models in NLG, such as generating stories from prompts. However, I suspect there maybe more real-world value in using language models for more mundane tasks such as quality assurance.

building NLG systems

We need to understand what users want!

Aug 8, 2022 ehudreiter1 Comment

We can build much better NLG systems if we understand what users want the systems to do! This may sound trite, but there is very little research in the academic community in understanding user needs and requirements, which is a shame and indeed lost opportunity.

building NLG systems

NLG=Task+Data+Model/Alg+Eval

May 20, 2022May 20, 2022 ehudreiterLeave a comment

Progress in NLG requires understanding what users want, creating high quality data sets, building models and algorithms, and thoroughly evaluating systems. I remain disappointed that the research community seems fixated on building models and pays much less attention to user needs, datasets, and evaluation.

building NLG systems

Sports NLG: Commercial vs Academic Perspective

Mar 21, 2022 ehudreiter4 Comments

Both academic researchers and commercial NLG developers are interested in building NLG systems which describe sporting events. However, they care about different things. For example, many academics show little interest in use cases, domain knowledge, robustness, and high quality input data, all of which are very important to commercial NLG developers.

Posts navigation

Older Posts
  • LinkedIn
  • Twitter

Top Posts & Pages

  • Can ChatGPT do Data-to-Text?
  • "Will I Pass my PhD Viva"
  • chatGPT: Great science, unclear commercials, hate the hype
  • Summarisation datasets should contain summaries!
  • Real-World Neural NLG
  • Texts can be accurate but still not appropriate
  • Hallucination in Neural NLG
  • What are the Problems with Rule-Based NLG?
  • Is GPT3 Useful for NLG?
  • Exercise: Find Problems in an Evaluation
Blog at WordPress.com.
Ehud Reiter's Blog
Blog at WordPress.com.
  • Follow Following
    • Ehud Reiter's Blog
    • Join 80 other followers
    • Already have a WordPress.com account? Log in now.
    • Ehud Reiter's Blog
    • Customise
    • Follow Following
    • Sign up
    • Log in
    • Report this content
    • View site in Reader
    • Manage subscriptions
    • Collapse this bar
 

Loading Comments...