• Monument@lemmy.sdf.org
    link
    fedilink
    English
    arrow-up
    2
    ·
    edit-2
    5 months ago

    So - I don’t think Firefox would be generating captions for PDFs on PDF creation.

    But of the major ways that PDF’s do get created - converted from text editors or design software, I know that Microsoft Word automatically suggests captions when the document creator adds an image (but does not automatically apply captions), and I believe that some design software does, as well.

    I think that, functionally, both suggesting captions at time of document creation, or at time of document read are prone to the same issues - that the software may not be smart enough to properly identify the object, and if it is, that it is not necessarily smart enough to explain it in context.
    By way of example, a screenshot of a computer program will have the automatic suggestion of “A graphical user interface” (or similar), but depending on the context and usage, it could be “A virus installer disguised as ___ video game installer.” Or “The ___ video game installer.” Between the document creator and the creation software or screen reader, only the document creator would really know the context for the image.

    Which is all to say that I think that Mozilla has the right idea with auto-tagging, but it will always fail on context. The only way to actually address the issue is to deal with it within the document creation software.
    But I wouldn’t be opposed to ML on those that can auto-suggest things or even critique how content authors write their descriptions.

    • mormund@feddit.de
      link
      fedilink
      arrow-up
      1
      ·
      5 months ago

      So - I don’t think Firefox would be generating captions for PDFs on PDF creation.

      I’m not sure. The blog post is not entirely clear on that.

      Between the document creator and the creation software or screen reader, only the document creator would really know the context for the image.

      Agreed. Context is usually very important for images. But with an auto-generated caption embedded in the document itself, you already lose some context. Because if the automatic caption is incorrectly stored as “The ___ video game installer” you cannot decide anymore if this was written by the author with the context in mind or just generated. Which I would argue is worse than no caption, as it lowers your trust in all captions.

      But I wouldn’t be opposed to ML on those that can auto-suggest things or even critique how content authors write their descriptions.

      Absolutely, I think that will be by far the best solution. It could massively encourage users to write their own captions if in most cases you only need to accept the suggestion. But so far, that seems unlikely to be the way forward. Why do that when you can just throw even more “AI” at the problem?