Skip to main content

Can Computers write Science Books? - Brian Clegg

The German academic publisher Springer has for some time been using automated editing software (with mixed results) - but recently has brought out a whole book written by a piece of AI software called Beta Writer. The book, Lithium-Ion Batteries: a machine generated summary of current research, can be downloaded free of charge as a PDF. But is this a serious challenge for science writers?

It's certainly interesting. If I'm honest, this is hardly a book at all - it's more the output of an automated abstract generator pulled together in book form, where frankly this information would be far better just as a web page. However, there's no doubt that there is some interesting work going on here, particularly in the introduction and conclusion sections of the 'book'.

The whole thing starts with a (human written) preface explaining the technology - by far the most readable part of the text. We then get four 'chapters' of machine-generated content, which each have the format introduction/ set of abstracts / conclusion. Obviously it's the introduction and conclusion that provide the most interest.

I'll focus on the first introduction, though the same criticisms apply throughout. The first test of a piece of scientific writing meant to be readable is to take a step back and get an overview of a chunk of text - does it look like English or is it dominated by acronyms and numbers? A chunk out of the first page shows that this is very dense technical text, extremely low on readability:



The other two significant indicators of readability are whether the text is a collection of fact statements or is written using connectives and summary to give flow, and whether or not overall there is a structure that takes the reader by the hand and leads them through a communication process. On both tests, the book falls down in a big way. Pretty well every sentence is a standalone fact statement that could be a bullet point: there is no flow whatsoever. And although some attempt has been made to group these statements effectively, there is no sense of a thought-through structure. In the interminable-seeming introductions - the first one runs to 22 dense pages - there is no sense that we are going anywhere, just that we are experiencing randomly thrown together bits of data.

Inevitably, an automated process will produce some sentences that don't quite work, so one essential here is to see whether these have been captured and fixed. A reasonably high percentage of the content does make grammatical sense, but there are regular hiccups - for example we get: 

  • 'That sort of research's principal aim...' - it should be 'principle' not 'principal'. 
  • 'Materials, a number of metal oxides with high theoretical capacity have aroused more and more attention including...' - that 'Materials,' start makes no sense.
  • 'Through Tang and others, mesoporous nanosheet is synthesized...' - sounds painful.
  • 'It is still maintained the huge capacity of 611 mAg-1... when utilized as an anode.' - doesn't make any sense.
  • 'Apart from, few-layer nanosheets enhance a fast insertion...' - apart from what?
  • And so on for many, many more examples.

Going on comments I've had from some Springer authors, the level of uncaught or automatic-editing-generated errors is fairly high in their human-authored publications - these books tend not to be heavily edited - but because they are starting with far more readable text, this is less of an issue.

So, should science writers be worried? Obviously, as a professional writer myself I'm biassed, but I would say 'No' - at least, not yet. The text in the introductions and conclusions is nowhere near the readability of a decent technical science book, let alone the far higher writing quality required for a good popular science book. And the outcome also emphasises that even if, long-term, automated writing becomes more common, it is always likely to need a look over by a human editor to avoid errors creeping in. However, this is a fascinating experiment and Springer should be congratulated for getting this far.

Comments

Popular posts from this blog

Mars - Stephen James O’Meara ****

This is the latest in the excellent ‘Kosmos’ series from Reaktion Books (who clearly have a thing about the letter k). They’re beautifully packaged, with glossy paper and hundreds of colourful images, but the text is so substantial and insightful they can’t simply be dismissed as ‘coffee-table books’. My earlier reviews of the Mercury and Saturn titles, written by William Sheehan, gave both books 4 stars. This new one by Stephen James O’Meara is up to the same standard.As with the previous books, this one goes into more detail than you might expect on the ‘prehistory’ of the subject, prior to the advent of space travel. The first three chapters – about a quarter of the book – deal in turn with mythological narratives, ground-based telescopic discoveries and romantic speculations about the Red Planet. Some of this is familiar stuff, but there are some obscure gems too. The Victorian astronomer Richard Proctor, for example, decided to name dozens of newly observed features on Mars after…

Nicholas Mee - Four Way Interview

Nicholas Mee studied theoretical physics and mathematics at the University of Cambridge.  He is Director of software company Virtual Image and the author of over 50 multimedia titles including The Code Book on CD-ROM with Simon Singh and Connections in Space with John Barrow, Martin Kemp and Richard Bright. He has played key roles in numerous science and art projects including the Symbolic Sculpture project with John Robinson, the European SCIENAR project, and the 2012 Henry Moore and Stringed Surfaces exhibition at the Royal Society. He is author of the award-winning popular science book Higgs Force: Cosmic Symmetry Shattered. His latest title is Celestial Tapestry.Why mathematics?Mathematics has its own inner beauty. But it also represents far and away the most powerful set of intellectual tools that we have and it contributes enormously to our understanding of how the universe works and our place within it. Furthermore, it enables us to control and manipulate the world with great p…

Hard Time (SF) - Jodi Taylor ****

Jodi Taylor has had a lot of success with her Chronicles of St Mary's series, time travel adventures with a quirky sense of humour. Those books feature St Mary's, a sort of standalone university history department with no teaching that investigates through time travel, but whose staff are more like the inhabitants of Hogwarts than any real university. I enjoyed Plan for the Worst in that series, but found the constant juvenile jokey behaviour of the staff irritating. Here, in the second of a spin-off series, Taylor switches focus to the Time Police, an organisation that are to some extent the enemy of St Mary's, even though both are technically good guys. Although there is still far too much banter between characters, the more serious setting lifts the book to a higher level, allowing Taylor's skill at putting her characters in danger to shine through with gripping adventure.The Time Police are responsible for preserving the timeline - in this adventure they rescue a p…