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

Lucy Jane Santos - Four Way Interview

Lucy Jane Santos is an expert in the history of 20th century leisure, health and beauty, with a particular interest in (some might say obsession with) the cultural history of radioactivity. Writes & talks (a lot) about cocktails and radium. Her debut book Half Lives: The Unlikely History of Radium was published by Icon Books in July 2020.

Why science?

I have always been fascinated by the idea of science especially our daily interactions with and understandings of science – especially in a beauty context. I could spend hours pondering the labels of things on my bathroom shelf. What is 4-t-butylcyclohexanol (as a random example)? Do I really understand what I am putting on my face and spending my money on? Would it change my purchase habits if I did?  

Why this book?

This book came from an accidental discovery – that there was a product called Tho Radia which contained radium and thorium. I found out about it because I actually bought a pot of it – along with a big batch of other produc…

Rewilding: Paul Jepson and Cain Blythe ****

Those who are enthusiastic about saving the environment often have a mixed relationship with science. They might for example, support organic farming or oppose nuclear power, despite organics having no nutritional benefit and requiring far more land to be used to raise the same amount of crops, while nuclear is a green energy source that should be seen as an essential support to renewables. This same confusion can extend to the concept of rewilding, which is one reason that the subtitle of this book uses the word 'radical'.

As Paul Jepson and Cain Blythe make clear, though, radical change is what is required if we are to encourage ecological recovery. To begin with, we need to provide environments for nature that take in the big picture - thinking not just of individual nature reserves but, for example, of corridors that link areas allowing safe species migration. And we also need to move away from an arbitrary approach to restricting to 'native' species, as sometimes…

Is Einstein Still Right? - Clifford Will and Nicolas Yunes ***

If there's one thing that gets a touch tedious in science reporting it's the news headlines that some new observation or experiment 'proves Einstein right' - as if we're still not sure about relativity. At first glance that's what this book does too, but in reality Clifford Will and Nicolas Yunes are celebrating the effectiveness of the general theory of relativity, while being conscious that there may still be situations where, for whatever reason, the general theory is not sufficient.

It's a genuinely interesting book - what Will and Yunes do is take experiments that are probably familiar to the regular popular science reader already and expand on the simplified view of them we are usually given. So, for example, one of the first things they mention is the tower experiments to show the effect of gravitational red shift. I was aware of these experiments, but what we get here goes beyond the basics of the conceptual experiment to deal with the realities of d…