Hey, folks! I’m back with yet another article on Artificial Intelligence. As an engineer, during my final year capstone project, the pain I had to go through reading dozens of IEEE Papers was excruciating. I’m sure hundreds and thousands of my fellow engineers can relate to this! In short, reading scientific papers is a tough job. It always contains language and sections that one might not understand, and not all of it would be interesting to you.
Yes, there are a lot of people who are great at perusing through a tough research paper. Nevertheless, if you are someone like me, who only wants a quick summary of the research document to decide if its interesting and worth the time to study it, then there is no better way……until now!
Researchers at the Allen Institute for Artificial Intelligence have developed a new model to summarize text from scientific papers, and present it in a few sentences in the form of TLDR (Too Long Didn’t Read).
The team has rolled this model out to the Allen Institute’s Semantic Scholar search engine for papers. Currently, you’ll only see these TL;DR summaries on papers related to computer science on search results or the author’s page.
How does TLDR work?
The AI takes the most important parts from the abstract, introduction, and conclusion section of the paper to form the summary.Researchers first “pre-trained” the model on the English language. Then they created a SciTLDR data set of over 5,400 summaries of computer science papers. It was further trained on more than 20,000 titles of research papers to reduce dependency on domain knowledge while writing a synopsis. Man, that’s a lot of training data!
The trained model was able to summarize documents over 5,000 words in just 21 words on an average — that’s a compression ratio of 238. Isn’t that insane? This compression rate reminds me of the infamous compression algorithm from the TV Series Silicon Valley. Furthermore, the researchers now want to expand this model to papers in fields other than computer science.
For all the geeks out there, you can try out the AI on the Semantic Scholar search engine. It’s truly worth exploring this! You’ll never know when this powerful tool can come in handy! Also, you can read more about summarizing AI in this paper.
Watch this space as I’ll be updating the developments of this tool closely! I’m very excited to get an opportunity to actually utilise this tool. For all the Master’s and PhD students – TRUST ME, this is a BOON!
That’s all for now folks! Stay tuned for the next one and it goes without saying, be safe everyone! Please wear a mask. 😉