Improving the Way We Consume Information

Meet Ori Ernst, a PhD candidate at the Natural Language Processing Lab at Bar-Ilan University's Department of Computer Science, whose research focuses on multi-document summarization and semantic relations between texts.

Ernst's research entails summarizing a collection of documents via machine learning algorithms and artificial intelligence. In each collection of documents, Ernst aims to simulate the process of human summarization, which dissects problems into smaller problems, such as finding important pieces of information, examining duplicate pieces of information, and unifying the pieces of information into a comprehensive, readable, and coherent summary up to 100 words.

Under the supervision of Prof. Ido Dagan and Prof. Jacob Goldberger, Ernst and his colleagues are building computational models, which, when combined, produce higher quality summaries than those produced by previous models. Their research won them the runner-up prize for the Best Paper Award at the 2021 Conference on Computational Natural Language Learning (CoNLL) in Punta Cana.

Ernst explains that the findings of his research will make our lives much easier in the future. "The information that exists today on the internet is expanding at an enormous speed; therefore, automatic summary methods will enter our lives in the coming years and will change the way we consume information." For example, in the future employees will automatically receive a summary after each work meeting, including an allocation of tasks, and search engines will be able to summarize answers that include information from several sources. The same is true for summarizing long legal documents, summarizing complex medical documents, summarizing intelligence transcripts, and identifying the important intelligence information from large databases.

Ernst earned his M.Sc. (magna cum laude) and a B.Sc. (summa cum laude) in electrical engineering from Bar-Ilan's Faculty of Engineering. Now, in his doctoral thesis, he is combing the fields of engineering with computer science.

"Over the course of my studies, I've received comprehensive support from both the academic and administrative staff of the University. I have had excellent supervisors over the years who not only helped promote my academic research, but also spent a lot of time in personal pedagogy, teaching and guiding me how research should be conducted, what mistakes to avoid, and how to focus on a research topic."

Alongside his research, Ernst works as a teaching assistant at the Faculty of Engineering, supervises graduate students, and consults on several projects. He is also a recipient of the Presidential Doctoral Fellowship of Excellence, which affords him the opportunity to give back to the community and volunteer with Paamonim, a non-profit organization that provides financial management consultation to families facing financial hardship. "I have already accompanied several families who worked hard and succeeded in improving their financial situations, and I hope I can continue with this project even after my doctorate," Ernst says.