A few months back, the 13th IEEE International Conference on Semantic Computing, ICSC2019, was held in Newport Beach, California, and Rakuten Institute of Technology researchers were there to present a paper. The area the conference covers is very wide and addresses everything where semantics is utilized in analysis or computing, such as analysis, description and derivation of data and content.
The paper we got accepted to the conference is named Unsupervised Extractive Summarization for Product Description Using Coverage Maximization with Attribute Concept, and presents an approach to creating summaries of products based on the extraction of key product characteristics from more general product descriptions. Text summarization is currently a popular field, and other presentations also covered the topic, so being able to hear how it is approached from different perspectives was very interesting. It all led to constructive discussions about how to scale the technology, in our case to millions of items on an e-commerce platform, and how to ensure that the generated summary is consistent and natural.
The conference also had many interesting workshops and keynotes covering a range of interesting topics. We look forward to participating again in the future.
For more information on ICSC, see the link below.