When we sought to construct a company Wiki, we found one of the most important issues, after validating it, was updating knowledge. Here MIT CSAIL is looking at that problem.
Auto-Updating Websites When Facts Change
MIT Computer Science and Artificial Intelligence Laboratory
March 29, 2021
Massachusetts Institute of Technology (MIT) researchers have developed models to reduce the amount of incorrect or outdated information online and dynamically adjust to recent changes. The researchers used deep learning models to rank an initial set of about 200 million revisions to popular English-language Wikipedia pages. Annotators found about a third of the top 300,000 revisions included a factual difference. The researchers created a model to mimic the filtering performed by human annotators, which can detect nearly 85% of revisions that include a factual change. They also created a model to automatically revise texts and suggest edits to other articles, as well as a robust fact verification model. MIT's Tal Schuster said, "Instead of teaching the model that the population of a certain city is this and this, we teach it to read the current sentence from Wikipedia and find the answer that it needs." ... '
No comments:
Post a Comment