New products that let people keep relatives "alive" via AI are proliferating -- offering, say, an interactive conversation with a recently departed dad who took the time to record a video interview before he passed. Why it matters: As interest in genealogy and ancestry proliferates, these tools let families preserve memories and personal connections through generations -- even giving children a sense of the physical presence of a relative who died before they were born. One such tool, StoryFile, was notably used at the late actor Ed Asner's memorial service, where mourners were invited to "converse" with the deceased at an interactive display that featured video and audio he recorded over several days before he died. At Asner's memorial, "many people just stopped by and asked a question or a couple questions," including Jason Alexander of "Seinfeld" fame, said Matt Asner, a TV and movie producer who now runs the Ed Asner Family Center, a nonprofit for people with special needs. The big picture: StoryFile is perhaps the most robust of a growing number of tools that help people create interactive digital memories of relatives.

We present the AsNER, a named entity annotation dataset for low resource Assamese language with a baseline Assamese NER model. The dataset contains about 99k tokens comprised of text from the speech of the Prime Minister of India and Assamese play. It also contains person names, location names and addresses. The proposed NER dataset is likely to be a significant resource for deep neural based Assamese language processing. We benchmark the dataset by training NER models and evaluating using state-of-the-art architectures for supervised named entity recognition (NER) such as Fasttext, BERT, XLM-R, FLAIR, MuRIL etc. We implement several baseline approaches with state-of-the-art sequence tagging Bi-LSTM-CRF architecture. The highest F1-score among all baselines achieves an accuracy of 80.69% when using MuRIL as a word embedding method. The annotated dataset and the top performing model are made publicly available.

If a tree falls in Peru's rainforest, Greg Asner can tell you what kind it was. Asner, an ecologist at the Carnegie Institution for Science and Stanford University, uses artificial intelligence and a powerful spectral imaging method to map the rainforest in unprecedented detail. By identifying each tree species by its chemical composition, he has shown the rainforest is more diverse than anyone thought. Asner's map takes the guesswork out of protecting one of the most biodiverse places on Earth and pinpointing new areas for conservation. "It's really advancing our ability to save forests and curb climate change," he said.