2021-2022 хаврын улирлын семинар №2. Сэдэв: Их сургуулийн өгөгдлийн нэгтгэлд онтологи хөгжүүлж ашиглах нь
Машин оюуны лабораторийн 2021-2022 оны хаврын улирлын семинар №4 2022-05-11-ны лхагва гарагийн 12.40 цагт IIIА байрны 221 тоотод болно.

Машин оюуны лабын 2021-2022 хаврын улирлын семинар 2022-05-04 ны 12.40 минутад МУИС-ийн 3-р байр 221 тоотод болно.

Илтгэгч 1: Док.Б.Хуягбаатар

Сэдэв: UniMorph 4.0: Universal Morphology

Хураангуй: The Universal Morphology (UniMorph) project is a collaborative effort providing broad-coverage instantiated normalized morphological inflection tables for hundreds of diverse world languages. The project comprises two major thrusts: a language-independent feature schema for rich morphological annotation and a type-level resource of annotated data in diverse languages realizing that schema. This paper presents the expansions and improvements made on several fronts over the last couple of years (since McCarthy et al. (2020)). Collaborative efforts by numerous linguists have added 66 new languages, including 30 endangered languages. We have implemented several improvements to the extraction pipeline to tackle some issues, e.g. missing gender and macrons information. We have also amended the schema to use a hierarchical structure that is needed for morphological phenomena like multiple-argument agreement and case stacking, while adding some missing morphological features to make the schema more inclusive. In light of the last UniMorph release, we also augmented the database with morpheme segmentation for 16 languages. Lastly, this new release makes a push towards inclusion of derivational morphology in UniMorph by enriching the data and annotation schema with instances representing derivational processes from MorphyNet.

Илтгэгч 2: Докторант .Ө.Батбаяр

Сэдэв: Дүрс боловсруулалтад суурилсан амин үзүүлэлтүүдээр идэвхитэй КОВИД-19 халдварыг илрүүлэгч

Хураангуй: To address the need for preliminary detection of COVID-19 infection in afebrile subjects, we developed a novel vital-signs-based infection screening composite-type camera (VISC-Camera) to screen for possibly infected patients in a non-contact manner. Results are available within 10 seconds, including data processing time. The proposed VISC-Camera system measures 22 × 14 × 4 cm and incorporates an infrared stereo depth camera for respiratory rate determination, a red–green–blue camera for heart rate monitoring, and a thermal camera for facial temperature measurement. The system discriminates infected patients from healthy people using a logistic regression algorithm based on the three measured parameters. Clinical testing was conducted on 154 COVID-19 inpatients (aged 18–81 years; M/F=87/67) and 147 healthy volunteers (aged 18–85 years, M/F=70/77) at the First Central Hospital of Mongolia. All patients had been treated with antivirals and had body temperatures <37.5°C. The system achieved 91% sensitivity and 90% specificity.

Comments are closed.