COMPARING NEURAL SENTENCE ENCODERS FOR TOPIC SEGMENTATION ACROSS DOMAINS: NOT YOUR TYPICAL TEXT SIMILARITY TASK

Comparing neural sentence encoders for topic segmentation across domains: not your typical text similarity task

Neural sentence encoders (NSE) are effective in many NLP tasks, including topic segmentation.However, no systematic comparison of their performance in topic segmentation has been performed.Here, we present such a comparison, using supervised and unsupervised segmentation models based on NSEs.We first compare results with baselines, showing that the

read more

Applying Nuclear Slidell Model To Calculate Energy Levels Ti42-44

In this work , we applied the nuclear shell Gift Card model by using Modified Surface Delta Interaction ( MSDI ) to study the nuclear structure for Ti42-44 nuclei from the calculation of the energy level values and its total angular momentum.After comperation with the experiment values which found to be rather in good agreement and determined the t

read more

Study on the optimal design of mistuned bladed disk (Simultaneous optimization of forced and self-excited vibration and amount of unbalance)

Although bladed disks are nominally designed to be cyclically symmetric (tuned system), the vibration characteristics of all blades on a disk are slightly different due to the manufacturing tolerance, deviations in the material properties, and wear during operation.These small variations break the cyclic symmetry and split the eigenvalue pairs.Blad

read more