Description
Book SynopsisThis book constitutes revised selected papers of the 10th International Conference on Analysis of Images, Social Networks and Texts, AIST 2021, held in Tbilisi, Georgia, in December 2021. Due to the COVID-19 pandemic the conference was held in hybrid mode.
The 17 full papers were carefully reviewed and selected from 118 submissions, out of which 92 were sent to peer review. The papers are organized in topical sections on natural language processing; computer vision; data analysis and machine learning; social network analysis; theoretical machine learning and optimisation.
Table of ContentsNatural Language Processing.- Call Larisa Ivanovna: Code-Mixing Fools Multilingual NLU Models.- Extracting Software Requirements from Unstructured Documents.- Continuous Prompt Tuning for Russian: How to Learn Prompts Efficiently with RuGPT3?.- An Intelligent Web-Service for Automatic Concept Map Generation.- Language-Free Regular Expression Search of Document's References.- Does BERT Look at Sentiment Lexicon?.- Context-Based Text-Graph Embeddings in Word-Sense Induction tasks.-
Computer Vision.- Analysis of Thresholding Methods for the Segmentation of Brain Vessels.- Transformer-based Deep Reinforcement Learning in VizDoom.- Text CAPTCHA Traversal via Knowledge Distillation of Convolutional Neural Networks: Exploring the Impact of Color Channels Selection.-
Data Analysis and Machine Learning.- Dropout Strikes Back: Improved Uncertainty Estimation via Diversity Sampling.- Learning to Generate Synthetic Training Data using Gradient Matching and Implicit Differentiation.-
Social Network Analysis.- Agent-Based Model for Estimation of Collective Emotions in Social Networks.- A method for identifying bridges in online social networks.-
Theoretical Machine Learning and Optimisation.- On the Pareto-Optimal Solutions in the Multimodal Clustering Problem.- On Several Edge-Disjoint MSTs with Given Diameter in Undirected Graph with Exponentially Distributed Edge Weights.- Neural Architecture Search with Structure Complexity Control.
