Recent Trends in Analysis of Images, Social Networks and Texts

This book constitutes the refereed proceedings of the 11th International Conference on Recent Trends in Analysis of Images, Social Networks and Texts, AIST 2023, held in Yerevan, Armenia, during September 2830, 2023.

The 19 full papers 2 short papers and 1 demo paper included in this book were carefully reviewed and selected from 52 submissions. They were organized in topical sections as follows: Natural Language Processing; Computer Vision; Data Analysis and Machine Learning; Network Analysis; Theoretical Machine Learning and Optimization; and Demo Paper.

Inhalt

.- Natural Language Processing.
.- Determination of the Number of Topics Intrinsically: Is It Possible?.
.- Sentence Difficulty in Three Languages: Russian Dataset compared to Italian and English.
.- Machine Translation Models Stand Strong in the Face of Adversarial Attacks.
.- Whether Large Language Models Learn at the Inference Stage?.
.- Machine Translation for Russian-Khakas language pair: translation results in low-resource setting.
.- Automatic aspect extraction from scientific texts.
.- User Review Summarization in Russian.
.- Tuning-free Discriminative Nearest Neighbor Few-shot Intent Detection via Consecutive Knowledge Transfer.
.- Prompt-tuning for Targeted Sentiment Analysis in Russian.
.- On the Way to Controllable Text Summarization in Russian.
.- Document-level relation extraction in Russian.
.- The Battle of Information Representations: Comparing Sentiment and Semantic Features for Forecasting Market Trends.
.- Computer Vision.
.- Interactive Image Segmentation with Superpixel Propagation.
.- Gesture recognition on video data.
.- Semantic-aware GAN Manipulations for Human Face Editing.
.- Learning facial expression recognition in-the-wild from synthetic data based on an ensemble of lightweight neural networks.
.- Acne recognition: training models with experts.
.- Data Analysis and Machine Learning.
.- Application of Multimodal Machine Learning for Image Recommendation Systems.
.- Data-Driven Approach for Identifying Functional State of Hemodialysis Fistulas: Entropy-Complexity and Formal Concept Analysis.
.- Network Analysis.
.- Approximate Density Computation for OA-biclustering.
.- Theoretical Machine Learning and Optimization.
.- Distributed Bayesian Coresets.
.- Demo Paper.
.- Development of a visualization tool for the occurrence of life events on the demographic Lexis grid.