Artificial Intelligence and Natural Language: 11th Conference, AINL 2022, Saint Petersburg, Russia, April 14–15, 2022, Revised Selected Papers

Preface
Organization
Contents
Inferring Image Background from Text Description
	1 Introduction
	2 Related Work
	3 Method
		3.1 Searching Location Words in the Sentence
		3.2 Searching Location Words in the Dictionary
	4 Datasets
		4.1 Real Texts
		4.2 Synthetic Texts
	5 Results
	6 Conclusions
	References
Topical Extractive Summarization
	1 Introduction
	2 Related Work
	3 Model Description
		3.1 ABAE
		3.2 Heterogeneous LexRank
	4 Datasets
		4.1 Our New Dataset Constructed from WikiPersons
	5 Experiments
		5.1 Evaluation Metrics
		5.2 Experiments with ABAE and Heterogeneous LexRank
	6 Conclusion
	A Appendix
		A.1 Experiments with BigARTM and WikiPersons
		A.2 Experiments with Neural Topic Models and WikiPersons
	References
The Semantic Shifts of the Topical Structure in the Corpus of Lentach News Posts
	1 Introduction
	2 Related Works
	3 Experimental Design
		3.1 Corpus Collecting and Preprocessing
		3.2 BERT Topic Modeling
	4 Results and Interpretation
	5 Discussion
	6 Summary
	References
Development of Folklore Motif Classifier Using Limited Data
	1 Introduction
	2 Related Work
		2.1 Zero-Shot Text Classification
		2.2 Working with ATU Index Labeled Texts
	3 Dataset
		3.1 ATU Index
		3.2 Texts
	4 Approach
	5 Experimental Setup
		5.1 Vectorizing Texts
		5.2 Models
	6 Results
	7 Conclusion
	References
Morphological and Emotional Features of the Speech in Children with Typical Development, Autism Spectrum Disorders and Down Syndrome
	1 Introduction
	2 Datasets
	3 Methods
		3.1 Graphematic Analysis of the Texts
		3.2 Morphological Text Analysis
	4 Results
	5 Conclusions and Discussion
	References
WikiMulti: A Corpus for Cross-Lingual Summarization
	1 Introduction
	2 Existing Datasets
		2.1 Multi-lingual Datasets
		2.2 Cross-Lingual Datasets
	3 WikiMulti Dataset
	4 Experiments
		4.1 Baselines
		4.2 Experimental Setup
	5 Results and Analysis
	6 Conclusion
	A  Evaluation results for the baseline models on WikiMulti
	B  English Good articles divided into categories
	References
Rethinking Crowd Sourcing for Semantic Similarity
	1 Introduction
	2 Related Work
	3 Domain-Specific Annotator Attributes for Natural Language
	4 The Data
	5 Experiments
		5.1 Filtering Heuristics for Unreliable Annotators
		5.2 Correlation with Automated Semantic Similarity Metrics
	6 Discussion
	7 Conclusion
	References
Interplay of Visual and Acoustic Cues of Irony Perception: A Case Study of Actor’s Speech
	1 Introduction
	2 Material
		2.1 Linguistic Analysis
		2.2 Requirements for the Audiovisual Material
	3 Perceptual Experiments
	4 Acoustic Analysis
	5 Co-speech Gestures
	6 Results and Discussion
	7 Conclusions
	References
Findings of Biomedical Russian to English Machine Translation Competition
	1 Introduction
	2 Dataset
		2.1 Markup Process
	3 Solutions
		3.1 Baselines
		3.2 Participant Solutions
	4 Metrics
	5 Competition Results
	6 Conclusion
	References
Translation of Medical Texts with Ensembling and Knowledge Distillation
	1 Introduction
	2 Related Work
	3 Data Preparation
	4 Description of the Approach
		4.1 Byte-Pair Encoding
		4.2 Single Model Description
		4.3 Knowledge Distillation
		4.4 Ensemble Teacher Model
	5 Evaluation and Results
		5.1 Single Teacher Model
		5.2 Ensemble Teacher Model
	6 Conclusion
	References
Author Index