The algorithms of wordform generation and recognition

the Ludic dialect has practically found itself on the periphery of the revitalization processes. There are no academics dictionaries on this dialect in Russia (compared to the Livvi dialect), which affects the low rate of filling of the Ludic sub-corpus in the VepKar. The central part of our work is the developed rules for generating nominal word forms. The rationale for choosing the South Ludic dialect for creating rules is given. The prepared tables demonstrate examples of the Ludiс dialect’s nominal inflection paradigm for single-stem and double-stem words. Inflectional types of names of the South Ludiс dialect are formalized. Rules for identifying stems that are needed for the subsequent generation of nominal word forms of the dialect of Svyatozero are proposed. A program is described, which is part of the VepKar corpus, in which these rules are programmed. The program allows us to speed up the generation of word forms in dictionary entries for subsequent text markup. Objective: to illustrate the rules for the automatic generation of word forms, prepared using a list of stems of nominal parts of speech of the Ludic dialect of the Karelian language. Research materials: lemmas and word forms from the Open Corpus of the Vepsian and Karelian languages (VepKar). Results and novelty of the research: based on the studied theoretical sources, the researchers were able to identify grammatical patterns. In the course of the experiments carried out in the study, a list of the stems and pseudo-stems of the nominal inflection of the Ludic dialect of the Karelian language (Southern Ludic dialect) was formed; a system of rules for generating word forms was developed; a corresponding program was prepared and tested. The scientific novelty of the research lies in the development of a system of unified rules for the automatic generation of word forms for the Ludic dialect of the Karelian language, which is being implemented for the first time

Infants’ recognition of foreign-accented words: Flexible yet precise signal-to-word mapping strategies

1 IntroductionOrganizations focus on automate their processes in order to improve efficiency, reduce costs, and/or reduce human beings' errors in an easy and rapid manner. Business process management (BPM) methods provide a solution to this issue. In this context, information systems like CRM, ERP, SCM, etc. have known an increasing demand. The main problem consists of the length of the business process specifications. If new regulations appear, these specifications must be adapted. Manually extraction of visual models is time consuming. During time, a series of solutions were proposed. The literature shows a crowd of approaches that extracts data models [1], [2], [3], and process models [4], [5] from Natural Language (NL) text. This paper aims to analyze the Natural Language Processing (NLP) techniques and tools used in order to provide different types of visual representations.On the last few years, approaches based on NLP have been developed in order to automate process conversion from NL text. NLP plays an important role in NL text analysis as NLP tries to understand speech and text as humans beings would do. Colloquialism, abbreviations or typos make this task a challenging one. NLP has the origins in 1950s when Alan Turing proposed the Turing test [6], by introducing the imitation game. Since then, the literature shows a plethora of NLP tools [7], [8], [9], [10] using several machine learning techniques, our focus being on those applied on data models and process models discovery from NL text, starting with the first language parser [11] to the actual ones like NLTk [7], [8], ANTLR1, etc.Linguistic analysis is closely tied to NLP. Liddy [12] highlights 7 levels of linguistic analysis: a) Phonetic or Phonological level: how words are pronounced, b) Morphological level: prefixes, suffixes and roots analysis, c) Lexical level: word level analysis including lexical meaning and Part-Of-Speech (POS) analysis, d) Syntactic level: grammatical analysis of words in a sentence, e) Semantic level: determining the possible meanings of sentences, f) Discourse level: interpreting structure and meaning for texts larger than a sentence, g) Pragmatic level: understanding the purpose of a language.Some of the problems approached by NLP are: POS tagging, parsing, Named Entity Recognition (NER), chunking, Semantic Role Labeling (SRL). Anaphora resolution [13] refers to the interpretation of the link between the anaphor and its antecedents.The remainder of the paper is organized as follows: Section 2 briefly outlines the NLP domain, describing the levels of linguistic analysis and the main NLP approaches of analyzing NL requirements. Section 3 focuses on data and process models extraction from NL text. This section makes an introduction to Object Oriented Analysis and Business Process Modeling and analyses the existing tools that discover data and process models from text. Subsequently, Section 4 summarizes the results of this work and the conclusions are drawn in Section 5.2NLPA detailed review on NLP is given in [14] and in [15]. Jones [14] divides the history of NLP into four phases: the first starts at the beginning of the 1940s and lasts to the late 1960s, the second begins from the end of 60s and lasts to the end of 70s, the third is represented by late 80s, where the fourth phase starts in the late of 90s. Next, we will detail each phase as they were defined in [14] and [15]. First phase treated machine translation issues, while the second focused on artificial intelligence. The third phase can be called grammatico-logical phase, which is followed by the lexical phase. A fifth phase is proposed in [16] where formal theories and statistical data are combined. Since this study was published first in 1994 and then it was re-organized in 2001 we can add the sixth phase: from 2000 until present where NLP techniques are combined in order to contribute to visual models extraction.Software requirements are usually written in NL which is asymmetric and irregular [17]. …

Today, natural language text processing automation is widely used in various fields (public sector, science, education, media, everyday services, etc.). This requires appropriate software tools (services) that can provide such automated processing. The purpose of this article is to analyse and study the problems of modelling the processes of linguistic analysis of Ukrainian natural language texts and designing appropriate software with the definition of the functional capabilities of its components. The research methodology encompasses a comparative analysis of the primary software solutions in this subject area (linguistic analysis of texts presented in natural language), systematisation of approaches to automated text processing, and formalisation of these processes in the form of a corresponding process model. The scientific novelty of the research lies in the analysis of current problems in systems supporting the processes of automated processing of texts in natural language, in particular Ukrainian; the development of a process model that combines different stages and phases of linguistic analysis of texts; and the design of an appropriate software solution to support this model. Conclusions. The work examines the main problems of natural language text processing; identifies the main methods of processing Ukrainian-language texts; analyses and systematises modern systems that support individual stages of automated natural language text processing; a project for an author’s software solution that will provide linguistic analysis of Ukrainian-language texts is described; a process model for linguistic analysis of natural language texts is proposed. The use of the proposed process model by users and developers will facilitate the deployment of high-quality Ukrainian-language services; on the part of institutions (relevant software products) during the modification of the linguistic analysis system, it will contribute to obtaining a more objective view of the most common problems of linguistic analysis (so-called language problems), lexicon gaps, and priorities for updates to Ukrainian-language NLP.

Early language input is far from uniform, even among children learning the same language. For instance, while some children are exposed to a single accent in their linguistic environment, others have routine exposure to multiple accents. Nonetheless, few studies have taken this into account when examining word recognition, and none has examined this issue in infants prior to the emergence of phonological constancy (∼18 months). This study demonstrates that daily exposure to multiple accents strongly impacts infants' performance in a laboratory word form recognition task. Accent variability in the input thus needs to be carefully considered when studying speech development.

The subject of the research is machine learning models and methods for generating legal contracts with limited resources and performance evaluation benchmarks. The goal of the work is to analyse approaches of domain-specific Large Language Models development and to find the optimal method of creating independent specialized systems that can generate contracts in different languages and legal systems. The article addresses the following tasks: identification of existing companies and solutions in this area, exploring approaches to create texts in natural language, analysis of evaluation and comparison methods of such systems, inspecting limitations and shortcomings of existing solutions and approaches, finding the optimal method of developing systems with limited resources. The following results were obtained: approaches of natural language generation and their features were investigated; the "Transformer" architecture was defined as a modern standard in the field of text information generation; different model types which are based on this architecture were considered; data sources for training were analysed; methods of adapting models in specialized areas were considered; model evaluating benchmarks for various tasks were reviewed; shortcomings of the existing specialized language models and the incompleteness of existing benchmarks for contract generation task evaluation were revealed. As a result of the analytical experiment, it was determined that the Retrieval-Augmented Generation method is the most optimal for solving the given task under the given conditions. The conducted experiment and its results can be used as a basis for further research of domain-specific language models development with limited resources. Conclusions: the article provides an overview of natural language generation methods using modern machine learning techniques, considers their advantages and disadvantages for small companies and scientific institutions that have limited resources. The work examinates a specialized legal domain and the problem of contract generation and determines the most optimal method to solve it.

The article deals with the structural-semantic analysis of the linguistic terminology represented in J.-B. Rudnytsky’s scientific papers. The scientist’s approaches to term formation, ways of introducing the term into the text, interpretation of its meaning, description of situations of terminological instability, etc. have been outlined. The specific Ukrainian terms used by the linguist have been characterized on a semantic criterion. Among them are the names of sections of linguistics, linguistic phenomena, parts of speech and their types, grammatical categories and forms of their expression, types of names and word forms, names of different groups of words, affixes, and their varieties, types of sounds, graphic and punctuation marks. The structural features of the linguistic terms inherent in J.-B. Rudnytsky’s scientific idiolect (uniterms, composites, complex terms) has been defined. Terms with an adjective component are considered as a specific feature of the scientist’s idiolect. According to semantics, terms for denotation linguistic phenomena, types of language, grammatical forms, categories of tokens, sets, punctuation marks, etc. have been singled out among them. The influence of the Western Ukrainian version of the Ukrainian language on the style of Prof. J.-B. Rudnytsky’s scientific studies, in particular, linguistic terminology have been revealed. The most frequent linguistic terms of foreign origin from the researcher’s idiolexicon have been grouped on a structural criterion. The author outlines the word-forming models of term formation, characterizes the individual scientific style of J.-B. Rudnytsky, comparing them with modern trends in the development of the Ukrainian language and its terminology. The article analyzes the manifestation of terminological synonymy in the scientist’s linguistic explorations, identifies the most common terminological hyperonyms represented in his scientific texts on linguistics.

System analysis of the problem of modeling a natural language (NL) made it possible to formulate the root cause of the low efficiency of modern means for accumulating and processing knowledge in such languages. This is the complexity of intellectualization for such tools, which are created on the basis of primitive artificial programming languages that practically represent a subset of flectional analytical languages or artificial constructions based on them. To reduce the severity of the identified problem, it is proposed to build NL modeling systems on the basis of technological tools for verbalization and recognition of sense. These tools consist of semiotic models of NL lexical and grammatical means. This approach seems to be especially promising for agglutinative languages; it is supposed to be implemented on the example of the Tatar language.

Research in the field of computer linguistics is relevant due to the rapid growth of information in natural languages on the Internet and social networks. Currently, there is an increase in the amount of information that humans and machines create in natural language. Information retrieval systems, dialog systems, machine translation, and automatic resume tools, spelling check modules analyze and process texts in natural languages. Thus, the range of automatic word processing systems is wide and covers a variety of tasks. One of the most important tasks of natural language processing (NLP) is to find errors in texts and including words, identify and correct incorrect words. The article provides an overview of semi-structured data, methods, and technologies for detecting incorrect words in natural languages. An approach for identifying incorrect words in the Kazakh language was developed and the features and capabilities of this approach were analyzed. A comparative analysis of texts on the Internet and social networks and of technologies that identify incorrect words in natural languages has been carried out.

Semi-automated development of conceptual models from natural language text

Cross-lingual learning for text processing: A survey

Multiple lines of research have developed Natural Language (NL) interfaces for formulating database queries. We build upon this work, but focus on presenting a highly detailed form of the answers in NL. The answers that we present are importantly based on the provenance of tuples in the query result, detailing not only the results but also their explanations. We develop a novel method for transforming provenance information to NL, by leveraging the original NL query structure. Furthermore, since provenance information is typically large and complex, we present two solutions for its effective presentation as NL text: one that is based on provenance factorization, with novel desiderata relevant to the NL case, and one that is based on summarization. We have implemented our solution in an end-to-end system supporting questions, answers and provenance, all expressed in NL. Our experiments, including a user study, indicate the quality of our solution and its scalability.

Applications in the World Wide Web aggregate vast amounts of information from different data sources. The aggregation process is often implemented with Extract, Transform and Load (ETL) processes. Usually ETL processes require information for aggregation available in structured formats, e. g. XML or JSON. In many cases the information is provided in natural language text which makes the application of ETL processes impractical. Due to the fact that information is provided in natural language, Information Extraction (IE) systems have been evolved. They make use of Natural Language Processing (NLP) tools to derive meaning from natural language text. State-of-the-art NLP tools apply Machine Learning methods. These NLP tools perform on newspapers with good quality, but they drop accuracy in other domains. However, to improve the quality for IE systems in specific domains often NLP tools are trained on domain specific text which is a time consuming process. This paper introduces an approach using a Continuous Integration pipeline for organizing and monitoring the annotation process on domain specific corpora.

It's a world of full of information. Data is one of the important element of this era. One of the major sources of data is social media platforms like Twitter, Facebook etc. Everyday social media generates lot of data. It's a free form of communication where people communicate with each other without any restriction. Users can post anything on social media. However, human tendency of speaking about non-existing or source-less thing makes it unclear or create unuseful information and becomes unreliable information. This casual and word-of mouth form of communication leads to generate uncertain data and quality of information from factuality point of view becomes primary concern in social media. So, uncertainty detection is important in social media. Uncertainty detection in natural language text becomes challenging because dealing with natural language text is pretty complicated thing. Uncertainty is an important field of linguistics. Basically, it means “lack of information”. So, a statement whose truth value cannot be determined is considered as uncertain. Linguistics and Natural Language Processing aims at classifying factual and uncertain proposition. In this chapter, comparisons of classification algorithm have been experimented to detect uncertain propositions in Twitter data of food price crisis. Comparative analysis of classification algorithm Naive Bayes and Support Vector Machine approach is done to detect uncertain propositions of tweets related to food price crisis. A model is trained to classify certain or uncertain proposition using a training file which is annotated using cue words available in English language text. Output of algorithm is the class showing given proposition is certain or uncertain. The objective of this chapter is to have a comparative analysis of text classification approach to detect uncertain events of Twitter data of food price crisis and to improve the accuracy of uncertainty classification approaches in order to detect uncertain events in natural language processing.

Text to Scene conversion system automatically converts the given natural language text in to its visual representation such as readymade image, composite scene or animation. Natural language is a language in which we, humans interact with each other. We have built a system which converts the natural language text into the composite scene. It basically converts the sentences with spatial relationships into virtual scene. It involves the natural language processing and 3D computer graphics techniques. System consists of two main modules: text processing module and graphics module. Text processing module plays an important role. It processes the text given by user and finds the objects to create the scene. Graphics module takes this information as input and generates scene by placing those objects in relative position. As students can understand the concepts easily with the visualization, we have proposed a system of text to scene conversion to visualize maths problems, which can be useful to understand the problem statement and solve it. Application of this system in education domain can be useful in developing efficient methodology.