Language Technology Applications Research Articles

Jezikovne tehnologije in jezikovno načrtovanje

On the one hand, language technologies strengthen the traditional language planning processes, i.e. the planning of the status and the corpus of the language, but on the other hand, they have other effects as well, which still need to be assessed from a sociolinguistic perspective, since they are not positive a priori. For a constructive synergy of technology and language planning, an interdisciplinary co-operation of disciplines from the fields of humanities and IT is necessary in all the decisive stages of the development of language technology applications.

Deep Learning-based Sequence Labeling Tools for Nepali

A Part-of-Speech (POS) tagger and Chunker (or shallow parser) are sequence labeling tools, crucial for improving the accuracy of Natural Language Processing (NLP) tasks like parsing, named entity recognition, sentiment analysis, information extraction, and so on. Developing such tools for a low-resource language is an arduous task. Nepali is a relatively resource-poor Indian language and has not been able to evolve from a computational perspective. Therefore, we present effective part-of-speech tagging and chunking tools for the Nepali text using sequential deep learning models—Bidirectional Long Short-Term Memory Network with a Conditional Random Field Layer (BI-LSTM-CRF) and other LSTM-based models exploring both character and word embeddings of the Nepali texts. Word Embedding has been used to capture syntactic as well as semantic information whereas character embedding has been applied to capture the morphological as well as shape information of words and also to handle the out-of-vocabulary problem. The developed chunker is the first statistical chunker for the Nepali language. A baseline model with a Conditional Random Field has also been developed to identify the optimum feature set for the aforementioned tasks. The BI-LSTM-CRF model produced an accuracy of 99.20% and 98.40%, for Nepali POS tagging and chunking, respectively. This is the highest-ever accuracy for Nepali. Thorough error analysis and observations have also been reported with examples. The developed tools can help advance research in Nepali language processing, improve the accuracy of language technology applications, and contribute to the preservation and promotion of the Nepali language.

Language Technology Applications: Current Developments and Future Implications

This paper provides an overview of the current developments and future implications of language technology applications in various domains, including communication, education, and business. The paper examines the use of machine translation, speech recognition, natural language generation, and text analytics in communication, as well as computer-assisted language learning, automatic essay scoring, and plagiarism detection in education. Additionally, the paper explores the use of language technology in customer service, content creation, and language localization in business. The ethical and social considerations associated with the use of language technology, including bias, privacy, security, and employment, are also discussed. Finally, the paper concludes with a summary of the main points, implications for the future, and recommendations for further research.

Application of advanced language technologies in analysis of category naming fluency task in healthy participants

AbstractBackgroundCategory naming fluency tasks have been used frequently to measure patients’ working memory and executive functions. Previous studies show that differences in scores in this task could reflect features of neurodegenerative disease. To better understand decreased performance in patients, it is critical to establish performance in healthy aging populations. Here, we investigated differences in total scores and lexical/speech features of words produced during animal fluency tasks of healthy young and older speakers which can only be derived with novel, automated, computational technologies.MethodData were collected in 52 young participants (26.9% males, mean age = 23.5±3.17) and 46 elderly participants (63.0% males, mean age = 69.9±6.77). Participants were instructed to list as many animals as possible for 60 seconds. Speech was transcribed and automatically force‐aligned. Transcripts were run through our automated Python pipeline to calculate the total number of animals listed and rate each word for the following semantic parameters: age of acquisition (AoA), ambiguity, familiarity, frequency. We also calculated phonetic and semantic distances between each word and its antecedent. Linear regression models tested the association between these automated language measures and total scores. We also examined the differences of the young and elderly groups using t‐tests.ResultElderly participants produced significantly fewer animals than young participants (p<0.001). Higher overall scores were associated with higher mean AoA (beta = 0.22, p = 0.049) and longer word duration (beta = 1.62, p = 0.037), as well as less frequent (beta = ‐0.51, p = 0.021) and familiar (beta = ‐3.96, p<0.001) animal names. We found no interaction with the age groups in any of the models. Elderly participants produced less frequent animal names than young participants (p = 0.029), along with significantly reduced phonetic distance scores (p = 0.008). Elderly participants scored significantly higher articulation rates (p = 0.007) and had a faster speech rate (p<0.001), attributable to producing more non‐animal words.ConclusionThis study demonstrates the applicability of advanced language technologies in analyzing category naming fluency tasks in healthy adults. We developed an automated scoring system and identify novel semantic and phonetic measures from digitally recorded fluency tasks. We also quantified some confounding age effects which could be explained by lexical/speech differences of words produced by the groups.

Creating electronic resources for African languages through digitisation: a technical report

The need for electronic resources for (under-resourced) African languages is an often stated one. These resources are needed for language research in general, and more specifically for the development of Human Language Technology (HLT) applications such as machine translation, speech recognition, electronic dictionaries, spelling and grammar checkers, and optical character recognition. These technologies rely on large quantities of high-quality electronic data. Digitisation is one of the strategies that can be used to collect such data. For the purpose of this paper, digitisation is understood as the conversion of analogue text, audio and video data into digital form, as well as the provision of born digital data that is currently not available in a format that enables downstream processing. There is a general perception that the African languages are under-resourced with regard to sufficient digitisation tools to function effectively in the modern digital world. Our paper is presented as a technical report, detailing the tools, procedures, best practices and standards that are utilised by the UP digitisation node to digitise text, audio and audio-visual material for the African languages. The digitisation effort is part of the South African Digital Languages Resources (SADiLaR) project (https://www.sadilar.org/index.php/en/), funded by the Department of Science and Innovation. Our report is based on a best practices document, developed through the course of our digitisation project and forms part of the deliverables as per contractual agreement between the UP digitisation node and the SADiLaR Hub. The workflow as explained in this document was designed with this specific project in mind; software and hardware utilised were also selected based on the constraints with regard to capacity and available technical skills in mind. We motivate our choice of Optical Character Recognition (OCR) software by referring to an earlier experiment in which we evaluated three commercially available OCR programmes. We did not attempt a full-scale evaluation of all available OCR software, but rather focused on selecting one that renders high quality outputs. We also reflect on one of the challenges specific to our project, i.e. copyright clearance. This is particularly relevant with regard to published material. In the absence of newspapers for specifically the African Languages (isiZulu being a notable exception), the biggest portion of textual material available for digitisation consists of printed material such as textbooks, novels, dramas, short stories and other literary genres. The digitisation process is driven by the availability of material for the different languages. Furthermore, obtaining copyright clearance from publishers is a prerequisite for digitisation and especially for the release of any digitised text data for further use and/or processing. Having information on a relatively small-scale digitisation workflow and best practices readily available will enable other interested parties to participate in the digitisation effort, thus contributing to the collection of electronic data for the African languages.

Interrogating Structural Bias in Language Technology: Focusing on the Case of Voice Chatbots in South Korea

The increasing use of language technology applications requires a more critical evaluation of the current state of language technology and its application than simply viewing it as an ideal and effective language learning aid. While an increased number of scholars have examined the issue of potential biases and hidden ideologies in language technology such as racism and gender discrimination, little attention has been paid to how the newly emerging language technology can contribute to reproduce the native speaker fallacy. This paper, focusing on the case of voice chatbots in Korea, critically examines how learning technology, in particular language technology applications, can potentially reproduce and reinforce the essentialist discourse of native speakerism, which posits native speaker accents as an ideal form of English and marginalizes nonnative English teachers and students.

Digital Transformation of Legal Services and Access to Justice: Challenges and Possibilities

Abstract The pandemic affected the access to justice situation in terms of the never rapid shift to digitalisation of legal services, and in this article, we evaluate whether artificial intelligence (AI) and its state-of-the-art technologies like machine learning and human language technologies have the potential to improve access to legal services. For this purpose, we not only examine and identify problematic areas, but also share the empirical data and insights of the practical application of AI technologies, especially human language technologies. In the first part of the article, we explore how the internet has created the foundations for a new paradigm of society including institution law. The second part of the article is devoted for analysis of challenges for access to justice in post pandemic world. In the third part, we elaborate on questions about technical feasibility, legal and moral acceptability of the digitalisation of legal services. Then follows the case analysis of the practical application of human language technologies in legal domain.

Low hanging fruit and the Boasian trilogy in digital lexicography of morphologically rich languages

Online lexicographical resources for the morphologically rich Indigenous languages in Canada use a wide range of strategies for conveying their language’s morphological system, i.e. how words are inflected and derived, which this paper illustrates in a survey of seventeen bilingual online resources. The strategies these resources employ boil down to two basic approaches to the underlying structure of the resource: 1) a lexical database, or 2) a computational model. Most resources we surveyed are constructed around lexical databases. These assume the word(form) as the basic unit, an assumption that makes it difficult to incorporate the language’s sub-word, morphological structure in full detail. However, one resource uses a computational morphological model to bring the language’s morphology into the core of the lexicon – this proved to be a “low-hanging fruit” in the application of language technology that had been accomplished within a reasonable time-frame, as has been advocated by Trond Trosterud. We discuss the value created and questions raised by this approach and argue that it successfully overcomes the traditional Boasian three-way partition of dictionary, grammar, and text, creating integrated language resources that meet the modern needs of low-resource endangered languages and their communities.

The age of computer dictionary and its problems

60’lı yıllarda bilgisayarların uygulamalı sözlükbilim alanında kullanılması, geleneksel sözlükçülüğün icrasında köklü değişimin habercisi olur. Özellikle 90’lı yıllarda elektronik dilsel verilerin bir araya getirilmesi, 21. yüzyılın başında ise az maliyetli yüksek hızlı geniş bantlı internetin artan kullanımı bu tür çalışmaların hızla artmasına neden olur. Bu gelişmeler eşliğinde kısa süre içerisinde birçok basılı sözlük elektronik ortamda yayınlanır. Elektronik yayınlanan e-sözlüklerin basılı sözlüklere olan üstünlüğü birçok sözlükbilimcinin hemen dikkatini çeker. Ancak başta melezleme (İng. hybridisation) sorunu olmak üzere derlem uyumu, veri güvenilirliği, erişim yolu, özelleştirme, nitelik ve kullanışlılık benzeri sorunlar az kişinin dikkatini çeker. Hâlbuki e-sözlükbilimdeki modern gelişmeler, disiplinin kendisinden beklenenin aşırı derecede artmasına neden olmuş; uygulama alanında köklü değişimin ortaya çıkmasına yol açmıştır. Bu çalışmada başta uygulamalı e-sözlükbilimin tarihî gelişimi yanı sıra bilgisayar sözlükçülüğü kavramının tanımı üzerinde durulmuştur. Ayrıca ilk kez Tarp (2012a, s. 256-268; 2012b, s. 116-117), tarafından tanımlanan teknolojinin e-sözlük üretim sürecindeki aşamalar [taklitçiler (İng. copycats); hızlı atlar (İng. faster horses); model t fordlar (İng. model T Fords); rolls roycelar (İng. rolls royces)] ele alınmıştır. Bunun yanı sıra çağdaş e-sözlüklerde melezleme, derlem, veri güvenilirliği, erişim yolu, kişiselleştirme ve nitelik açısından herhangi bir sorunun olup olmadığı tespit edilmeye çalışılmıştır. Bilindiği üzere e-cihazlar, dilbilimsel ve sözlükbilgisel verileri çözümlemek için dil teknolojisi yazılımına ihtiyaç duyar. Sözlükbilgisel verilerin dil teknolojisi uygulamaları tarafından okunur/anlaşılır olması için dilin ölçünlü olması gerekir. Çünkü e-cihazlar, dillerdeki eksiklik ve/veya hataları algılamada insanlara kıyasla daha hassastır. Bundan dolayı bu çalışma ile e-sözlüklerin -varsa- sorunları tespit edilmeye çalışılmış; tespit edilen sorunların giderilmesi için bazı önerilerde bulunulmuştur.

The FCG Editor: An innovative environment for engineering computational construction grammars.

Since its inception in the mid-eighties, the field of construction grammar has been steadily growing and constructionist approaches to language have by now become a mainstream paradigm for linguistic research. While the construction grammar community has traditionally focused on theoretical, experimental and corpus-based research, the importance of computational methodologies is now rapidly increasing. This movement has led to the establishment of a number of exploratory computational construction grammar formalisms, which facilitate the implementation of construction grammars, as well as their use for language processing purposes. Yet, implementing large grammars using these formalisms still remains a challenging task, partly due to a lack of powerful and user-friendly tools for computational construction grammar engineering. In order to overcome this obstacle, this paper introduces the FCG Editor, a dedicated and innovative integrated development environment for the Fluid Construction Grammar formalism. Offering a straightforward installation and a user-friendly, interactive interface, the FCG Editor is an accessible, yet powerful tool for construction grammarians who wish to operationalise their construction grammar insights and analyses in order to computationally verify them, corroborate them with corpus data, or integrate them in language technology applications.

Infraestrutura de Investigação para a Ciência e Tecnologia da Linguagem - PORTULAN CLARIN

This paper presents the PORTULAN CLARIN Research Infrastructure for the Science and Technology of Language, which is part of the European research infrastructure CLARIN ERIC as its Portuguese national node, and belongs to the Portuguese National Roadmap of Research Infrastructures of Strategic Relevance. The PORTULAN CLARIN includes a helpdesk, a repository, where resources, such as corpora, lexicons and processing tools are deposited for long-term archiving and can be searched and retrieved, and a workbench, where Language Technology tools and applications are made readily available online and can be used in different types of interfaces. Its goal is to contribute to the technological development of natural languages and for their preparation for the digital age, with a special focus on the Portuguese language in all its varieties and modalities.

The Voice and Speech Processing within Language Technology Applications: Perspective of the Russian Data Protection Law

Language technology (LT) in its broad sense comprises speech technology, computational linguistics, and natural language processing technology. These technologies are expected to have great economic potential and a considerable impact on the everyday life of society. The development of LT fosters applications for artificial intelligence (AI) and broadens the horizon for its advancement. LT deals not only with written forms of linguistic expression butalso extends to voice and speech. Voice excluding speech or its contents is a combination of unique physical patterns, such as vocal qualities, volume, speed, and certain other biometric data. Voice can provide medically relevant information, e.g. about a person’s mental state,stress level, etc., which is potentially sensitive medical data. Voice with inclusion of speech content can also include personal data (e.g. name, address, ID number, etc.). Consideration of voice and speech as personal data presents a range of legal vulnerabilities and challenges for developing and disseminating LT. This paper explores the extent to which the special regime used for personal data derived from voice and speech affects how it is processed and how it bears on the development and dissemination of LT. This investigation will identify legal vulnerabilities that arise in this connection, and its findings should be useful to both researchers and entrepreneurs in LT. The results of this study provide a basis for further research intoLT and related legal issues concerning personal data in Russia.&nbsp

Applications of virtual reality modeling language technology for COVID-19 pandemic

During COVID-19 pandemic, researchers have used innovative technologies for fast tracking the development to end this pandemic. Virtual Reality (VR) has offered an imperative role for fighting this pandemic, through audiovisual-based virtual communication. Virtual reality modeling language (VRML), as an international standard of virtual reality, has developed rapidly. VRML expanded the function of script node by introducing Java and script programs written in java script language. This paper presents a VRML method. Libraries and platoons are virtualized to meet the normal use of users. In principle, any text editing system can be used for VRML programming, but some editing systems have few related functions and are not suitable for large-scale VRML Scene Design. The VRML algorithm proposed in this paper can be applied to large buildings. The VRML algorithm proposed in this paper is compared with the traditional algorithm. The VRML algorithm proposed in this paper is superior to the traditional algorithm in the aspects of realism, interactivity, design rationality and execution speed. The practicability of the VRML algorithm is proved. It provides help for people who are inconvenient to go out during the protection period of covid-19.

The semantics of evaluational adjectives

AbstractWe apply the Natural Semantic Metalanguage (NSM) approach (Goddard & Wierzbicka 2014) to the lexical-semantic analysis of English evaluational adjectives and compare the results with the picture developed in the Appraisal Framework (Martin & White 2005). The analysis is corpus-assisted, with examples mainly drawn from film and book reviews, and supported by collocational and statistical information from WordBanks Online. We propose NSM explications for 15 evaluational adjectives, arguing that they fall into five groups, each of which corresponds to a distinct semantic template. The groups can be sketched as follows: “First-person thought-plus-affect”, e.g.wonderful; “Experiential”, e.g.entertaining; “Experiential with bodily reaction”, e.g.gripping; “Lasting impact”, e.g.memorable; “Cognitive evaluation”, e.g.complex, excellent. These groupings and semantic templates are compared with the classifications in the Appraisal Framework’s system of Appreciation. In addition, we are particularly interested in sentiment analysis, the automatic identification of evaluation and subjectivity in text. We discuss the relevance of the two frameworks for sentiment analysis and other language technology applications.

Knowledge patterns for online health portal development.

This article describes the development and evaluation of a set of knowledge patterns that provide guidelines and implications of design for developers of mental health portals. The knowledge patterns were based on three foundations: (1) knowledge integration of language technology approaches; (2) experiments with language technology applications and (3) user studies of portal interaction. A mixed-methods approach was employed for the evaluation of the knowledge patterns: formative workshops with knowledge pattern experts and summative surveys with experts in specific domains. The formative evaluation improved the cohesion of the patterns. The results of the summative evaluation showed that the problems discussed in the patterns were relevant for the domain, and that the knowledge embedded was useful to solve them. Ten patterns out of thirteen achieved an average score above 4.0, which is a positive result that leads us to conclude that they can be used as guidelines for developing health portals.

A Basic Language Resource Kit Implementation for the Igbo NLP Project

Igbo, an African language with around 32 million speakers worldwide, is one of the many languages having few or none of the language processing resources needed for advanced language technology applications. In this article, we describe the approach taken to creating an initial set of resources for Igbo, including an electronic text corpus, a part-of-speech (POS) tagset, and a POS-tagged subcorpus. We discuss the approach taken in gathering texts, the preprocessing of these texts, and the development of the POS tagged corpus. We also discuss some of the problems encountered during corpus and tagset development and the solutions arrived at for these problems.

Ob-Ugric database

In this paper we describe the data processing procedures and the preliminary results of the project Ob-Ugric database (OUDB), a web-based framework which aims at developing corpus-based descriptive resources of Khanty and Mansi dialects. Using established language documentation and annotation tools, OUDB provides interlinked corpus and lexicon data from digitized texts as well as recent fieldwork studies in an uniform IPA-transcription together with the corresponding audio recordings thus making these less described languages of the Ob-Ugric branch of the Finno-Ugric language family accessible for researchers as well as the language community and archiving the raw data for documentation, linguistic evaluation and possible future use in building resources for language technology applications.

ON DOCUMENTING LOW RESOURCED INDIAN LANGUAGES INSIGHTS FROM KANAUJI SPEECH CORPUS

Well - designed and well - developed corpora can considerably be helpful in bridging the gap between theory and practice in language documentation and revitalization process, in building language technology applications, in testing language hypothesis and in numerous other important areas. Developing a corpus for an under - resourced or endangered language encounters several problems and issues. The present study starts with an over view of the role that corpora (speech corpora in particular) can play in language documentation and revitalization process. It then provides a brief account of the situation of endangered languages and corpora development efforts in India. Thereafter, it d iscusses the various issues involved in the construction of a speech corpus for low resourced languages. Insights are followed from speech database of Kanauji of Kanpur, an endangered variety of Western Hindi, spoken in Uttar Pradesh. Kanauji speech databa se is being developed at Indian Institute of Technology Ropar, Punjab.

Modeling under-resourced languages for speech recognition

One particular problem in large vocabulary continuous speech recognition for low-resourced languages is finding relevant training data for the statistical language models. Large amount of data is required, because models should estimate the probability for all possible word sequences. For Finnish, Estonian and the other fenno-ugric languages a special problem with the data is the huge amount of different word forms that are common in normal speech. The same problem exists also in other language technology applications such as machine translation, information retrieval, and in some extent also in other morphologically rich languages. In this paper we present methods and evaluations in four recent language modeling topics: selecting conversational data from the Internet, adapting models for foreign words, multi-domain and adapted neural network language modeling, and decoding with subword units. Our evaluations show that the same methods work in more than one language and that they scale down to smaller data resources.

Iarg-AnCora: Spanish corpus annotated with implicit arguments

This article presents the Spanish Iarg-AnCora corpus (400 k-words, 13,883 sentences) annotated with the implicit arguments of deverbal nominalizations (18,397 occurrences). We describe the methodology used to create it, focusing on the annotation scheme and criteria adopted. The corpus was manually annotated and an interannotator agreement test was conducted (81 % observed agreement) in order to ensure the reliability of the final resource. The annotation of implicit arguments results in an important gain in argument and thematic role coverage (128 % on average). It is the first corpus annotated with implicit arguments for the Spanish language with a wide coverage that is freely available. This corpus can subsequently be used by machine learning-based semantic role labeling systems, and for the linguistic analysis of implicit arguments grounded on real data. Semantic analyzers are essential components of current language technology applications, which need to obtain a deeper understanding of the text in order to make inferences at the highest level to obtain qualitative improvements in the results.