Semisupervised Learning-Based Word-Sense Disambiguation Using Word Embedding for Afaan Oromoo Language by Tabor Wegi Geleta, Jara Muda Haro

“…Finding context meaning is challenging the activity of automatically identifying machine translation, indexing engines, and predicting neighbor words in natural language. …”
Get full text

METAGRAPH THEORY AS A BASIS FOR MODELING RELEVANT MEDIA DISCOURSE by Yuriy E. Gapanyuk

Get full text

INTERPRETING METAPHORICAL LANGUAGE: A CHALLENGE TO ARTIFICIAL INTELLIGENCE by Inna V. Skrynnikova

Get full text

T-LLaMA: a Tibetan large language model based on LLaMA2 by Hui Lv, Chi Pu, La Duo, Yan Li, Qingguo Zhou, Jun Shen

“…Abstract The advent of ChatGPT and GPT-4 has generated substantial interest in large language model (LLM) research, showcasing remarkable performance in various applications such as conversation systems, machine translation, and research paper summarization. However, their efficacy diminishes when applied to low-resource languages, particularly in academic research contexts like Tibetan. …”
Get full text

Tibetan–Chinese speech-to-speech translation based on discrete units by Zairan Gong, Xiaona Xu, Yue Zhao

“…Abstract Speech-to-speech translation (S2ST) has evolved from cascade systems which integrate Automatic Speech Recognition (ASR), Machine Translation (MT), and Text-to-Speech (TTS), to end-to-end models. …”
Get full text

EXPLORING AUTOMATED SUMMARIZATION: FROM EXTRACTION TO ABSTRACTION by Svetlana G. Sorokina

Get full text

Poetic and theatrical occasionalisms: Creation of new morphologically complex words by Joseph von Eichendorff, Johann Nepomuk Nestroy, Peter Handke and Arno Schmidt by Wolfgang U. Dressler, Barbara Tumfart, Dietmar Kunisch, Vanessa Hannesschläger

“…We urge that theatre productions should highlight occasionalisms and report that Nestroy’s German occasionalisms are generally better translated into English by programs of machine translation then by human translators. …”
Get full text

TEXTS OF DIFFERENT EMOTIONAL CLASSES AND THEIR TOPIC MODELING by Anastasia V. Kolmogorova, Qiuhua Sun

Get full text

ATTRIBUTION OF MEDIA TEXTS BASED ON A TRAINED NATURAL LANGUAGE MODEL AND LINGUISTIC ASSESSMENT OF IDENTIFICATION QUALITY by Vladimir A. Klyachin, Ekaterina V. Khizhnyakova

Get full text

Morphologically-analyzed and syntactically-annotated Quran datasetMendeley Data by Majdi Sawalha, Faisal Al-Shargi, Sane Yagi, Abdallah T. AlShdaifat, Bassam Hammo, Mariam Belajeed, Lubna R. Al-Ogaili

“…This dataset is particularly valuable for tasks such as dependency parsing, grammar checking, machine translation, and text summarization. The potential applications of MASAQ are vast, ranging from pedagogical uses in teaching Arabic grammar to developing sophisticated NLP tools. …”
Get full text

A Hybrid Contextual Embedding and Hierarchical Attention for Improving the Performance of Word Sense Disambiguation by Robbel Habtamu Yigzaw, Beakal Gizachew Assefa, Elefelious Getachew Belay

“…It plays a crucial role in natural language applications such as machine translation, question-answering, chatbots, information retrieval, sentiment analysis, and overall language comprehension. …”
Get full text

COMMUNICATIVE TYPE “MUNICIPAL EMPLOYEE” IN THE MEDIA SPACE: DEVELOPMENT OF AN AUTOMATIC INFORMATION AND ANALYTICAL ASSESSMENT SYSTEM by Irina S. Karabulatova, Konstantin V. Vorontsov, Daniil A. Okolyshev, Ludan Zhang

Get full text

A systematic review of Machine Learning and Deep Learning approaches in Mexico: challenges and opportunities by José Luis Uc Castillo, Ana Elizabeth Marín Celestino, Diego Armando Martínez Cruz, José Tuxpan Vargas, José Alfredo Ramos Leal, Janete Morán Ramírez

“…These models are recognized as powerful tools in many fields due to their capability to carry out several tasks such as forecasting, image classification, recognition, natural language processing, machine translation, etc. This review article aimed to provide comprehensive information on the Machine Learning and Deep Learning algorithms applied in Mexico. …”
Get full text

A BERT-Based Classification Model: The Case of Russian Fairy Tales by Валерий Дмитриевич Соловьев, Марина Ивановна Солнышкина, Andrey Ten, Николай Аркадиевич Прокопьев

“… Introduction: Automatic profiling and genre classification are crucial for text suitability assessment and as such have been in high demand in education, information retrieval, sentiment analysis, and machine translation for over a decade. Of all kinds of genres, fairy tales make one of the most challenging and valuable objects of study due to its heterogeneity and a wide range of implicit idiosyncrasies. …”
Get full text

FEN-MRMGCN: A Frontend-Enhanced Network Based on Multi-Relational Modeling GCN for Bus Arrival Time Prediction by Ting Qiu, Chan-Tong Lam, Bowie Liu, Benjamin K. Ng, Xiaochen Yuan, Sio Kei Im

Get full text

MT Evaluation in the Context of Language Complexity by Dasa Munkova, Michal Munk, null Ľubomír Benko, Jiri Stastny

“…The paper focuses on investigating the impact of artificial agent (machine translator) on human agent (posteditor) using a proposed methodology, which is based on language complexity measures, POS tags, frequent tagsets, association rules, and their summarization. …”
Get full text

RELEVANCE AND LINGUISTIC ACCURACY OF THE INFORMATION PROVIDED ON WEBSITES by Neringa Lekandrė, Gemma Navickienė

“…Some texts seem to have been machine-translated. Therefore, an assumption can be made that companies are reluctant to pay language service providers to create the content of their websites, and the internal human resources managing the websites are not aware of the requirements to be followed to maintain the relevance and linguistic accuracy of the information to be provided in several languages in case the company operates internationally. …”
Get full text

Peningkatan Akurasi Mesin Penerjemah Bahasa Inggris - Indonesia dengan Memaksimalkan Kualitas dan Kuantitas Korpus Paralel by Herry Sujaini

“…Abstract The parallel corpus has a very important role in the statistical machine translator (SMT) system. The parallel corpus obtained by various sources usually has poor quality, while the quantity of parallel corpus is the main demand for good translation results. …”
Get full text