Sentence Segmentation Research Articles

Exploring Natural Language Processing through an Exemplar Using YouTube.

There has been a growing emphasis on data across various health-related fields, not just in nursing research, due to the increasing volume of unstructured data in electronic health records (EHRs). Natural Language Processing (NLP) provides a solution by transforming this unstructured data into structured formats, thereby facilitating valuable insights. This methodology paper explores the application of NLP in nursing, using an exemplar case study that analyzes YouTube data to investigate social phenomena among adults living alone. The methodology involves five steps: accessing data through YouTube's API, data cleaning, preprocessing (tokenization, sentence segmentation, linguistic normalization), sentiment analysis using Python, and topic modeling. This study serves as a comprehensive guide for integrating NLP into nursing research, supplemented with digital content demonstrating each step. For successful implementation, nursing researchers must grasp the fundamental concepts and processes of NLP. The potential of NLP in nursing is significant, particularly in utilizing unstructured textual data from nursing documentation and social media. Its benefits include streamlining nursing documentation, enhancing patient communication, and improving data analysis.

Exploring Tourist Experience through Online Reviews Using Aspect-Based Sentiment Analysis with Zero-Shot Learning for Hospitality Service Enhancement

Hospitality services play a crucial role in shaping tourist satisfaction and revisiting intention toward destinations. Traditional feedback methods like surveys often fail to capture the nuanced and real-time experiences of tourists. Digital platforms such as TripAdvisor, Yelp, and Google Reviews provide a rich source of user-generated content, but the sheer volume of reviews makes manual analysis impractical. This study proposes integrating aspect-based sentiment analysis with zero-shot learning to analyze online tourist reviews effectively without requiring extensive annotated datasets. Using pretrained models like RoBERTa, the research framework involves keyword extraction, sentence segment detection, aspect construction, and sentiment polarity measurement. The dataset, sourced from TripAdvisor reviews of attractions, hotels, and restaurants in Central Java, Indonesia, underwent preprocessing to ensure suitability for analysis. The results highlight the importance of aspects such as food, accommodation, and cultural experiences in tourist satisfaction. The findings indicate a need for continuous service improvement to meet evolving tourist expectations, demonstrating the potential of advanced natural language processing techniques in enhancing hospitality services and customer satisfaction.

Segmentation-aware relational graph convolutional network with multi-layer CRF for nested named entity recognition

AbstractNamed Entity Recognition (NER) is fundamental in natural language processing, involving identifying entity spans and types within a sentence. Nested NER contains other entities, which pose a significant challenge, especially pronounced in the domain of medical-named entities due to intricate nesting patterns inherent in medical terminology. Existing studies can not capture interdependencies among different entity categories, resulting in inadequate performance in nested NER tasks. To address this problem, we propose a novel Layer-based architecture with Segmentation-aware Relational Graph Convolutional Network (LSRGCN) for Nested NER in the medical domain. LSRGCN comprises two key modules: a shared segmentation-aware encoder and a multi-layer conditional random field decoder. The former part provides token representation including boundary information from sentence segmentation. The latter part can learn the connections between different entity classes and improve recognition accuracy through secondary decoding. We conduct experiments on four datasets. Experimental results demonstrate the effectiveness of our model. Additionally, extensive studies are conducted to enhance our understanding of the model and its capabilities.

A complex network approach to analyse pre-trained language models for ancient Chinese.

Ancient Chinese is a splendid treasure within Chinese culture. To facilitate its compilation, pre-trained language models for ancient Chinese are developed. After that, researchers are actively exploring the factors contributing to their success. However, previous work did not study how language models organized the elements of ancient Chinese from a holistic perspective. Hence, we adopt complex networks to explore how language models organize the elements in ancient Chinese system. Specifically, we first analyse the characters' and words' co-occurrence networks in ancient Chinese. Then, we study characters' and words' attention networks, generated by attention heads within SikuBERT from two aspects: static and dynamic network analysis. In the static network analysis, we find that (i) most of attention networks exhibit small-world properties and scale-free behaviour, (ii) over 80% of attention networks exhibit high similarity with the corresponding co-occurrence networks, (iii) there exists a noticeable gap between characters' and words' attention networks across layers, while their fluctuations remain relatively consistent, and (iv) the attention networks generated by SikuBERT tend to be sparser compared with those from Chinese BERT. In dynamic network analysis, we find that the sentence segmentation task does not significantly affect network metrics, while the part-of-speech tagging task makes attention networks sparser.

英语被动句的汉译探析

In the academic research and practice of English translation, in-depth analysis and discussion on English passive sentences and their Chinese translation strategies are of great significance. This article employs a variety of Chinese translation strategies including direct conversion, active sentence conversion, addition, omission, and segmentation to unveil and analyze the essential factors that must be considered in the process of translating English passive sentences into Chinese. These factors encompass word class, grammatical structure, and specific language habits, underscoring their importance in ensuring the accuracy and fluency of translations. This paper aims to assist scholars and learners in the field of English translation not only to gain a deeper understanding of the grammatical and semantic characteristics of English passive sentences but also to master and apply effective translation techniques to enhance their ability to accurately translate English passive sentences into Chinese.

Harnessing Open Innovation for Translating Global Languages into Indian Lanuages

Understanding foreign languages can be challenging for individuals living in India's diverse linguistic landscapes. We propose a new technology that utilizes machine translation to address this issue, specifically focusing on speech recognition and synthesis. It aims to convert online video resources into Indian languages by integrating open-source technologies like text-to-speech (TTS), speech-to-text (STT) systems, and FFmpeg library to separate or augment audio and video. We used the whisper model, the application that can read up to 60 different Languages in the form of audio as input, and it transcripts the audio into text with segments of sentences based on timestamps. The sentence-based transcription generated by whisper is then translated into the desired language using Google Cloud translate_v2. Later, Each timestamp was individually converted into audio using the Google Cloud text-to-speech service, ensuring the audio fits inside the length of its respective timestamp. The individual audio segments are then augmented to generate the final audio in the desired language. Finally, the audio is attached to the original video, ensuring video-audio synchronization. The accuracy of the translation was verified by comparing the naturalness of the audio with general spoken language standards. This application benefits visually impaired individuals and those who cannot read text, providing them with a means to acquire knowledge in their native languages.

Tibetan Sentence Boundaries Automatic Disambiguation Based on Bidirectional Encoder Representations from Transformers on Byte Pair Encoding Word Cutting Method

Sentence Boundary Disambiguation (SBD) is crucial for building datasets for tasks such as machine translation, syntactic analysis, and semantic analysis. Currently, most automatic sentence segmentation in Tibetan adopts the methods of rule-based and statistical learning, as well as the combination of the two, which have high requirements on the corpus and the linguistic foundation of the researchers and are more costly to annotate manually. In this study, we explore Tibetan SBD using deep learning technology. Initially, we analyze Tibetan characteristics and various subword techniques, selecting Byte Pair Encoding (BPE) and Sentencepiece (SP) for text segmentation and training the Bidirectional Encoder Representations from Transformers (BERT) pre-trained language model. Secondly, we studied the Tibetan SBD based on different BERT pre-trained language models, which mainly learns the ambiguity of the shad (“།”) in different positions in modern Tibetan texts and determines through the model whether the shad (“།”) in the texts has the function of segmenting sentences. Meanwhile, this study introduces four models, BERT-CNN, BERT-RNN, BERT-RCNN, and BERT-DPCNN, based on the BERT model for performance comparison. Finally, to verify the performance of the pre-trained language models on the SBD task, this study conducts SBD experiments on both the publicly available Tibetan pre-trained language model TiBERT and the multilingual pre-trained language model (Multi-BERT). The experimental results show that the F1 score of the BERT (BPE) model trained in this study reaches 95.32% on 465,669 Tibetan sentences, nearly five percentage points higher than BERT (SP) and Multi-BERT. The SBD method based on pre-trained language models in this study lays the foundation for establishing datasets for the later tasks of Tibetan pre-training, summary extraction, and machine translation.

THE SUBJECT'S POSITION IN THE SENTENCE IN MASS-MEDIA ECOLOGICAL DISCOURSE (IN THE GERMAN-LANGUAGE MEDIA)

The article is devoted to the study of word order in sentences in German-language media texts on environmental topics. It describes the key points in the formation of the analytical structure in the German language and its influence on the word order in a sentence. The cases of the subject in the fourth place in a simple sentence and in the second place in the subordinate clause are analyzed. The sentence members shifting the subject to the right, such as the objects of time and place, mode and degree, conditions, direct and prepositional supplements, were revealed. The frequency of their use is determined. The link between the word order and the actual sentence segmentation is characterized. An attempt has been made to identify the markers of a rhema in the analysed cases and the frequency of their use. Quantitative and ordinal numerals, nouns with quantitative meaning, indefinite article, prepositional group, negation, subordinate clause and demonstrative pronoun were found to be markers of a rhema.

Quasi-real-time estimation of a loudspeaker direction from sound pressure level ratio among four channels

This paper describes a quasi-real-time estimation method of loudspeaker direction under Gaussian noise environment. Our estimation method is based on sound pressure level ratio among four channels when the loudspeaker is surrounded by four microphones. Performance of our method tends to be better when acoustic spatial radiation characteristics of sound source is skewed. Preliminary experiments show that an offline processing version of our method is more than 99% accurate in acoustically clean environments. In this paper, we discuss the noise robustness of our method through simulation experiments. Loudspeaker direction is estimated from 0.34s segments of Japanese sentences every 0.01s, that is quasi-real-time processing. Those segments are contaminated by Gaussian noise at 0dB, 10dB, 20dB. We demonstrate that the proposed method is robust to Gaussian noise. The results show that accuracies of proposed method (Prop2) are 96.9%, 98.2%, 98.4% at the band the center frequency of which is 2000Hz.

Translation transformations when transferring humor (based on A. Bradley’s novel “The Sweetness at the Bottom of the Pie”)

The article analyzes translation transformations from English into Ukrainian when conveying humor. The selected research material is Alan Bradley’s novel “The Sweetness at the Bottom of the Pie” and its translation into Ukrainian by Maria Lapenko. The analysis was carried out on the basis of C. Nord’s typology of translation transformations. The translation of humor in the novel “The Sweetness at the Bottom of the Pie” was carried out with the help of a number of translation transformations, in particular grammatical, lexical-grammatical and lexical. Quite often, the comic effect is enhanced when translated into Ukrainian. Such cases are observed, for example, in the segmentation of sentences, when the translator divides one complex sentence into two or more simple ones, making the context of humor more visible and emphasized. Besides, lexical additions of authentic Ukrainian phraseological means give imagery and expressiveness to the translation. As a result, the language of translation becomes brighter, more emotional and expressive, thus the translator not only conveys humor, but also enhances the comic effect. A decrease in the comic effect when translating into Ukrainian rarely happens, in particular, when the translator uses such transformations as grammatical replacement of sentence members and integral transformation. In these cases, an own version of the translation was given and its adequacy reasoned. In the course of the research, which has a stylistic translation purpose, the hypothesis was confirmed that the translation task of adequate reproduction of the content involves a thorough analysis of the communicative-pragmatic organization of the original text with the subsequent formation of a system of techniques and means of reproduction of the necessary pragmatic effect in the translated text. In most cases, the translator M. Lapenko managed to preserve and convey the comic effect that was laid by the author in the original.

A Review of Text Summarization Techniques Using NLP

Techniques that employ natural language processing (NLP), often known as text summarizing, automatically construct summaries of extensive texts. Extractive and abstractive summarization are two main categories that may be used to classify these methods. In extractive summarizing, the most significant lines or phrases from a text are isolated and used to generate a summary. On the other hand, in abstractive summarization, a summary is generated that is clear, short, and accurate in its representation of the text's primary concepts. NLP methods like sentence segmentation, part-of-speech tagging, named entity recognition, and semantic analysis are used in generating a summary from a text and locating and extracting relevant information from the text. Text summarizing is a subject that has received a significant amount of study and has applications in various fields, including the summation of news articles, documents, and emails, among other things.

Ranjana Script Handwritten Character Recognition using CNN

This paper proposes a public image database for Ranjana script Handwritten Character Datasets (RHCD), publicly available for Ranjana script researchers or anyone interested in the subject. To the best of our knowledge, the Ranjana script Handwritten Character Dataset (RHCD) is the first publicly available database for Ranjana script researchers. Ranjana script descended from the Brahmi script, consists of 36 consonant letters, 16 vowel letters, and 10 numerical letters. The focus of this research is three-fold: the first is to create a new database for Ranjana script Handwritten Character Recognition; the second is to test the character recognition accuracy of the created RHCD using existing CNN algorithms like LeNET-5, AlexNET, and ZFNET algorithm; the third is to propose a model by investigating different hyper-tuning parameters to improve the recognition accuracy of the created RHCD. The research method applied in this study is dataset collection, digitization & cropping, pre-processing, dataset splitting, data augmentation, and finally, implementing the CNN model (existing and proposed). Performance evaluation is based on the test accuracy, precision, recall, and F1-score. The experiment result shows that our model ranks first, with a testing accuracy of 99.73% for 64x64 pixels resolution with precision, recall, and F1-score value 1. Creation and recognition of Ranjana script characters, vowel modifiers, and compound characters can be the next milestone to be achieved. Segmentation of words and sentences into characters and recognizing each character individually can be the next research domain.

An adaptable sentence segmentation based on Indonesian rules

<p>Sentence segmentation that breaks textual data strings into individual sentences is an important phase in natural language processing (NLP). Each word in the string that is added a punctuation mark such as a period, question mark, or exclamation point, becomes the location for splitting the string. Humans can easily see the punctuation and split the string into sentences, but not machines. Basically, the three punctuation marks also perform other functions so that the sentence segmentation process must really be able to detect whether a word marked with punctuation is a sentence boundary or not. This research proposes a sentence segmentation system called segmentasi kalimat bahasa Indonesia (SKBI) or Indonesian language Sentence Segmentation by applying a set of rules and can be used in Indonesian texts and can be adapted for English. There are 34 rules built with a combination of 27 fairly complete features that contribute to this research. The experimental results for the Indonesian text show that the SKBI is able to achieve an F1-Score of 96.89% and 97.07% for English. Both need to be improved but now better than previous research.</p>

A Multi-Scale Hybrid Attention Network for Sentence Segmentation Line Detection in Dongba Scripture

Dongba scripture sentence segmentation is an important and basic work in the digitization and machine translation of Dongba scripture. Dongba scripture sentence segmentation line detection (DS-SSLD) as a core technology of Dongba scripture sentence segmentation is a challenging task due to its own distinctiveness, such as high inherent noise interference and nonstandard sentence segmentation lines. Recently, projection-based methods have been adopted. However, these methods are difficult when dealing with the following two problems. The first is the noisy problem, where a large number of noise in the Dongba scripture image interference detection results. The second is the Dongba scripture inherent characteristics, where many vertical lines in Dongba hieroglyphs are easily confused with the vertical sentence segmentation lines. Therefore, this paper aims to propose a module based on the convolutional neural network (CNN) to improve the accuracy of DS-SSLD. To achieve this, we first construct a tagged dataset for training and testing DS-SSLD, including 2504 real images collected from Dongba scripture books and sentence segmentation targets. Then, we propose a multi-scale hybrid attention network (Multi-HAN) based on YOLOv5s, where a multiple hybrid attention unit (MHAU) is used to enhance the distinction between important features and redundant features, and the multi-scale cross-stage partial unit (Multi-CSPU) is used to realize multi-scale and richer feature representation. The experiment is carried out on the Dongba scripture sentence segmentation dataset we built. The experimental results show that the proposed method exhibits excellent detection performance and outperforms several state-of-the-art methods.

Assessing the communication needs of parents of children with cancer - semantic, grammatical and psychological analyses

The objective of the present study is to evaluate the communication needs of the parents of children with cancer from the perspective of the semantic values of the morphological units used and integrated into sentence structures or sentence segments (with response status to open questions) and from the perspective of the factual analysis of the percentages of closed questions. We believe that the results we have reached, processed with interdisciplinary tools of psycholinguistics, morphology, syntax and semantics of the Romanian language and psychological analysis, can provide data that can contribute to the identification of the best strategies for ensuring emotional well-being and increasing the quality of life of families where there is a child with cancer.

Pairwise Cross-Document Event Coreference Resolution with Contrastive Learning

Cross-Document (CD) Event Coreference Resolution (ECR) is a fundamental task in Natural Language processing (NLP) and Knowledge Base Population (KBP). Resolving the event coreference relationship is a challenging task, which necessitates a thorough semantic comprehension of the events. Existing methods have spontaneously formulated this problem as a binary classification task based on sentence segments. However, the information distributed in the longer context is ignored by most prior works. Recent event coreference works focus on adding auxiliary information to improve the performance. The information such as involved entity information, structural information or database queried information is extracted from related documents as long context. Whereas extraction error, matching error and other types of error are introduced in the process of obtaining related information when the context is incomplete. In this work, we present a Contrastive Learning based Pairwise Event Coreference (CLPEC) framework to complete and optimize the CD-ECR task utilizing contextual information with contrastive learning technology. We also adopt augmentation technology to preprocess event representations and improve our performance. Experiment results show that we achieve competitive results on a number of key metrics on the ECB+ corpus.

Automatic sentence segmentation for classical Chinese: The Spring and Autumn Annals as an example

Abstract There exists no sentence boundary in most classical Chinese literature texts. Since it is difficult to read literature of this kind, experts in literature or linguistics would segment the sentence manually. This article explores the effectiveness of classical Chinese sentence segmentation method so as to provide a reference for classical Chinese punctuation. On the basis of the machine learning methods, we chose three components of machine learning, namely models, tagging schemes, and features, to compare the learning results. The models include conditional random field (CRF) models, long short term memory (LSTM) models, BiLSTM–CRF models, and three Bidirectional Encoder Representation from Transformers (BERT) models. There are five tagging schemes in this article and three features including the statistical feature, Guangyun, and Fanqie. Finally, the performance of the combined feature template is evaluated by ten-fold cross-validation on four classical Chinese texts in different genres. The SikuBERT model is proved to be the most effective model for sentence segmentation at present. Different tagging schemes and various features are introduced. The results show that 5-tag-J tagging schemes can improve performance. Statistical feature, as an important clue for classical Chinese sentence segmentation, is useful in related tasks, but Guangyun and Fanqie have little impact. Other important factors of sentence segmentation are genres and writing styles.

An intelligent algorithm for fast machine translation of long English sentences

Abstract Translation of long sentences in English is a complex problem in machine translation. This work briefly introduced the basic framework of intelligent machine translation algorithm and improved the long short-term memory (LSTM)-based intelligent machine translation algorithm by introducing the long sentence segmentation module and reordering module. Simulation experiments were conducted using the public corpus and the local corpus containing self-collected linguistic data. The improved algorithm was compared with machine translation algorithms based on a recurrent neural network and LSTM. The results suggested that the LSTM-based machine translation algorithm added with the long sentence segmentation module and reordering module effectively segmented long sentences and translated long English sentences more accurately, and the translation was more grammatically correct.

THE EFFECTS OF AGE, PRESENTATION MODE (ONLINE, OFFLINE), AND SEGMENTATION OF AMBIGUOUS SENTENCES ON ATTACHMENT PREFERENCES OF FEMALE EFL LEARNERS

One kind of structural ambiguity is in sentences including two determiner phrases (DP) that are followed by a relative clause (RC). One example of this type of ambiguity is "Somebody shot the servant of the actress who was on the balcony". Speakers of different languages attribute RC either to DP1 or DP2. The goal of this study was to investigate the relationship between participants' age and participants' attachment preferences, as well as different ways of presenting the material (i.e., offline vs. online) on the attachment preferences. This study also aims to see if the segmentation of experimental sentences plays any role in participant attachment preferences. To this end, a sample of 50 female native speakers of Persian ranging between 15 to 25 years participated in this study. The instruments used in the present research include an offline sentence acceptability judgment test and main tests that included the first main test, offline test, online complete presentation (timed), and an online segment-by-segment sentence. For the analysis of data t-tests and ANOVA were used. The statistics showed that participants' age affects attachment preferences, and adolescents have a tendency toward DP1 selection. Different modes of presenting ambiguous sentences also affected the results; presenting materials in a self-paced online method leads to a significant difference other two modes. Finally, segmentation plays a role in the attachment preference of RC and in resolving ambiguous sentences. The results showed that students had a preference for segmented presentation rather than a holistic mode of presentation.<p> </p><p><strong> Article visualizations:</strong></p><p><img src="/-counters-/soc/0029/a.php" alt="Hit counter" /></p>

SEGMENTED CONSTRUCTIONS IN THE BELARUSIAN TRANSLATION
 OF “THE LITTLE PRINCE”

The syntax of the first Belarusian-language translation of the allegorical story-fairy tale by Antoine de Saint-Exupery “The Little Prince” (1943) is considered. It is noted that the syntactic specificity of the translation in the authorship of Edzi Agnyatsvet is primarily due to the “colloquial” nature of the work itself and the influence on the idiostyle of the translator of the Belarusian oral speech. An important role was also played by the translator’s own intentions, which manifested itself in functionally conditioned constructions: segmentation of sentences, statements with particles, structural incompleteness, etc. Such constructions in the Belarusian-language translation allowed the author to actualize the readers’ attention to the conceptually important points of the content of the tale.