Language Understanding Research Articles

Developing an instrument to measure Korean pre‐service teachers' understanding of language as an epistemic tool in mathematics education

AbstractThis study adapted and validated an instrument to measure pre‐service teachers' understanding of language as an epistemic tool in mathematics education in South Korea. Initially validated for science education, the instrument was tailored for mathematics education and translated into Korean. The validation process included tests for content validity, substance validity through translation, and structural validity, affirming the instrument's efficacy in this new context. The rating scale model was employed to analyze raw response data and confirm a unidimensional model fit. To ensure the functional equivalence of translated items, rigorous domain reanalysis, translation, and back‐translation processes were implemented. A pilot study involving 215 Korean pre‐service teachers was conducted, yielding results that support the instrument's reliability and validity in measuring their understanding of language as an epistemic tool in mathematics. This adaptation provides a quantitative measure for this understanding and an example to revise the instrument for new contexts.

College Chatbot Using RASA

The rapid advancement of Artificial Intelligence, Machine Learning, etc., has brought about significant changes in the technological sphere for decades. One such transformative technology is a Chatbot, a Conversational AI capable of addressing users’ queries. These chatbots are tailored to serve various objectives, one of which is to streamline tasks in education through automation. In line with this, a paper titled “College Chatbot Using RASA” has been written, which can effectively respond to questions based on college and other college-related information. The chatbot has been made accessible via an API utilizing the Streamlit framework. The RASA framework, a key open-source technology, has been harnessed to enable the chatbot. RASA plays a vital role in the chatbot's functionality by combining two main components, Rasa Core and Rasa Natural Language Understanding (NLU). Rasa NLU component is used to deduce intent and extract necessary entities from user input, while Rasa Core generates output by constructing a probabilistic model. The model is evaluated by getting a confusion matrix and prediction confidence distribution. The chatbot, upon testing, showcases the best result of 1 for each accuracy, precision, recall, and F1 score.

Real-Time Extraction of News Events Based on BERT Model

Abstract For the large number of news reports generated every day, in order to obtain effective information from these unstructured news text data more efficiently. In this paper, we study the real-time crawling of news data from news websites through crawling techniques and propose a BERT model-based approach to extract events from news long text. In this study, NetEase news website is selected as an example for real-time extraction to crawl the news data of this website. BERT model as a pre-trained model based on two-way encoded representation of transformer performs well on natural language understanding and natural language generation tasks. In this study, we will fine-tune the training based on BERT model on news corpus related dataset and perform sequence annotation through CRF layer to finally complete the event extraction task. In this paper, the DUEE dataset is chosen to train the model, and the experiments show that the overall performance of the BERT model is better than other network models. Finally, the model of this paper is further optimised, using the ALBERT and RoBERTa models improved on the basis of the BERT model, experiments were conducted, the results show that both models are improved compared to the BERT model, the ALBERT model algorithm performs the best, the model algorithm's F1 value is 1% higher than that of BERT. The results show that the performance is optimised.

Voicing Emotion at School: Quintilian, Donatus, and Nicholas Udall

Abstract: This essay argues that late antique and early modern texts could teach pronunciation through careful attention to emotional language, even when the topic was not explicitly addressed. Rhetoricians have long been aware that certain compositions require sensitive, modulated delivery. In the Institutio Oratoria , Quintilian showed that an orator needed an understanding of language and control over his voice to transmit the emotions of a client to his audience. The performance of emotional speeches was also modeled in two pedagogical works based on the plays of Terence: Aelius Donatus’s Commentum Terentii , which was read in the early modern period, and Nicholas Udall’s Floures for Latine Spekynge (1534), a collection of lines from Terence accompanied by translations into English. Donatus and Udall interpreted the plays’ emotional lines and, in doing so, guided readers to speak them well. Pronunciation was a central part of early modern education, teaching pupils to present themselves to the world with appropriateness, coherence, and composure.

Cook’s balloon versus dinoprostone for Labour induction of term pregnancies with fetal GROWth restriction: study protocol for a randomised controlled trial in tertiary maternity hospitals in Spain (COLIGROW study)

IntroductionFetal growth restriction (FGR) affects about 3%–5% of term pregnancies. If prenatally detected and anterograde umbilical artery flow is preserved (stage I), it is recommended to deliver at term (≥...

Foucault and Wittgenstein: Practical Critique and Democratic Politics

This paper aims to explore a set of convergence points between Foucault’s and Wittgenstein’s perspectives on philosophy and language, integrating them into a mutually complementary approach that I term ‘practical critique.’ The concept of ‘practical critique’ is founded on three pillars: the understanding of philosophy and language as critical practices, the public nature of language, and confessional subjectivity. I examine these three areas of convergence across three subsequent sections. In the concluding section, I discuss how this perspective can be fertile for understanding democratic politics today. I argue that all three pillars predominantly support democratic politics over any other political form. To explain that, I engage with the debate on the language of democratic theory and the potential expansion of the understanding of the public sphere. The notion of the public that emerges from this perspective offers an alternative or supplementation to the classical Habermasian view of the public sphere and democratic theory. It is envisioned as an open space of discursive multiplicity and diversity, where practices of exclusion or oppression can be made visible, challenged, and resisted.

Inheriting the glory of PāṆinian grammar into computer science

the integration of Pāṇinian grammar principles into computer science represents a significant advancement in computational linguistics and natural language processing. Pāṇini, an ancient Indian grammarian, formulated an elaborate system of grammar known as Aṣṭādhyāyī around the 4th century BCE, which has been revered for its systematic and concise rules governing Sanskrit language structure. In recent years, there has been a growing interest in adapting Pāṇinian principles to enhance computational frameworks for understanding human languages. This paper explores the theoretical foundations of Pāṇinian grammar and its applicability in the context of modern computational linguistics. The integration of Paninian grammar into computer science enhances the accuracy and efficiency of natural language processing system and contributes to preservation and dissemination of ancient linguistic knowledge. Through this the researchers aim to bridge gap between traditional linguistic scholarship and modern computational methodologies. By embracing the systematic and rigorous framework laid out by Pāṇini millennia ago, researchers are poised to achieve new breakthroughs in understanding and processing human language through innovative computational techniques. The journey from ancient Sanskrit grammar to innovative computer science exemplifies a harmonious blend of tradition and innovation in the quest for linguistic knowledge and technological advancement. Keywords - Pāṇini, Aṣṭādhyāyī, Computational linguistics, Machine translation, semantic analysis, syntactic rules.

Methods of Teaching Russian Derivation as a Basis for Expanding the Vocabulary of Foreign Medical Students

The article raises the pedagogical problem of creating an integrated system of training foreign students receiving higher medical education using an intermediary language (English) for the state final certification, which takes place in Russian. The analysis of the texts of situational tasks in examination disciplines (therapy, surgery, obstetrics and gynecology, pediatrics) allowed us to identify their standard structure with the allocation of a finite number of typical syntactic blocks in the tasks, which allowed us to focus on their lexical content and, above all, on the systemic word-formation analysis of different parts of speech, understanding the meanings of words and their significant parts. The formation of students’ systematic understanding of language occurs through the use of functional-communicative, structural-semantic, component methods, modeling methods in word-formation refraction, methods of systematization and classification of word-formation material. This is facilitated by the innovative generalizing course “Scientific activity of a doctor” (8–10 semesters) developed by the authors, the purpose of which is to create motivational attitudes that ensure the use of system data of derivatology in teaching Russian as a foreign language. It is concluded that the creation of an idea of the Russian word structure and its assimilation, form the ability to correlate the basics of different types, to identify word-formation morphemes that make it possible to predict the meaning of previously unknown words and facilitate the understanding of a complex special text of clinical situational tasks, which contributes to the formation of a professional terminological dictionary of a medical university student. It is confirmed that methodological techniques that ensure knowledge of the semantics of communicatively significant derived lexical units make it possible to fully perceive and generate speech. Keywords: methods of teaching, derivation, linguodidactics, professional communication, bilingual education

Making mathematics visible through narrative

The latest content and practice standards for mathematics have promoted the use of academic language and discourse in this content area. As such, the WIDA Consortium has evolved its guidelines to deepen teachers’ conceptual understanding of language in their content areas, and thus, enable them to provide more effective instruction to multilingual learners. Karen L. Terrell explores one of the primary “key language uses” in mathematics — the narrative genre. She also considers how visuals can be powerful scaffolds and means of expression for multilingual learners and discusses how visuals can be used for students to both receive and express knowledge. The use of narrative and visuals can make mathematics more accessible to all students.

Chinese EMR Named Entity Recognition Using Fused Label Relations Based on Machine Reading Comprehension Framework.

Chinese electronic medical record (EMR) presents significant challenges for named entity recognition (NER) due to their specialized nature, unique language features, and diverse expressions. Traditionally, NER is treated as a sequence labeling task, where each token is assigned a label. Recent research has reframed NER within the machine reading comprehension (MRC) framework, extracting entities in a question-answer format, achieving state-of-the-art performance. However, these MRC-based methods have a significant limitation: they extract entities of various types independently, ignoring their interrelations. To address this, we introduce the Fusion Label Relations with MRC (FLR-MRC) model, which enhances the MRC model by implicitly capturing dependencies among entity types. FLR-MRC models interrelations between labels using graph attention networks, integrating these with textual data to identify entities. On the benchmark CMeEE and CCKS2017-CNER datasets, FLR-MRC achieves F1-scores of 0.6652 and 0.9101, respectively, outperforming existing clinical NER methods.

An Analysis of Primary and Secondary Slang Used in The Movie “Plane” by Jean François Richet

This study entitled “ An Analysis of Primary Slang and Secondary Slang Used in The Movie “Plane” by Jean- Francois Richet. This research aimed to explore the utilization of primary and secondary slang in the movie titled "Plane," directed by Jean-François Richet. To collect the data, a structured approach involving qualitative descriptive methods. Additionally, the study utilized Chapman (2007) as the theoretical framework. The analysis showed that secondary slang words were more common in the movie, with 16 (73%) instances, compared to 6 (27%) instances of primary slang. In conclusion, this research emphasized the importance of primary and secondary slang in the movie, showcasing their role in character interactions and narrative authenticity. The study of the movie "Plane" and the use of Chapman's slang language theory enhanced our understanding of language's contribution to cinematic storytelling.

Relation extraction using large language models: a case study on acupuncture point locations.

In acupuncture therapy, the accurate location of acupoints is essential for its effectiveness. The advanced language understanding capabilities of large language models (LLMs) like Generative Pre-trained Transformers (GPTs) and Llama present a significant opportunity for extracting relations related to acupoint locations from textual knowledge sources. This study aims to explore the performance of LLMs in extracting acupoint-related location relations and assess the impact of fine-tuning on GPT's performance. We utilized the World Health Organization Standard Acupuncture Point Locations in the Western Pacific Region (WHO Standard) as our corpus, which consists of descriptions of 361 acupoints. Five types of relations ("direction_of", "distance_of", "part_of", "near_acupoint", and "located_near") (n = 3174) between acupoints were annotated. Four models were compared: pre-trained GPT-3.5, fine-tuned GPT-3.5, pre-trained GPT-4, as well as pretrained Llama 3. Performance metrics included micro-average exact match precision, recall, and F1 scores. Our results demonstrate that fine-tuned GPT-3.5 consistently outperformed other models in F1 scores across all relation types. Overall, it achieved the highest micro-average F1 score of 0.92. The superior performance of the fine-tuned GPT-3.5 model, as shown by its F1 scores, underscores the importance of domain-specific fine-tuning in enhancing relation extraction capabilities for acupuncture-related tasks. In light of the findings from this study, it offers valuable insights into leveraging LLMs for developing clinical decision support and creating educational modules in acupuncture. This study underscores the effectiveness of LLMs like GPT and Llama in extracting relations related to acupoint locations, with implications for accurately modeling acupuncture knowledge and promoting standard implementation in acupuncture training and practice. The findings also contribute to advancing informatics applications in traditional and complementary medicine, showcasing the potential of LLMs in natural language processing.

Impact of Digital Storytelling on Motivation in Middle School English Classrooms

Motivation is a key factor in the learning process, especially in language acquisition. This research examines the effects of using digital storytelling (DST) on motivation in English classrooms. The study, which used a mixed methods approach, involved 100 middle school students in Bengaluru selected through convenience sampling. Data collection methods included questionnaires and semi-structured interviews. Students were divided into experimental and control groups, with the former receiving DST-integrated instruction and the latter being taught using traditional methods. The results of the quantitative analysis showed a positive influence on motivation in the experimental group compared to the control group. Qualitative results showed that implementing DST increased students' motivation, engagement, and understanding of the English language more effectively than traditional teaching methods. Further research is encouraged to explore the full potential of DST to improve student language skills and motivation.

Toward an Explainable Large Language Model for the Automatic Identification of the Drug-Induced Liver Injury Literature.

Drug-induced liver injury (DILI) stands as a significant concern in drug safety, representing the primary cause of acute liver failure. Identifying the scientific literature related to DILI is crucial for monitoring, investigating, and conducting meta-analyses of drug safety issues. Given the intricate and often obscure nature of drug interactions, simple keyword searching can be insufficient for the exhaustive retrieval of the DILI-relevant literature. Manual curation of DILI-related publications demands pharmaceutical expertise and is susceptible to errors, severely limiting throughput. Despite numerous efforts utilizing cutting-edge natural language processing and deep learning techniques to automatically identify the DILI-related literature, their performance remains suboptimal for real-world applications in clinical research and regulatory contexts. In the past year, large language models (LLMs) such as ChatGPT and its open-source counterpart LLaMA have achieved groundbreaking progress in natural language understanding and question answering, paving the way for the automated, high-throughput identification of the DILI-related literature and subsequent analysis. Leveraging a large-scale public dataset comprising 14 203 training publications from the CAMDA 2022 literature AI challenge, we have developed what we believe to be the first LLM specialized in DILI analysis based on LLaMA-2. In comparison with other smaller language models such as BERT, GPT, and their variants, LLaMA-2 exhibits an enhanced out-of-fold accuracy of 97.19% and area under the ROC curve of 0.9947 using 3-fold cross-validation on the training set. Despite LLMs' initial design for dialogue systems, our study illustrates their successful adaptation into accurate classifiers for automated identification of the DILI-related literature from vast collections of documents. This work is a step toward unleashing the potential of LLMs in the context of regulatory science and facilitating the regulatory review process.

Combining large language models with enterprise knowledge graphs: a perspective on enhanced natural language understanding.

Knowledge Graphs (KGs) have revolutionized knowledge representation, enabling a graph-structured framework where entities and their interrelations are systematically organized. Since their inception, KGs have significantly enhanced various knowledge-aware applications, including recommendation systems and question-answering systems. Sensigrafo, an enterprise KG developed by Expert.AI, exemplifies this advancement by focusing on Natural Language Understanding through a machine-oriented lexicon representation. Despite the progress, maintaining and enriching KGs remains a challenge, often requiring manual efforts. Recent developments in Large Language Models (LLMs) offer promising solutions for KG enrichment (KGE) by leveraging their ability to understand natural language. In this article, we discuss the state-of-the-art LLM-based techniques for KGE and show the challenges associated with automating and deploying these processes in an industrial setup. We then propose our perspective on overcoming problems associated with data quality and scarcity, economic viability, privacy issues, language evolution, and the need to automate the KGE process while maintaining high accuracy.

Building a Turkish UCCA dataset

Abstract Semantic representation is the task of conveying the meaning of a natural language utterance by converting it to a logical form that can be processed and understood by machines. It is utilised by many applications in natural language processing (NLP), particularly in tasks relevant to natural language understanding (NLU). Due to the widespread use of semantic parsing in NLP, many semantic representation schemes with different forms have been proposed; Universal Conceptual Cognitive Annotation (UCCA) is one of them. UCCA is a cross-lingual semantic annotation framework that allows easy annotation without requiring substantial linguistic knowledge. UCCA-annotated datasets have been released so far for English, French, German, Russian, and Hebrew. In this paper, we present a UCCA-annotated Turkish dataset of 400 sentences that are obtained from the METU-Sabanci Turkish Treebank. We provide the UCCA annotation specifications defined for the Turkish language so that it can be extended further. We followed a semi-automatic annotation approach, where an external semantic parser is utilised for the initial annotation of the dataset, which is manually revised by two annotators. We used the same semantic parser model to evaluate the dataset with zero-shot and few-shot learning, demonstrating that even a small sample set from the target language in the training data has a notable impact on the performance of the parser (15.6% and 2.5% gain over zero-shot for labelled and unlabelled results, respectively).

Intent detection for task‐oriented conversational agents: A comparative study of recurrent neural networks and transformer models

AbstractConversational assistants (CAs) and Task‐oriented ones, in particular, are designed to interact with users in a natural language manner, assisting them in completing specific tasks or providing relevant information. These systems employ advanced natural language understanding (NLU) and dialogue management techniques to comprehend user inputs, infer their intentions, and generate appropriate responses or actions. Over time, the CAs have gradually diversified to today touch various fields such as e‐commerce, healthcare, tourism, fashion, travel, and many other sectors. NLU is fundamental in the natural language processing (NLP) field. Identifying user intents from natural language utterances is a sub‐task of NLU that is crucial for conversational systems. The diversity in user utterances makes intent detection (ID) even a challenging problem. Recently, with the emergence of Deep Neural Networks. New State of the Art (SOA) results have been achieved for different NLP tasks. Recurrent neural networks (RNNs) and Transformer architectures are two major players in those improvements. RNNs have significantly contributed to sequence modelling across various application areas. Conversely, Transformer models represent a newer architecture leveraging attention mechanisms, extensive training data sets, and computational power. This review paper begins with a detailed exploration of RNN and Transformer models. Subsequently, it conducts a comparative analysis of their performance in intent recognition for Task‐oriented (CAs). Finally, it concludes by addressing the main challenges and outlining future research directions.

Language Diversity in “Monolingual” Japan: Language Awareness Among High School Teachers of English

ABSTRACT Decades of research has investigated the heterogeneity of English among speakers of various linguistic and cultural backgrounds, but there still remains a significant gap between how English is taught in schools in Japan and the use of the language in international communication. The “standard English” of formal education is considered to relate to ways in which students perceive kyōtsūgo (common language), as a correct and universally intelligible variety of Japanese. In light of this cross-linguistic finding, the paper explores how language diversity is conceptualised across English and Japanese by six Japanese high school teachers of English. Data drawn from interviews and correspondence were analysed using a language awareness (LA) frame. The findings revealed tension between the teachers’ understanding of language and perceptions of Japan as a “monolingual” context for English language teaching (ELT). The study has the potential to contribute to the incorporation of language diversity in ELT in Japan and beyond.

Enhancing performance of transformer-based models in natural language understanding through word importance embedding

Transformer-based models have achieved state-of-the-art performance on natural language understanding (NLU) tasks by learning important token relationships through the attention mechanism. However, we observe that attention can become overly distributed during fine-tuning, failing to preserve the dependencies between meaningful tokens adequately. This phenomenon negatively affects the learning of token relationships in sentences. To overcome this issue, we propose a methodology that embeds the feature of word importance (WI) in the transformer-based models as a new layer, weighting the words according to their importance. Our simple yet powerful approach offers a general technique to boost transformer model capabilities on NLU tasks by mitigating the risk of attention dispersion during fine-tuning. Through extensive experiments on GLUE, SuperGLUE, and SQuAD benchmarks for pre-trained models (BERT, RoBERTa, ELECTRA, and DeBERTa), and MMLU, Big Bench Hard, and DROP benchmarks for the large language model, Llama2, we validate the effectiveness of our method in consistently enhancing performance across models with negligible overhead. Furthermore, we validate that our WI layer better preserves the dependencies between important tokens than standard fine-tuning by introducing a model classifying dependent tokens from the learned attention weights. The code is available at https://github.com/bigbases/WordImportance.

Large Language Models for Intelligent Transportation: A Review of the State of the Art and Challenges

Large Language Models (LLMs), based on their highly developed ability to comprehend and generate human-like text, promise to revolutionize all aspects of society. These LLMs facilitate complex language understanding, translation, content generation, and problem-solving, enabled by vast historical data processing and fine-tuning. Throughout the past year, with the initial release of ChatGPT to the public, many papers have appeared on how to exploit LLMs for the ways we operate and interact with intelligent transportation systems. In this study, we review more than 130 papers on the subject and group them according to their major contributions into the following five categories: autonomous driving, safety, tourism, traffic, and others. Based on the aggregated proposals and findings in the extant literature, this paper concludes with a set of challenges and research recommendations, hopefully contributing to guide research in this young, yet extremely active research domain.