Language Research Articles

Generative Retrieval-Augmented Ontologic Graph and Multiagent Strategies for Interpretive Large Language Model-Based Materials Design.

Transformer neural networks show promising capabilities, in particular for uses in materials analysis, design, and manufacturing, including their capacity to work effectively with human language, symbols, code, and numerical data. Here, we explore the use of large language models (LLMs) as a tool that can support engineering analysis of materials, applied to retrieving key information about subject areas, developing research hypotheses, discovery of mechanistic relationships across disparate areas of knowledge, and writing and executing simulation codes for active knowledge generation based on physical ground truths. Moreover, when used as sets of AI agents with specific features, capabilities, and instructions, LLMs can provide powerful problem-solution strategies for applications in analysis and design problems. Our experiments focus on using a fine-tuned model, MechGPT, developed based on training data in the mechanics of materials domain. We first affirm how fine-tuning endows LLMs with a reasonable understanding of subject area knowledge. However, when queried outside the context of learned matter, LLMs can have difficulty recalling correct information and may hallucinate. We show how this can be addressed using retrieval-augmented Ontological Knowledge Graph strategies. The graph-based strategy helps us not only to discern how the model understands what concepts are important but also how they are related, which significantly improves generative performance and also naturally allows for injection of new and augmented data sources into generative AI algorithms. We find that the additional feature of relatedness provides advantages over regular retrieval augmentation approaches and not only improves LLM performance but also provides mechanistic insights for exploration of a material design process. Illustrated for a use case of relating distinct areas of knowledge, here, music and proteins, such strategies can also provide an interpretable graph structure with rich information at the node, edge, and subgraph level that provides specific insights into mechanisms and relationships. We discuss other approaches to improve generative qualities, including nonlinear sampling strategies and agent-based modeling that offer enhancements over single-shot generations, whereby LLMs are used to both generate content and assess content against an objective target. Examples provided include complex question answering, code generation, and execution in the context of automated force-field development from actively learned density functional theory (DFT) modeling and data analysis.

The nature of glossolalia in the neo-Pentecostal churches in Nigeria

Glossolalia has been a major divisive doctrine in the Christendom, as some Pentecostals claim that it is proof of being a real Christian. This article examined the extent to which tongues-speaking in the neo-Pentecostal churches in Nigeria conforms to New Testament (NT) teaching. It employed narrative criticism and the phenomenological approach. The essay found that glossolalia appeared in the NT in both human and unintelligible languages. As the gift caused disorderliness in the Corinthian church, Paul says it is desirable but should not be allowed to disrupt worship. During worship, there should not be more than three people speaking in tongues, and they should do it in turn. Most importantly, if there is not an interpreter, there should be no tongues-speaking at all. The work further discovered that in the Nigerian neo-Pentecostal churches, it is the unintelligible form of glossolalia that is predominantly practised, and usually without interpretation, thereby contradicting Paul’s order. Moreover, the gift is being feigned by many to prove that they are born-again. In terms of its nature and conduct, therefore, glossolalia in the neo-Pentecostal churches in Nigeria is more of a deliberate practice than a continuation of the NT practice.Intradisciplinary and/or interdisciplinary implications: The disciplines of NT theology and Christian ethics are implicated in this article. It argues that the glossolalia being practised in the Nigerian neo-Pentecostal churches is virtually a deliberate practice rather than a spiritual gift.

The Shape of Relations to Come: Multidimensional Analyses of Complex Human Behavior

AbstractScience, understood to be the behavior of scientists, falls within the purview of behavior analysis. All scientists use scientific instruments to study a natural phenomenon, and for the behavior analyst, perhaps no tool is more important than the graph used to show changes in level, trend, and variability, and upon which behavior analysts make data-based decisions. Modern behaviorism as we know it dates back to the development of the cumulative recorder first developed in the 1930s. Though revolutionary to the science of behavior, two-dimensional graphs may be limited in application for analyzing complex human behavior. In the current article, we conceptualize verbal behavior as a multidimensional field of environmental relations, and introduce the use of multi-axial radar charts for its visual and quantitative analysis. From there, we survey the use of radar charts toward advancing a behavior-analytic understanding of human language and cognition. We demonstrate the use of radar charts for calculating simple shape descriptors as a quantitative measure of dynamic interactants, and show how they can be used to measure change over time.

Urological Cancers and ChatGPT: Assessing the Quality of Information and Possible Risks for Patients

IntroductionOpenAI has created ChatGPT, an artificial intelligence language model that has gained considerable recognition for its capacity to produce text responses resembling human language. Consequently, this study seeks to evaluate the effectiveness of ChatGPT's responses in addressing publicly accessible queries related to prostate, kidney, bladder, and testicular cancers. Material and MethodsA comprehensive compilation of frequently asked questions (FAQs) pertaining to prostate, bladder, kidney, and testicular cancers was gathered from diverse sources. Additionally, the recommendations outlined in the European Association of Urology (EAU) 2023 Guideline Oncology were consulted. The chosen questions for evaluation were presented to the ChatGPT 4.0 premium version. The quality of ChatGPT responses was appraised using the global quality score (GQS). Each ChatGPT response was independently reviewed by a panel of physicians, who assigned a GQS score to assess its overall quality. ResultsFor prostate cancer, 64.6% of the questions had a GQS score of 5, compared to 62.9 % for bladder, 68.1% for kidney, and 63.9% for testicular cancers, whereas none of the responses had a GQS score of 1. Meanwhile, the category with the lowest proportion of responses, with a GQS score of 5 for each disease, was prognosis and follow-up. The mean GQS score of the answers given to EAU guideline questions was statistically significantly lower than the average score of the answers given to FAQs. ConclusionChatGPT is a valuable tool for addressing general inquiries regarding urological cancers, boasting commendable accuracy rates. Nonetheless, its performance in responding to questions aligned with the EAU guideline was deemed unsatisfactory.

Driving and suppressing the human language network using large language models.

Transformer models such as GPT generate human-like language and are predictive of human brain responses to language. Here, using functional-MRI-measured brain responses to 1,000 diverse sentences, we first show that a GPT-based encoding model can predict the magnitude of the brain response associated with each sentence. We then use the model to identify new sentences that are predicted to drive or suppress responses in the human language network. We show that these model-selected novel sentences indeed strongly drive and suppress the activity of human language areas in new individuals. A systematic analysis of the model-selected sentences reveals that surprisal and well-formedness of linguistic input are key determinants of response strength in the language network. These results establish the ability of neural network models to not only mimic human language but also non-invasively control neural activity in higher-level cortical areas, such as the language network.

The role of artificial intelligence in generating original scientific research

Artificial intelligence (AI) is a revolutionary technology that is finding wide application across numerous sectors. Large language models (LLMs) are an emerging subset technology of AI and have been developed to communicate using human languages. At their core, LLMs are trained with vast amounts of information extracted from the internet, including text and images. Their ability to create human-like, expert text in almost any subject means they are increasingly being used as an aid to presentation, particularly in scientific writing. However, we wondered whether LLMs could go further, generating original scientific research and preparing the results for publication. We taskedGPT-4, an LLM, to write an original pharmaceutics manuscript, on a topic that is itself novel. It was able to conceive a research hypothesis, define an experimental protocol, produce photo-realistic images of 3D printed tablets, generate believable analytical data from a range of instruments and write a convincing publication-ready manuscript with evidence of critical interpretation. The model achieved all this is less than 1 h. Moreover, the generated data were multi-modal in nature, including thermal analyses, vibrational spectroscopy and dissolution testing, demonstrating multi-disciplinary expertise in the LLM. One area in which the model failed, however, was in referencing to the literature. Since the generated experimental results appeared believable though, we suggest that LLMs could certainly play a role in scientific research but with human input, interpretation and data validation. We discuss the potential benefits and current bottlenecks for realising this ambition here.

The Effect of Visual Stimuli on L2 Acquisition

This paper introduces the impact of visual stimuli on the acquisition of a Second Language (L2) or foreign language learning (FLL). Based on the importance of the role of vision in research, the findings can be classified according to three categories:(1) the comparison of multimodal audiovisual integration with conventional single-input integration; (2) the beneficial impact of visual elements on emotional stimulation; and (3) the rational synergy between the human visual system and language learning. Looking into recent studies, it is clear that people are increasingly turning to visual interactions rather than only conventional resources. Prior studies have largely concentrated on visual aids used in classroom instruction as a comprehensive tool, as opposed to a set of stimuli that are received and released. As a result, there was little discussion and attention paid to internal linkages. In line with visual contact, there has been a steady and robust advancement in social networks, encompassing well-known sites like Facebook, Instagram, YouTube, and TikTok, increasing the frequency and diversity of interactive, multi-way communication. Older and newer types of picture resources are distinguished based on how interactive they are. The success of language acquisition will be influenced by the degree of involvement. The discussion will mainly focus on emotional interaction and response mechanisms, including input, output, and attention. Three representative key literature will be selected from the classification module for in-depth study and their importance will be analyzed, aiming to describe the impact of visual stimuli on L2 acquisition from different perspectives. This balances the value of visual impacts with the potential drawbacks, allowing for new study ideas and development approaches in the field of L2 acquisition as well as the quest for more cutting-edge and successful learning techniques in the future. The results also show that visual stimuli have an important impact on L2 acquisition or foreign language learning in different dimensions in terms of interactive characteristics, whether from the perspective of cognitive-linguistic, sociolinguistic, or psycholinguistic.

Japanese Language Intonation By Japanese Language Education Students

When learning Japanese we will come across sentences that are the same but have different meanings. Because of the similarity of the sentences, many students who study Japanese often make mistakes in pronouncing the sentence and also in understanding the true meaning of it. In written language, the meaning of sentences in Japanese can be distinguished by punctuation. For example, an interrogative sentence can be distinguished by looking at the ka(か) particle behind the sentence, then a command sentence, and so on can be identified by looking at the predicate. However, in conversations, especially informal conversations, it becomes vague, for example, the loss of the ka(か) particle in interrogative sentences and so on. This can be understood by the interlocutor when we use the right intonation. In learning Japanese, less is taught about intonation differences, and there are many misunderstandings when communicating with Japanese people. Therefore, the researcher did study about the difference in meaning caused by intonation in the same sentence. This study aimed to identify intonation in sentences produced by students of the Japanese language study program. This research was carried out using exploratory qualitative research methods and data were collected using in-depth interviews. The data collected in the form of spoken sentences spoken by Japanese language study program students who are also native Japanese were classified, analyzed, and then described in writing. Interview transcripts were analyzed using thematic content analysis using a Speech Analyzer (SA) as a tool for recording, transcribing, and analyzing speech sounds. Linguists and ethnomusicologists can use SA to investigate, imitate, and explain the acoustic sounds of human language. The main respondents were students of the UNIMA Japanese Language Education Study Program. The number of respondents targeted was 30 people with a duration of 15 min of interviews. The selection of respondents were 5th-semester students who had studied Japanese for approximately 2 years and met the criteria of having studied bunpo and dokkai. Other data sources are in the form of linguistic theory and language comparison
 Keywords: language, intonation, Japanese, , education, students

Does electrical activity in fungi function as a language?

All cells generate electrical energy derived from the movements of ions across membranes. In animal neurons, action potentials play an essential role in the central nervous system. Plants utilize a variety of electrical signals to regulate a wide range of physiological processes, including wound responses, mimosa leaf movements, and cell turgor changes, such as those involved in stomatal movements. Although fungal hyphae exhibit electrical fluctuations, their regulatory role(s), if any, is still unknown. In his paper “Language of fungi derived from their electrical spiking activity”, Andrew Adamatzky, based on a quantitative analysis of voltage fluctuations in fungal mycelia, concludes that the patterns of electrical fluctuations he detects can be grouped into “words” analogous to those found in human languages. He goes on to speculate that this “fungal language” is used “to communicate and process information” between different parts of the mycelium. Here we argue on methodological grounds that the presumption of a fungal language is premature and unsupported by the evidence presented, that the voltage fluctuations he detects are likely to originate as nonbiological noise and experimental artifacts, and that the measured electrical patterns show no similarity to any properties of human language.

Emergence of machine language: towards symbolic intelligence with neural networks.

Inspired by human language, machine language is a novel discrete representation learned from visual data only through playing the speak, guess, and draw game.

Automated Text Summarization as A Service

Recent advancements in technology have enabled the storage of voluminous data. As this data is abundant, there is a need to create summaries that would capture the relevant details of the original source. Since manual summarization is a very taxing process, researchers have been actively trying to automate this process using modern computers that could try to comprehend and generate natural human language. Automated text summarization has been one of the most researched areas in the realm of Natural Language Processing (NLP). Extractive and abstractive summarization are two of the most commonly used techniques for generating summaries. In this study, we present a new methodology that takes the aforementioned summarization techniques into consideration and based on the input, generates a summary that is seemingly better than that generated using a single approach. Further, we have made an attempt to provide this methodology as a service that is deployed on the internet and is remotely accessible from anywhere. This service provided is scalable, fully responsive, and configurable. Next, we also discuss the evaluation process through which we came up with the best model out of many candidate models. Lastly, we conclude by discussing the inferences that we gained out of this study and provide a brief insight into future directions that we could explore.

The Limitations of Large Language Models for Understanding Human Language and Cognition.

Researchers have recently argued that the capabilities of Large Language Models (LLMs) can provide new insights into longstanding debates about the role of learning and/or innateness in the development and evolution of human language. Here, we argue on two grounds that LLMs alone tell us very little about human language and cognition in terms of acquisition and evolution. First, any similarities between human language and the output of LLMs are purely functional. Borrowing the "four questions" framework from ethology, we argue that what LLMs do is superficially similar, but how they do it is not. In contrast to the rich multimodal data humans leverage in interactive language learning, LLMs rely on immersive exposure to vastly greater quantities of unimodal text data, with recent multimodal efforts built upon mappings between images and text. Second, turning to functional similarities between human language and LLM output, we show that human linguistic behavior is much broader. LLMs were designed to imitate the very specific behavior of human writing; while they do this impressively, the underlying mechanisms of these models limit their capacities for meaning and naturalistic interaction, and their potential for dealing with the diversity in human language. We conclude by emphasising that LLMs are not theories of language, but tools that may be used to study language, and that can only be effectively applied with specific hypotheses to motivate research.

A Lingual Agnostic Information Retrieval System.

The exclusion of monolingual natives from cyberspace is a global socioeconomic and cultural problem. Efforts at addressing this problem have been socioeconomic, culminating in training, empowerment, and digital access with the indelible hurt of language inequities. This paper is aimed at the cyber-inclusion of monolingual natives. Since cyber participation is basically through human interaction with cyber-applications in a human language, encapsulating these applications for interaction in any human language will help evade the hurt of language inequities. Information retrieval system (IRS) remains a fundamental cyber-application. Consequently, adopting the design science research methodology, we introduced a lingual agnostic IRS architecture designed on the principle of transparency on user language detection, information translations, and caching. The detailed design of the architecture was done using the unified modeling language. The designed IRS architecture has been implemented using the agile and component-based software engineering approaches. The resultant lingual agnostic IRS (LAIRS) was evaluated using heuristics and system evaluation methods for parity of language of interaction against the default language and was excellently stable across queries and languages, guaranteeing 86% parity with the default language in the use of other languages for information access and retrieval. Furthermore, it has been shown that LAIRS is the most appropriate IRS to address the problem of language barriers to cyber-inclusion compared with existing IRSs.

Explanatory account of the human language faculty: The developmentalist challenge and biolinguistics

The aim of this paper is to explore whether Maria Kronfeldner?s analysis of human nature could be applied to the concept of cognitive systems and related capabilities, such as the human language faculty. Firstly, I will address the nature-nurture debate, that is, explanatory claims of nature as having a role in causing the language ability, and explanatory claims of culture as responsible for the development of human language capabilities. The nature-nurture divide generates a problem since it overlooks the interaction of nature and culture during the development of language capabilities, the problem called the developmentalist challenge. I will demonstrate different standpoints that try to answer this challenge, most famously the constructivist theory of Jean Piaget and the theory of universal grammar of Noam Chomsky. Following the insights of Kronfeldner, if we opt for an explanatory (and not classificatory or descriptive) account of the human language, we will search for the explanatory epistemic roles and their fulfilments. As Kronfeldner states, different sciences search for different differences regarding explanandum, and I hope to show that the integrative interdisciplinary framework dealing with cognitive systems is needed. The conclusion is that biolinguistics is an interdisciplinary field with a necessary unifying potential regarding explanatory account of the human language faculty.

Communication among animals and bioacoustics studies on bees.

The communication of honey bees encompasses diverse forms, focusing on signals that resemble those in the learning process. Bioacoustics plays a crucial role in understanding this phenomenon, especially in the context of social insects, where communicative coding is complex and essential for survival. In this article, various aspects of bee communication are analyzed, examining both acoustics and other forms of information transmission. In the bee family, there are several communication mechanisms, such as the dance of bees, vibrations, buzzing, and singing. The dance communication of honey bees, based on dance movements, dates back as far as 40 million years, making it older than human language. This form of communication is linked to environmental needs and determines the survival of bees. Signals from queen bees are associated with reproductive needs within the colony, and other individuals exhibit diverse sound characteristics. Different species of bees utilize various aspects of the environment for communication, including gravity and the position of the sun. The precision of transmitted signals may depend on the distance to a food source or potential threat. Sounds emitted by bees serve diverse functions, such as deterring predators or recruiting other individuals for food collection. Modern technologies, especially bioacoustics, enable more precise studies of bee communication. Advanced methods of vibrational spectrum analysis even allow the prediction of swarming with high effectiveness, which can be particularly useful in beekeeping practices. Studies on the bioacoustic hive, utilizing stereo microphones and soundproofing, indicate the potential of these technologies for a better understanding of bee communication in natural conditions. However, many aspects of bee communication still require more detailed research, such as the role of honey-filled cells in transmitting vibrations, necessitating the use of precise tools and technologies. The bioacoustic hive project, based on traditional bee frames, provides new insights into bee communication, especially concerning sounds generated during bee collisions within the hive. Conclusions from bioacoustic studies have significant practical potential in apiculture. The use of stereo microphones and soundproofing improves the perception and assessment of acoustic phenomena within the hive. Prospects for utilizing sound recorders for continuous monitoring of life inside the hive, and the assessment of zoo-hygienic conditions, underscore the growing importance of bioacoustics in beekeeping practices. These discoveries open new perspectives for research into the social life of these crucial insect species and their conservation.

Drought Prediction with Feature Enhanced LSTM Model using Metaheuristic Optimization Algorithms

The impact of drought builds on all three fronts of economy, environment, and society is devastating. Predicting its arrival and duration is highly important to arrange any sort of mitigation plans. The association of detailed relationship between multiple variables makes drought prediction a highly complex task. Especially influence of global warming, polar sea extent variations and their influence on overall ocean temperature have altered the seasonal rainfall behaviors all over the world. In the midst of it, predictions centered on the history of rainfall levels become inaccurate. The proposed system is an optimized deep learning prediction model integrating indigenous knowledge (IK) is proposed to predict the drought. IK expressed in human language is translated using fuzzy function and fed to an improved Long Short Term Memory (LSTM) model. The LSTM model hyperparameters are optimized using a hybrid of Particle Swarm Optimization (PSO) with firefly to produce the meta-heuristics algorithm which will provide the best performance in presence of integration of IK features into modern meteorological features which solves the problem of local minima in LSTM hyperparameter optimization. The performance of the proposed results were tested compared with the meteorological information gathered by the Karnataka Natural Disaster Monitoring Centre (KNDMC) for the district named Chitradurga of the Karnataka state in India. The proposed system which is Indigenous Knowledge merged along the cross model attention network can produce at least 1.4% higher Nash–Sutcliffe model efficiency coefficient (NSE) and 30% lower Mean Absolute Error (MAE) in the prediction of Standard Precipitation Index (SPI) compared to Convolution Neural Networks (CNN) and LSTM based time series prediction models.

Prominence effects in vocal iconicity: Implications for lexical access and language changea).

This paper explores how three cognitive and perceptual cues, vocal iconicity, resemblance-based mappings between form and meaning, and segment position and lexical stress, interact to affect word formation and language processing. The study combines an analysis of the word-internal positions that iconic segments occur in based on data from 245 language families with an experimental study in which participants representing more than 30 languages rated iconic and non-iconic pseudowords. The pseudowords were designed to systematically vary segment and stress placement across syllables. The results for study 1 indicate that segments used iconically appear approximately 0.26 segment positions closer toward the beginning of words compared to non-iconic segments. In study 2, it was found that iconic segments occurring in stressed syllables and non-iconic segments occurring in the second syllable were rated as significantly more fitting. These findings suggest that the interplay between vocal iconicity and prominence effects increases the predictive function of iconic segments by foregrounding sounds, which intrinsically carry semantic information. Consequently, these results contribute to the understanding of the widespread occurrence of vocal iconicity in human languages.

Incorporating Artificial Intelligence Into Athletic Training Education: Developing Case-Based Scenarios Using ChatGPT

Context ChatGPT is an AI-based large language model platform capable of mimicking human language patterns by responding to user queries. Although concerns over AI-generated content exist in health care and higher education, the ChatGPT platform can assist athletic training educators in creating academic content to alleviate aspects of their academic workload and responsibilities. Objective To provide a brief historical overview of ChatGPT, accepted positives and negatives, and examples of how athletic training educators can use ChatGPT for case-based scenario contention creation. Background The initial development of ChatGPT began in 2018, with its public launch in November 2022. ChatGPT uses machine and in-context learning to replicate human language expression. Since its public launch, students, researchers, educators, clinicians, governments, and companies have sought to determine how to incorporate ChatGPT into their workflow operations. Data Synthesis Athletic training educators can incorporate ChatGPT into their academic content creation methodology. With the capability of ChatGPT, athletic training educators have the potential to facilitate athletic training student learning more efficiently. Results ChatGPT can ease the academic workload of athletic training educators while being a beneficial clinical tool that athletic training students may use in their future workplace settings. Recommendation(s) Athletic training educators should consider using ChatGPT or a similar AI-based large language model platform when developing education content and simulation scenarios. Conclusions ChatGPT can lessen athletic training educator workload and potentially facilitate athletic training student learning.

Gibbon vocal communication provides insights into the origin and evolution of human music and language

Gibbon vocal communication provides insights into the origin and evolution of human music and language

Developing ChatGPT for biology and medicine: a complete review of biomedical question answering.

ChatGPT explores a strategic blueprint of question answering (QA) to deliver medical diagnoses, treatment recommendations, and other healthcare support. This is achieved through the increasing incorporation of medical domain data via natural language processing (NLP) and multimodal paradigms. By transitioning the distribution of text, images, videos, and other modalities from the general domain to the medical domain, these techniques have accelerated the progress of medical domain question answering (MDQA). They bridge the gap between human natural language and sophisticated medical domain knowledge or expert-provided manual annotations, handling large-scale, diverse, unbalanced, or even unlabeled data analysis scenarios in medical contexts. Central to our focus is the utilization of language models and multimodal paradigms for medical question answering, aiming to guide the research community in selecting appropriate mechanisms for their specific medical research requirements. Specialized tasks such as unimodal-related question answering, reading comprehension, reasoning, diagnosis, relation extraction, probability modeling, and others, as well as multimodal-related tasks like vision question answering, image captioning, cross-modal retrieval, report summarization, and generation, are discussed in detail. Each section delves into the intricate specifics of the respective method under consideration. This paper highlights the structures and advancements of medical domain explorations against general domain methods, emphasizing their applications across different tasks and datasets. It also outlines current challenges and opportunities for future medical domain research, paving the way for continued innovation and application in this rapidly evolving field. This comprehensive review serves not only as an academic resource but also delineates the course for future probes and utilization in the field of medical question answering.