Traditional Language Models Research Articles

Hyena architecture enables fast and efficient protein language modeling

AbstractThe emergence of self‐supervised deep language models has revolutionized natural language processing tasks and has recently extended its applications to biological sequence analysis. Traditional language models, primarily based on Transformer architectures, demonstrate substantial effectiveness in various applications. However, these models are inherently constrained by the attention mechanism's quadratic computational complexity, , which limits their efficiency and leads to high computational costs. To address these limitations, we introduce ProtHyena, a novel approach that leverages the Hyena operator in protein language modeling. This innovative methodology alternates between subquadratic long convolutions and element‐wise gating operations, which circumvents the constraints imposed by attention mechanisms and reduces computational complexity to subquadratic levels. This enables faster and more memory‐efficient modeling of protein sequences. ProtHyena can achieve state‐of‐the‐art results and comparable performance in 8 downstream tasks, including protein engineering (protein fluorescence and stability prediction), protein property prediction (neuropeptide cleavage, signal peptide, solubility, disorder, gene function prediction), protein structure prediction, with only 1.6 M parameters. The architecture of ProtHyena represents a highly efficient solution for protein language modeling, offering a promising avenue for fast and efficient analysis of protein sequences.

One-stop multi-sensor fusion and multimodal precise quantified traditional Chinese medicine imaging health examination technology

Except for single-mode traditional Chinese medicine imaging techniques such as infrared thermal imaging, the one-stop multimodal whole-body imaging health examination technology and device is still blank. We focus on infrared thermal imaging as the main modality, integrated various modalities of medical imaging intelligent sensing agents such as terahertz imaging. The upper and lower computer and virtual instrument architecture are used, and the imaging data are collected by the lower computers that each is an intelligent sensing agent. The upper computer is used for image reconstruction with intelligent algorithms. Based on the core theory of traditional Chinese medicine, intelligent fusion imaging is achieved through various modalities to achieve the ‘observation, hearing, questioning, and palpation’ four diagnostic integration. We use fractional Fourier transform to filter imaging data, Laplacian pyramid for image fusion. We have proposed an implementation method and process for combining traditional Chinese medicine imaging large language model with knowledge graph, and based on deep learning, we have studied the image and report generation algorithm that combines traditional Chinese medicine pathology and four diagnostic methods with knowledge graph fusion, as well as the traditional Chinese medicine human physiological and pathological interpretation and evaluation system. We have achieved some results, and through further research and development, we can achieve commercial applications.

RWD31 Comparing Traditional and Large Language Models for Extracting Breast and Endometrial Related Clinical Features From Electronic Health Records

RWD31 Comparing Traditional and Large Language Models for Extracting Breast and Endometrial Related Clinical Features From Electronic Health Records

User Interaction Patterns and Breakdowns in Conversing with LLM-Powered Voice Assistants

Conventional Voice Assistants (VAs) rely on traditional language models to discern user intent and respond to their queries, leading to interactions that often lack a broader contextual understanding, an area in which Large Language Models (LLMs) excel. However, current LLMs are largely designed for text-based interactions, thus making it unclear how user interactions will evolve if their modality is changed to voice. In this work, we investigate whether LLMs can enrich VA interactions via an exploratory study with participants (N=20) using a ChatGPT-powered VA for three scenarios (medical self-diagnosis, creative planning, and discussion) with varied constraints, stakes, and objectivity. We observe that LLM-powered VA elicits richer interaction patterns that vary across tasks, showing its versatility. Notably, LLMs absorb the majority of VA intent recognition failures. We additionally discuss the potential of harnessing LLMs for more resilient and fluid user-VA interactions and provide design guidelines for tailoring LLMs for voice assistance.

UTILIZING RETRIEVAL-AUGMENTED GENERATION IN LARGE LANGUAGE MODELS TO ENHANCE INDONESIAN LANGUAGE NLP

The improvement of Large Language Models (LLM) such as ChatGPT through Retrieval-Augmented Generation (RAG) techniques has urgency in the development of natural language translation technology and dialogue systems. LLMs often experience obstacles in addressing special requests that require information outside the training data. This study aims to discuss the use of Retrieval-Augmented Generation (RAG) on large-scale language models to improve the performance of Natural Language Processing (NLP) in Indonesian, which has so far been poorly supported by high-quality data and to overcome the limitations of traditional language models in understanding the context of Indonesian better. The method used is a combination of retrieval capabilities (external information search) with generation (text generation), where the model utilizes broader and more structured basic data through the retrieval process to produce more accurate and relevant text. The data used includes the Indonesian corpus of the 30 Juz Quran translation into Indonesian. The results of the trial show that the RAG approach significantly improves the performance of the model in various NLP tasks, including token usage optimization, text classification, and context understanding, by increasing the accuracy and relevance of the results

Biologically Plausible Sparse Temporal Word Representations.

Word representations, usually derived from a large corpus and endowed with rich semantic information, have been widely applied to natural language tasks. Traditional deep language models, on the basis of dense word representations, requires large memory space and computing resource. The brain-inspired neuromorphic computing systems, with the advantages of better biological interpretability and less energy consumption, still have major difficulties in the representation of words in terms of neuronal activities, which has restricted their further application in more complicated downstream language tasks. Comprehensively exploring the diverse neuronal dynamics of both integration and resonance, we probe into three spiking neuron models to post-process the original dense word embeddings, and test the generated sparse temporal codes on several tasks concerning both word-level and sentence-level semantics. The experimental results show that our sparse binary word representations could perform on par with or even better than original word embeddings in capturing semantic information, while requiring less storage. Our methods provide a robust representation foundation of language in terms of neuronal activities, which could potentially be applied to future downstream natural language tasks under neuromorphic computing systems.

QSIM: A Quantum-inspired hierarchical semantic interaction model for text classification

Semantic interaction modeling is a fundamental technology in natural language understanding that guides models to extract deep semantic information from text. Currently, the attention mechanism is one of the most effective techniques in semantic interaction modeling, which learns word-level attention representation by measuring the relevance between different words. However, the attention mechanism is limited to word-level semantic interaction, it cannot meet the needs of fine-grained interactive information for some text classification tasks. In recent years, quantum-inspired language modeling methods have successfully constructed quantized representations of language systems in Hilbert spaces, which use density matrices to achieve fine-grained semantic interaction modeling.This paper presents a Quantum-inspired hierarchical Semantic Interaction Model (QSIM), which follows the sememe-word-sentence language construction principle and utilizes quantum entanglement theory to capture hierarchical semantic interaction information in Hilbert space. Our work builds on the idea of the attention mechanism and extends it. Specifically, we explore the original semantic space from a quantum theory perspective and derive the core semantic space using the Schmidt decomposition technique, where: (1) Sememe is represented as the unit vector in the two-dimensional minimum semantic space; (2) Word is represented as reduced density matrices in the core semantic space, where Schmidt coefficients quantify sememe-level semantic interaction. Compared to density matrices, reduced density matrices capture fine-grained semantic interaction information with lower computational cost; (3) Sentence is represented as quantum superposition states of words, and the degree of word-level semantic interaction is measured using entanglement entropy.To evaluate the model’s performance, we conducted experiments on 15 text classification datasets. The experimental results demonstrate that our model is superior to classical neural network models and traditional quantum-inspired language models. Furthermore, the experiment also confirms two distinct advantages of QISM: (1) flexibility, as it can be integrated into various mainstream neural network text classification architectures; and (2) practicability, as it alleviates the problem of parameter growth inherent in density matrix calculation in quantum language model.

Language Model Method for Collocation Rules of Parts of Speech in Machine Translation System

With the development of the times, modern society has now entered the Internet of Things (IoT) information age and Machine Translation (MT) plays an important role in increasingly frequent cross-language communication. In recent years, China's artificial intelligence industry has been in a stage of rapid construction, and the scale of its core industries has grown explosively, and a large number of artificial intelligence companies, including issuers, have emerged. Part of speech has always been a major problem in MT. One of the reasons is that there are a large number of multi-category words in Chinese and a large number of polysemy words in English, so part of speech collocation problems account for a large proportion of MT errors, which to some extent affects the credibility and accuracy of the translation. To reduce the error problem in MT of part of speech collocation, this paper used Machine Learning (ML) methods to study the Language Model (LM) of part of speech collocation based on recurrent neural network (NN) and compared it with the traditional statistical LM. In terms of the accuracy rate of the two LMS in the automatic evaluation index of machine translation, the experimental results show that the recursive NN LM established by the ML method had an accuracy rate of 80.42% and 83.57%, respectively, for the part-of-speech matching rules of the IoT machine translation system in the dialogue between Chinese and English and the translation of articles. The accuracy of traditional statistical LM evaluation was 71.29% and 69.52%, respectively. Compared to traditional statistical LM, the accuracy of translation was higher. This showed that the recurrent NN LM reduced the number of errors in the collocation of parts of speech in MT and improved the accuracy and credibility of MT.

Annotation Vocabulary (Might Be) All You Need.

Protein Language Models (pLMs) have revolutionized the computational modeling of protein systems, building numerical embeddings that are centered around structural features. To enhance the breadth of biochemically relevant properties available in protein embeddings, we engineered the Annotation Vocabulary, a transformer readable language of protein properties defined by structured ontologies. We trained Annotation Transformers (AT) from the ground up to recover masked protein property inputs without reference to amino acid sequences, building a new numerical feature space on protein descriptions alone. We leverage AT representations in various model architectures, for both protein representation and generation. To showcase the merit of Annotation Vocabulary integration, we performed 515 diverse downstream experiments. Using a novel loss function and only $3 in commercial compute, our premier representation model CAMP produces state-of-the-art embeddings for five out of 15 common datasets with competitive performance on the rest; highlighting the computational efficiency of latent space curation with Annotation Vocabulary. To standardize the comparison of de novo generated protein sequences, we suggest a new sequence alignment-based score that is more flexible and biologically relevant than traditional language modeling metrics. Our generative model, GSM, produces high alignment scores from annotation-only prompts with a BERT-like generation scheme. Of particular note, many GSM hallucinations return statistically significant BLAST hits, where enrichment analysis shows properties matching the annotation prompt - even when the ground truth has low sequence identity to the entire training set. Overall, the Annotation Vocabulary toolbox presents a promising pathway to replace traditional tokens with members of ontologies and knowledge graphs, enhancing transformer models in specific domains. The concise, accurate, and efficient descriptions of proteins by the Annotation Vocabulary offers a novel way to build numerical representations of proteins for protein annotation and design.

Comparison of Classification Algorithm and Language Model in Accounting Financial Transaction Record: A Natural Language Processing Approach

The problem of financial recording not following the principles of accounting science has the potential to cause unnecessary problems. However, micro, small, and medium enterprises with their distinctive characteristics, though not all, still face many obstacles in writing financial reports. Even though there is already much financial software available, our study aims to investigate opportunities for implementing automation of accounting financial transaction records using the NLP approach, to interpret financial transactions based on text written on the transaction form into accounting journals (debits and credits). Experiments were carried out by comparing the performance of three classification algorithms, namely SVM, K-Nearest Neighbor, and Random Forest, with traditional (TF-IDF and BOW) and contextual (Word2Vec) Language Models. There are 200 financial transaction datasets consisting of ten classes. The data is divided into two parts, namely, the balance dataset and the imbalance dataset. The pair SVM and Word2Vec in the balanced dataset gave the highest accuracy (92.5%), precision (92.5%), recall/sensitivity (93.33%), and F1 score (92%). However, compared with the results of related semantic research (the average performance reaches 95%), the results obtained in this study are still lower. One point that may have a significant effect is the amount of data in the corpus, which is still lacking. Researchers suggest increasing the number of datasets and using a combination of other language models such as Glove, Bert etc. This study can also be used as a model for more complex financial transaction cases in future research.

A Multi-solution Study on GDPR AI-enabled Completeness Checking of DPAs

Specifying legal requirements for software systems to ensure their compliance with the applicable regulations is a major concern of requirements engineering. Personal data which is collected by an organization is often shared with other organizations to perform certain processing activities. In such cases, the General Data Protection Regulation (GDPR) requires issuing a data processing agreement (DPA) which regulates the processing and further ensures that personal data remains protected. Violating GDPR can lead to huge fines reaching to billions of Euros. Software systems involving personal data processing must adhere to the legal obligations stipulated both at a general level in GDPR as well as the obligations outlined in DPAs highlighting specific business. In other words, a DPA is yet another source from which requirements engineers can elicit legal requirements. However, the DPA must be complete according to GDPR to ensure that the elicited requirements cover the complete set of obligations. Therefore, checking the completeness of DPAs is a prerequisite step towards developing a compliant system. Analyzing DPAs with respect to GDPR entirely manually is time consuming and requires adequate legal expertise. In this paper, we propose an automation strategy that addresses the completeness checking of DPAs against GDPR provisions as a text classification problem. Specifically, we pursue ten alternative solutions which are enabled by different technologies, namely traditional machine learning, deep learning, language modeling, and few-shot learning. The goal of our work is to empirically examine how these different technologies fare in the legal domain. We computed F2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$_2$$\\end{document} score on a set of 30 real DPAs. Our evaluation shows that best-performing solutions yield F2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$_2$$\\end{document} score of 86.7% and 89.7% are based on pre-trained BERT and RoBERTa language models. Our analysis further shows that other alternative solutions based on deep learning (e.g., BiLSTM) and few-shot learning (e.g., SetFit) can achieve comparable accuracy, yet are more efficient to develop.

Predicting which patients with cancer will see a psychiatrist or counsellor from their initial oncology consultation document using natural language processing.

Patients with cancer often have unmet psychosocial needs. Early detection of who requires referral to a counsellor or psychiatrist may improve their care. This work used natural language processing to predict which patients will see a counsellor or psychiatrist from a patient's initial oncology consultation document. We believe this is the first use of artificial intelligence to predict psychiatric outcomes from non-psychiatric medical documents. This retrospective prognostic study used data from 47,625 patients at BC Cancer. We analyzed initial oncology consultation documents using traditional and neural language models to predict whether patients would see a counsellor or psychiatrist in the 12 months following their initial oncology consultation. Here, we show our best models achieved a balanced accuracy (receiver-operating-characteristic area-under-curve) of 73.1% (0.824) for predicting seeing a psychiatrist, and 71.0% (0.784) for seeing a counsellor. Different words and phrases are important for predicting each outcome. These results suggest natural language processing can be used to predict psychosocial needs of patients with cancer from their initial oncology consultation document. Future research could extend this work to predict the psychosocial needs of medical patients in other settings.

Visualization for a new era: Impact and application of large language models and AIGC to traditional business models

<p>This paper focuses on the application and business value of large-scale language models, such as GPT and Ernie’s model. These models combined with AIGC tools like stable diffusion generate images with fixed styles, character traits, and continuous plots using randomized story scripts. As a result, it enhances the operational efficiency between or within industries widely, and it fully demonstrate their business value. On the technical side, this paper describes in detail of building a pipeline to generate cue words required for stable diffusion, in which using large-scale language models and story scripts. Subsequently, the limitations of text-to-image are summarized by comparing the traditional method and language model, i.e. comparing characteristics from traditional book production and images generated using language model’s cue words. This leads to a supervised multiround iterative LoRA modeling scheme that utilizes CLIP to achieve character IP fixation. To evaluate the impact of the application direction, we combine application scenarios and researches on application aspects regarding current AIGC industry structure, we found that the AIGC tool has several major aspects, mainly includes the aspects of basic big model, industry and scenario models, business and domain small models, AI infrastructure and AIGC supporting services. big model and AIGC techniques generate images with no specific rules and have less limitation. We call this ‘visualization’ in the new AI era. In this paper, we explore the possible impacts and economic values when changing from traditional domain to the new AI ear.</p>

Chinese Cyberbullying Detection Using XLNet and Deep Bi-LSTM Hybrid Model

The popularization of the internet and the widespread use of smartphones have led to a rapid growth in the number of social media users. While information technology has brought convenience to people, it has also given rise to cyberbullying, which has a serious negative impact. The identity of online users is hidden, and due to the lack of supervision and the imperfections of relevant laws and policies, cyberbullying occurs from time to time, bringing serious mental harm and psychological trauma to the victims. The pre-trained language model BERT (Bidirectional Encoder Representations from Transformers) has achieved good results in the field of natural language processing, which can be used for cyberbullying detection. In this research, we construct a variety of traditional machine learning, deep learning and Chinese pre-trained language models as a baseline, and propose a hybrid model based on a variant of BERT: XLNet, and deep Bi-LSTM for Chinese cyberbullying detection. In addition, real cyber bullying remarks are collected to expand the Chinese offensive language dataset COLDATASET. The performance of the proposed model outperforms all baseline models on this dataset, improving 4.29% compared to SVM—the best performing method in traditional machine learning, 1.49% compared to GRU—the best performing method in deep learning, and 1.13% compared to BERT.

Enhancing Aspect Category Detection Through Hybridised Contextualised Neural Language Models: A Case Study In Multi-Label Text Classification

Abstract Recently, the field of Natural Language Processing (NLP) has made significant progress with the evolution of Contextualised Neural Language Models (CNLMs) and the emergence of large LMs. Traditional and static language models exhibit limitations in tasks demanding contextual comprehension due to their reliance on fixed representations. CNLMs such as BERT and Semantic Folding aim to produce feature-rich representations by considering a broader linguistic context. In this paper, Deep Learning-based Aspect Category Detection approaches are introduced to perform text classification. The study extensively assesses classification model performance, emphasising enhanced representativeness and optimised feature extraction resolution using CNLMs and their hybridised variants. The effectiveness of the proposed approaches is evaluated on benchmark datasets of 4500 reviews from the laptop and restaurant domains. The results show that the proposed approaches using hybridised CNLMs outperform state-of-the-art methods with an f-score of 0.85 for the laptop and f-scores higher than 0.90 for the restaurant dataset. This study represents a pioneering work as one of the initial research efforts aiming to jointly evaluate the representation performance of CNLMs with different architectures to determine their classification capabilities. The findings indicate that the proposed approaches can enable the development of more effective classification models in various NLP tasks.

CANBLWO: A Novel Hybrid Approach for Semantic Text Generation

Semantic text generation is critical in Natural Language Processing (NLP) as it faces challenges such as maintenance of coherence among texts, contextual relevance, and quality output. Traditional language models often produce grammatically inconsistent text. To address these issues, we introduce Convolutional Attention Bi-LSTM with Whale Optimization (CANBLWO), a novel hybrid model that integrates a Convolutional Attention Network (CAN), Bidirectional Long Short-Term Memory (Bi-LSTM), and Whale Optimization Algorithm (WOA). CANBLWO aims to generate semantically rich and coherent text and outperforms the traditional models like Long Short-Term Memory (LSTM), Recurrent Neural Networks (RNN), Bi-LSTM, and Bi-LSTM with attention, Bidirectional Encoder Representations from Transformers (BERT), and Generative Pre-trained Transformer 2 (GPT-2). Our model achieved 0.79, 0.78, 0.76, and 0.82 scores in Metric for Evaluation of Translation with Explicit Ordering (METEOR), Bi-Lingual Evaluation Understudy (BLEU), Consensus-based Image Description Evaluation (Ciders), and Recall-Oriented Understudy for Gisting Evaluation (ROUGE) metrics, respectively. The proposed model also demonstrates 97% and 96% accuracy on Wiki-Bio and Code/Natural Language Challenge (CoNaLa) datasets, highlighting its effectiveness against Large Language Models (LLMs). This study underscores the potential capability of hybrid approaches in enhancing semantic text generation

Integrating Large Language Model for Natural Language-Based Instruction toward Robust Human-Robot Collaboration

Human-Robot Collaboration (HRC) aims to create environments where robots can understand workspace dynamics and actively assist humans in operations, with the human intention recognition being fundamental to efficient and safe task fulfillment. Language-based control and communication is a natural and convenient way to convey human intentions. However, traditional language models require instructions to be articulated following a rigid, predefined syntax, which can be unnatural, inefficient, and prone to errors. This paper investigates the reasoning abilities that emerged from the recent advancement of Large Language Models (LLMs) to overcome these limitations, allowing for human instructions to be used to enhance human-robot communication. For this purpose, a generic GPT 3.5 model has been fine-tuned to interpret and translate varied human instructions into essential attributes, such as task relevancy and tools and/or parts required for the task. These attributes are then fused with perceived on-going robot action to generate a sequence of relevant actions. The developed technique is evaluated in a case study where robots initially misinterpreted human actions and picked up wrong tools and parts for assembly. It is shown that the fine-tuned LLM can effectively identify corrective actions across a diverse range of instructional human inputs, thereby enhancing the robustness of human-robot collaborative assembly for smart manufacturing.

Mapping sentence comprehension and syntactic complexity: evidence from 131 stroke survivors.

Understanding and interpreting how words are organized in a sentence to convey distinct meanings is a cornerstone of human communication. The neural underpinnings of this ability, known as syntactic comprehension, are far from agreed upon in current neurocognitive models of language comprehension. Traditionally, left frontal regions (e.g. left posterior inferior frontal gyrus) were considered critical, while more recently, left temporal regions (most prominently, left posterior middle temporal gyrus) have been identified as more indispensable to syntactic comprehension. Syntactic processing has been investigated by using different types of non-canonical sentences i.e. those that do not follow prototypical word order and are considered more syntactically complex. However, non-canonical sentences can be complex for different linguistic reasons, and thus, their comprehension might rely on different neural underpinnings. In this cross-sectional study, we explored the neural correlates of syntactic comprehension by investigating the roles of left hemisphere brain regions and white matter pathways in processing sentences with different levels of syntactic complexity. Participants were assessed at a single point in time using structural MRI and behavioural tests. Employing lesion-symptom mapping and indirect structural disconnection mapping in a cohort of 131 left hemisphere stroke survivors, our analysis revealed the following left temporal regions and underlying white matter pathways as crucial for general sentence comprehension: the left mid-posterior superior temporal gyrus, middle temporal gyrus and superior temporal sulcus and the inferior longitudinal fasciculus, the inferior fronto-occipital fasciculus, the middle longitudinal fasciculus, the uncinate fasciculus and the tracts crossing the most posterior part of the corpus callosum. We further found significant involvement of different white matter tracts connecting the left temporal and frontal lobes for different sentence types. Spared connections between the left temporal and frontal regions were critical for the comprehension of non-canonical sentences requiring long-distance retrieval (spared superior longitudinal fasciculus for both subject and object extraction and spared arcuate fasciculus for object extraction) but not for comprehension of non-canonical passive sentences and canonical declarative sentences. Our results challenge traditional language models that emphasize the primary role of the left frontal regions, such as Broca's area, in basic sentence structure comprehension. Our findings suggest a gradient of syntactic complexity, rather than a clear-cut dichotomy between canonical and non-canonical sentence structures. Our findings contribute to a more nuanced understanding of the neural architecture of language comprehension and highlight potential directions for future research.

Word Play in Modern Russian Network Discourse

The phenomenon of the word play is studied in this work on the basis of the network discourse reflected in the materials of the Russian competition “Word of the Year” for 2007-2021. The participants of this contest were subject to sociolinguistic analysis – words, expressions, and phrases that are products of a word play. All of them, as it turned out, were included in the nomination “Neologism of the Year”. The empirical analysis was subordinated to the goal of determining their functionality and identifying the underlying word-formation models and techniques of lexical implementation of the latter. The results of the study indicate the active appeal of users of social networks to the word play in two situations. Firstly, when a communicator wants to express one’s disagreement, a critical attitude towards real events. Then s/he usually resorts to ridicule as a form of word play, functionally aimed at lowering evaluative meanings (a case of “corrective humor”). Secondly, in a situation of counteracting psychological tension and stress caused by a traumatic event, when using a joke, the communicator seeks to reduce emotional tension—his/her own and / or the audience (a case of “benevolent humor”). In both situations, as the analysis showed, the same set of word-formation models of the Russian language and word play techniques are used. To create new lexical units, paronymic attraction and contamination are most widely used. These models are adjoined by prefixation, suffixation, their combination, as well as other traditional Russian language models for generating lexical units. Among the techniques of the word play that provide a laughing reaction, deceived expectation, logical inconsistency and playing with set expressions stand out. In general, the results of the study indicate that the word play remains a popular means of achieving the comic effect desired by the communicator, not only by journalists, as noted by analysts of modern Russian public discourse, but also by ordinary users of social networks in their everyday speech communication.

Фактор клишированности в описании словосодержащего семиозиса: норма и границы языка

The article presents a number of observations on the methods of not quite convincing definition of the " language norm" and "language boundaries" within the framework of the traditional language model, the main methodological constant of which is a priori confidence that the content ("meaning", "meaning", "semantics", " content plan, etc.) exists in direct connection with the verbal substrate. As a result, contradictory statements arise: “The norm exists objectively”, at the same time “The norm exists subjectively”; "Norm is single", at the same time "Norm is multiple"; “The norm is manifested in synchrony”, at the same time “The norm is manifested in diachrony”; “Language coincides with the norm”, at the same time “Language does not coincide with the norm”; “Language belongs to the researcher”, at the same time “Language belongs to the user”; “Language has unity”, at the same time “Language consists of varieties of a language”. To solve the same problems, the concept of cliché and semiotic action is proposed as tools, which more correctly reflect the essence of natural speaking-writing and at the output give a more harmonious picture (model) of what is happening. According to the communicative model, in natural communication, the source of content produced and received is personal semiotic influence (polymodal, multifactorial, multichannel, not necessarily word-containing). In order to achieve changes in external cognitive states (which have not yet occurred at the time of the action, but are only planned), the semiotic actor makes attempts to influence, manifesting actional modes of his consciousness under given conditions in complex ways. In view of this, in a natural act, the novelty sought by the actor is generated and understood, which constitutes the meaning formation of a given semiotic act. The concept of cliché in relation to words and other "signs", assuming the procedural (actional) principle of formation of any semiotic content, allows us to separate the clichwd (mechanical, meaningless, behavioral) "language", including verbal, from the meaning-forming semiotic influence, to emphasize the deep conventionality of construction "systemic" and "universal" "language".