Human Language Understanding Research Articles

A transformer-based spelling error correction framework for Bangla and resource scarce Indic languages

Spelling error correction is the task of identifying and rectifying misspelled words in texts. It is a potential and active research topic in Natural Language Processing because of numerous applications in human language understanding. The phonetically or visually similar yet semantically distinct characters make it an arduous task in any language. Earlier efforts on spelling error correction in Bangla and resource-scarce Indic languages focused on rule-based, statistical, and machine learning-based methods which we found rather inefficient. In particular, machine learning-based approaches, which exhibit superior performance to rule-based and statistical methods, are ineffective as they correct each character regardless of its appropriateness. In this paper, we propose a novel detector-purificator-corrector framework, DPCSpell based on denoising transformers by addressing previous issues. In addition to that, we present a method for large-scale corpus creation from scratch which in turn resolves the resource limitation problem of any left-to-right scripted language. The empirical outcomes demonstrate the effectiveness of our approach, which outperforms previous state-of-the-art methods by attaining an exact match (EM) score of 94.78%, a precision score of 0.9487, a recall score of 0.9478, an f1 score of 0.948, an f0.5 score of 0.9483, and a modified accuracy (MA) score of 95.16% for Bangla spelling error correction. The models and corpus are publicly available at https://tinyurl.com/DPCSpell.

COMPARISON OF DEEP LEARNING TECHNIQUES FOR TEXTUAL SENTIMENT ANALYSIS

Examining the opinions of the people might provide us with valuable knowledge. Sentiment analysis is a method for analyzing textual data that helps find subjective information, such as opinions and feelings that individuals or groups have expressed. It improves our understanding of human language using deep learning and natural language techniques. Several deep learning models, including RNNs, LSTMs, GRUs, and their bidirectional variants, are compared in this work. Three publicly available datasets - the imdb_reviews, Twitter Sentiment Dataset, and Emotions dataset were used in the investigation. Accuracy performance is evaluated for six deep learning models. According to experimental studies, bidirectional structures outperform their unidirectional counterparts in most cases. Across several datasets, the bidirectional models continuously produced the best accuracy.

THE TERM "CONCEPT" AS A BASIC CONCEPT OF COGNITIVE SEMANTICS

Today, there is much debate over the term cognitive linguistics, and there is no agreement on what exactly the term means. According to English linguists, cognitive linguistics is a branch of linguisticsIn cognitive semantics, the term "concept" refers to a mental representation of a category that encompasses a set of related objects, events, or ideas. Concepts are fundamental to human cognition and language understanding. Cognitive semantics emphasizes that the meaning of words and expressions is grounded in conceptual structures, which are shaped by our sensory-motor experiences and cultural context.

Knowledge-based Data Processing for Multilingual Natural Language Analysis

Natural Language Processing (NLP) aids the empowerment of intelligent machines by enhancing human language understanding for linguistic-based human-computer communication. Recent developments in processing power, as well as the availability of large volumes of linguistic data, have enhanced the demand for data-driven methods for automatic semantic analysis. This paper proposes multilingual data processing using feature extraction with classification using deep learning architectures. Here, the input text data has been collected based on various languages and processed to remove missing values and null values. The processed data has been extracted using Histogram Equalization based Global Local Entropy (HEGLE) and classified using Kernel-based Radial basis Function (Ker_Rad_BF). These architectures could be utilized to process natural language. We present solutions to the multilingual sentiment analysis issue in this research article by implementing algorithms, and we compare precision factors to discover the optimum option for multilingual sentiment analysis. For the HASOC dataset, the proposed HEGLE_ Ker_Rad_BF achieved an accuracy of 98%, a precision of 97%, a recall of 90.5%, an f-1 score of 85%, RMSE of 55.6%, and a loss curve analysis attained 44%. For the TRAC dataset, the accuracy of 98%, the precision attained is 97%, the Recall is 91%, the F-1 score is 87%, and the RMSE of the proposed neural network is 55%.

Exploratory analysis on the natural language processing models for task specific purposes

Natural language processing (NLP) is a technology that has become widespread in the area of human language understanding and analysis. A range of text processing tasks such as summarisation, semantic analysis, classification, question-answering, and natural language inference are commonly performed using it. The dilemma of picking a model to help us in our task is still there. It’s becoming an impediment. This is where we are trying to determine which modern NLP models are better suited for the tasks set out above in order to compare them with datasets like SQuAD and GLUE. For comparison, BERT, RoBERTa, distilBERT, BART, ALBERT, and text-to-text transfer transformer (T5) models have been used in this study. The aim is to understand the underlying architecture, its effects on the use case and also to understand where it falls short. Thus, we were able to observe that RoBERTa was more effective against the models ALBERT, distilBERT, and BERT in terms of tasks related to semantic analysis, natural language inference, and question-answering. The reason is due to the dynamic masking present in RoBERTa. For summarisation, even though BART and T5 models have very similar architecture the BART model has performed slightly better than the T5 model.

Simulation modeling of the system of managing the psychophysiological state of a person based on non-verbal extralinguistic characteristics

Today, when artificial intelligence systems are being created, the time of constant dia-logue between humans and computer, there is a great demand for intelligent control systems and human-machine systems. These systems are very complex and require analysis and re-search. The publication is devoted to the simulation computer modeling of control of the psy-chological and physical state of a person. The basis of the human-computer dialogue system is the speech-to-text conversion sys-tem. The use of this system is the basis for the creation of computer language control systems. Unlike systems that work on the principle of identifying a single user response to a request and a proposal or a question from a password database, it is necessary to expand the lan-guage interface of the computer. It is necessary for the computer to accept commands from the operator and execute them only if the voice and its timbre match those registered in the database. Such a system will allow you to differentiate access to the computer and ensure se-curity for the user, preserve his privacy or save his personal data. After analyzing the speech activity of the operator, it became clear that it was necessary to develop a system of command control and «speech-to-text» conversion in the fused speech stream. This task is solved by comparing the words of the commands and is part of the problem of automatic recognition and understanding of the operator's human language. On the basis of such systems, a computer language control system can be created. The analysis has shown that unlike text-dependent identification systems, systems with a dialog method implement not only a one-time operator response to a query or question from the password database, but also the extension of its full-fledged language interface. The computer receives commands from the operator and executes them only if the voice matches the one registered in the database. This analysis is effective in the context of real-life speech activity of the operator. The literature review showed that for the development of sys-tems of command control and "speech-to-text" transformation in a stream of fused speech, it is necessary to use "mechanisms" of automatic recognition and understanding of the opera-tor's language.

An Overview of the Application of Convolutional Neural Networks inSentiment Analysis

The field of natural language processing, or NLP, uses its understanding of human language to find practical solutions to issues. It mainly includes two parts: the core task and the application. The core task represents the common problem that needs to be solved in various natural language application directions. It includes language models, morphology, grammar analysis, semantic analysis, etc. At the same time, the application section focuses on specific natural language processing tasks such as machine translation, information retrieval, question-answering systems, dialogue systems, etc. Natural language processing has made a significant contribution to the development of human society and the economy and provides strong support for all aspects of research work. Opinion mining, or sentiment analysis, is a subfield of natural language processing that develops systems for identifying and extracting ideas from text. Sentiment analysis is a hot topic since it has many practical applications. Many opinion-expressing texts are available on review sites, forums, blogs, and social media as the amount of publicly available information on the Internet grows. This unstructured information can then be automatically transformed into structured data about products, services, brands, politics, or other topics on which people can express their opinions using sentiment analysis systems. This information can be used for marketing analytics, public relations, product reviews, network sponsor ratings, product feedback, and customer service. With the rapid growth of labeled sample data sets and the notable enhancement in graphics processor (GPU) performance, convolutional neural network research has advanced rapidly and achieved remarkable leads to various computer vision tasks. By reviewing the application of CNN, we see that convolutional operations are naturally suitable for some text processing and, thus, naturally suitable for the background of sentiment analysis.

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.

Autonomous GIS: the next-generation AI-powered GIS

ABSTRACTLarge Language Models (LLMs), such as ChatGPT, demonstrate a strong understanding of human natural language and have been explored and applied in various fields, including reasoning, creative writing, code generation, translation, and information retrieval. By adopting LLM as the reasoning core, we introduce Autonomous GIS as an AI-powered geographic information system (GIS) that leverages the LLM's general abilities in natural language understanding, reasoning, and coding for addressing spatial problems with automatic spatial data collection, analysis, and visualization. We envision that autonomous GIS will need to achieve five autonomous goals: self-generating, self-organizing, self-verifying, self-executing, and self-growing. We developed a prototype system called LLM-Geo using the GPT-4 API, demonstrating what an autonomous GIS looks like and how it delivers expected results without human intervention using three case studies. For all case studies, LLM-Geo returned accurate results, including aggregated numbers, graphs, and maps.. Although still in its infancy and lacking several important modules such as logging and code testing, LLM-Geo demonstrates a potential path toward the next-generation AI-powered GIS. We advocate for the GIScience community to devote more efforts to the research and development of autonomous GIS, making spatial analysis easier, faster, and more accessible to a broader audience.

Research on Text Summarization Techniques Based on Deep Learning-WS-Attention

The bonafide semantic understanding of human language text, exhibited by its effective summarization, may well be the holy grail of natural language processing (NLP). That statement isn't as hyperbolic as it sounds: as true human language understanding definitely is the holy grail of NLP, and genuine effective summarization of said human language would necessarily entail true understanding, transitivity would back me up on this. However, the show must go on, and there currently exist an array of actual techniques for summarizing text, some of which stretch back decades. These techniques take different approaches to reach the same goal, and can be classified into a fairly narrow set of categories for pursuing their shared goal.

Symbols and grounding in large language models.

Large language models (LLMs) are one of the most impressive achievements of artificial intelligence in recent years. However, their relevance to the studyof language more broadly remains unclear. This article considers the potential of LLMs to serve as models of language understanding in humans. While debate on this question typically centres around models' performance on challenging language understanding tasks, this article argues that the answer depends on models' underlying competence, and thus that the focus of the debate should be on empirical work which seeks to characterize the representations and processing algorithms that underlie model behaviour. From this perspective, the article offers counterarguments to two commonly cited reasons why LLMs cannot serve as plausible models of language in humans: their lack of symbolic structure and their lack of grounding. For each, a case is made that recent empirical trends undermine the common assumptions about LLMs, and thus that it is premature to draw conclusions about LLMs' ability (or lack thereof) to offer insights on human language representation and understanding. This article is part of a discussion meeting issue 'Cognitive artificial intelligence'.

MiMuSA—mimicking human language understanding for fine-grained multi-class sentiment analysis

MiMuSA—mimicking human language understanding for fine-grained multi-class sentiment analysis

When Arne met J. L.: attitudes to scientific method in empirical semantics, ordinary language philosophy and linguistics

In the autumn of 1959, Arne Naess and J. L. Austin, both pioneers of empirical study in the philosophy of language, discussed their points of agreement and disagreement at a meeting in Oslo. This article considers the fragmentary record that has survived of that meeting, and investigates what light it can shed on the question of why the two philosophers apparently found so little common ground, given their shared commitment to the importance of data in the study of language. Naess and Austin held different views about two significant aspects of the relationship between scientific method and philosophical investigation. The first aspect concerns the nature of experimental data; Naess used the statistical analysis of data collected from non-philosophical informants while Austin advocated deliberation leading to agreement over usage by a few skilled experts. The second aspect relates to their respective attitudes to the role of theory in philosophical inquiry, attitudes which drew on discussions of scientific method, and its relevance to philosophy, from the early decades of the twentieth century. This article traces the evidence for these views on scientific method in Naess’s and Austin’s respective published work, and in the record of their Oslo meeting. It concludes with a brief overview of opinions about scientific method manifest in the decades since that meeting in various branches of linguistics. These opinions speak to the enduring importance of attitudes to scientific method in relation to our study and understanding of human language.

DALL·E 2 fails to reliably capture common syntactic processes

Machine intelligence is increasingly being linked to claims about sentience, language processing, and an ability to comprehend and transform natural language into a range of stimuli. We analyze the ability of DALL·E 2 to translate natural language prompts into images, since it remains unclear whether it possesses the facility for accurately representing grammatical strategies. We target the performance of DALL·E 2 across 10 phenomena that are pervasive in human language: binding principles and coreference, passives, structural ambiguity, negation, compositionality and word order, quantification, double object constructions, sentence coordination, ellipsis, and comparatives. In contrast to young infants, who master these tasks, DALL·E 2 fails to accurately represent inferred meanings, performing at or near chance. While programs can be trained to recognize vast numbers of words and calculate probabilities of word sequences, these results challenge recent claims concerning artificial understanding of human language. The full set of tested materials and the outputs are made available as a benchmark for future testing.

Language cognition and language computation — human and machine language understanding

Language understanding is the key scientific issue in cognitive science and computer science. However, the two disciplines are quite different in selecting specific research questions. Research in cognitive science focuses on analyzing the working mechanism of the brain and describing its response to language, while only a few research studies investigate the brain's language system as a whole. In contrast, computer scientists focus on the efficiency of practical applications when choosing research questions and often ignore essential laws of language. Thus, the research question becomes: “Can we combine these two disciplines to develop new insights into building intelligent language models and studying cognitive mechanisms?" This paper first reviews the research question, history, and methods of language understanding in cognitive science and computer science, focusing on the current research status and challenges. Then, it compares the commonalities and differences in language understanding between the two fields. Finally, it analyzes the existing work that combines the insights from language cognition and computation and prospects the future development trend.

Modelling argumentation in short text: A case of social media debate

The technological leaps of artificial intelligence (AI) and the rise of machine learning have triggered significant progress in a plethora of natural language processing (NLP) and natural language understanding tasks. One of these tasks is argumentation mining which has received significant interest in recent years and is regarded as a key domain for future decision-making systems, behaviour modelling, and natural language understanding problems. Until recently, natural language modelling tasks, such as computational argumentation schemes, were often tested in controlled environments, such as persuasive essays, reducing unexpected behaviours that could occur in real-life settings, like a public debate on social media. Additionally, the growing demand for enhancing the trust and the explainability of the AI services has dictated the design and adoption of modelling schemes to increase the confidence in the outcomes of the AI solutions. This paper attempts to explore modelling argumentation in short text and proposes a novel framework for argumentation detection under the name Abstract Framework for Argumentation Detection (AFAD). Moreover, different proof-of-concept implementations are provided to examine the applicability of the proposed framework to very short text developing a rule-based mechanism and compare the results with data-driven solutions. Eventually, a combination of the deployed methods is applied increasing the correct predictions in the minority class on an imbalanced dataset. The findings suggest that the modelling process provides solid grounds for technical research while the hybrid solutions have the potential to be applied to a wide range of NLP-related tasks offering a deeper understanding of human language and reasoning.

Quantum Probability-inspired Graph Attention Network for Modeling Complex Text Interaction

Inspired by quantum-like phenomena in human language understanding, recent studies propose quantum probability-inspired neural networks to model natural language by treating words as superposition states and a sentence as a mixed state. However, many complex natural language processing tasks (e.g., emotion–cause pair extraction or joint dialog act recognition and sentiment classification) require modeling the complex and graphical interaction of multiple text pieces (e.g., multiple clauses in a document or multiple utterances in a dialog). The existing quantum probability-inspired neural networks only encode sequential interaction of a sequence of words, but cannot model the complex interaction of text pieces. To generalize the quantum framework from modeling word sequence to modeling complex and graphical text interaction, we propose a Quantum Probability-inspired Graph Attention NeTwork (QPGAT) by combining quantum probability and graph attention mechanism in a unified framework. Specifically, a text interaction graph is firstly constructed to describe the complex interaction of text pieces. Then QPGAT models each text node as a particle in a superposition state and each node’s neighborhood in the graph as a mixed system in a mixed state to learn interaction-aware text node representations. We apply QPGAT to the two important and complex NLP tasks, emotion–cause pair extraction and joint dialog act recognition and sentiment classification. Experiment results show that QPGAT is competitive compared with the state-of-the-art methods on the two complex NLP tasks, demonstrating the effectiveness of QPGAT. Moreover, QPGAT can also provide a reasonable post-hoc explanation about the model decision process for emotion–cause pair extraction.

Dissecting word embeddings and language models in natural language processing

Natural language processing (NLP) is an area in artificial intelligence that deals with understanding, interpretation and development of human language for computers to carry out tasks such as sentiment analysis, summarization of text in a document, developing conversational agents, machine translation and speech recognition. From conversational agents called catboats deployed on various websites that interact with consumers digitally to understand the needs of the consumers to reading summarized content delivered through apps in smartphones, NLP has had some major achievements in transforming the digital world that is increasingly gearing towards artificial intelligence. One area that has seen remarkable growth in recent times is language modelling, a statistical technique to compute the probability of tokens or words in a given sentence. In this paper, we attempt to present an overview of various representations with respect to language modelling, from neural word embeddings such as Word2Vec and GloVe to deep contextualized pre-trained embedding such as ULMFit, ELMo, OpenAI GPT and BERT.

Animal listening

The ‘Elegy on the Nightingale’ is a curious Latin poem of uncertain (but probably post-classical) date and authorship that is transmitted by several medieval manuscripts. It offers a catalogue of animal sounds rich in what linguists call iconicity, and literary scholars, onomatopoeia: to read these verses aloud is to imitate the sounds being described. The poem begins in address to the nightingale of its title, praised for her ability to make music by mimicking all she hears. By the end has the poem itself done the same? For all their playfulness, the verses strike at the heart of our own theoretical commonplaces, starting with the supposed arbitrariness of the sign, always unsettled by such examples, exceptional though they may be. So too did the writing down of non-human sounds preoccupy ancient linguists, who sought to segregate them from language proper. Nevertheless, it is difficult to deny that these sound-words conjure what they name, especially since, in many cases, it is only our ability to match their sounds to animals we can still hear that enables us to know what the poem is saying. What happens to our understanding of the poetic text as a transcription of human speech or song when we take it seriously as a recording of non-human sound? And even more dramatically, what happens to our understanding of human language when we strive (as this poem strives, albeit surreptitiously) to listen with non-human ears? With some help from the animal imaginings of Jakob von Uexküll, this article attempts some preliminary answers.

Self-Attention on Sentence Snippets Incongruity for Humor Assessment

Researches on humor identification can advocate a better understanding of human language. Many studies focused on the categorical classification problem of humor, which is less sensible to the intermediate level funny content. Previous work captured the incongruity between words but not sentence snippets. In this paper, a novel method is proposed to exploit snippet-level incongruity features from different aspects, combined with the sentence snippets representations to predict funniness scores. The experiment result shows that this model outperforms most of the competitive methods.