Language Research Articles

Roles of Natural Language Processing in New Product Development Process: Literature Review

Customer satisfaction is a key success factor for a business. To provide products that meet customer satisfaction, companies must be able to understand the customers’ needs and desires. Technological developments nowadays have helped companies to understand customer desires more easily so that companies can provide products that satisfy their customer. Natural Language Processing (NLP) is a technology that allows computers to process human language. NLP is also commonly referred as text-mining. NLP has been utilized in the New Product Development (NPD) process. We compiled studies related to NLP and NPD and conducted a literature review to map out how far NLP has been utilized in NPD processes. We found that in this era of Big Data, current NLP studies most often have the goal to process text data from online reviews on e-commerce and from social media. By using NLP, large amounts of data can produce valuable Voice of Customer (VOC) information for product development. We also found that NLP technology also has been utilized in other NPD processes that do not involve VOC, such as the design stage, document processing, and extraction of requirements in the NPD process.

Pre-Trained Language Models for Text Generation: A Survey

Text Generation aims to produce plausible and readable text in human language from input data. The resurgence of deep learning has greatly advanced this field, in particular, with the help of neural generation models based on pre-trained language models (PLMs). Text generation based on PLMs is viewed as a promising approach in both academia and industry. In this article, we provide a survey on the utilization of PLMs in text generation. We begin with introducing two key aspects of applying PLMs to text generation: (1) how to design an effective PLM to serve as the generation model; and (2) how to effectively optimize PLMs given the reference text and to ensure that the generated texts satisfy special text properties. Then, we show the major challenges that have arisen in these aspects, as well as possible solutions for them. We also include a summary of various useful resources and typical text generation applications based on PLMs. Finally, we highlight the future research directions which will further improve these PLMs for text generation. This comprehensive survey is intended to help researchers interested in text generation problems to learn the core concepts, the main techniques and the latest developments in this area based on PLMs.

Human Language Data Processing using NLTK

Natural Language Toolkit (NLTK) is a comprehensive Python library designed to facilitate the exploration, analysis, and processing of human language data. With its extensive collection of tools, NLTK provides researchers, developers, and educators with a powerful platform for tasks ranging from basic text processing to advanced natural language understanding and machine learning. The toolkit includes modules for tokenization, stemming, lemmatization, part-of-speech tagging, named entity recognition, syntactic parsing, semantic analysis, and more. Furthermore, NLTK offers access to numerous linguistic resources such as corpora, lexicons, and treebanks, making it an invaluable resource for both learning and research in the field of natural language processing (NLP). NLTK serves as an indispensable tool for unlocking the complexities of human language

ДОСЛІДЖЕННЯ ОСОБЛИВОСТЕЙ ЗАСТОСУВАННЯ ШТУЧНОГО ІНТЕЛЕКТУ В ІНЖЕНЕРІЇ ПРОГРАМНОГО ЗАБЕЗПЕЧЕННЯ

The study explores the transformative impact of artificial intelligence in the realm of software development, showcasing how AI-powered tools streamline workflows and enhance productivity. From automating documentation creation with tools like Rewind.ai and Mutable.ai to translating code into human language for easier comprehension through Figstack, AI is revolutionizing development practices. These innovations underscore AI's pivotal role in reshaping software development processes, improving code quality, and fostering efficient teamwork in an increasingly dynamic landscape.

Distributed Sensitivity to Syntax and Semantics throughout the Language Network.

Human language is expressive because it is compositional: The meaning of a sentence (semantics) can be inferred from its structure (syntax). It is commonly believed that language syntax and semantics are processed by distinct brain regions. Here, we revisit this claim using precision fMRI methods to capture separation or overlap of function in the brains of individual participants. Contrary to prior claims, we find distributed sensitivity to both syntax and semantics throughout a broad frontotemporal brain network. Our results join a growing body of evidence for an integrated network for language in the human brain within which internal specialization is primarily a matter of degree rather than kind, in contrast with influential proposals that advocate distinct specialization of different brain areas for different types of linguistic functions.

Delta-band Activity Underlies Referential Meaning Representation during Pronoun Resolution.

Human language offers a variety of ways to create meaning, one of which is referring to entities, objects, or events in the world. One such meaning maker is understanding to whom or to what a pronoun in a discourse refers to. To understand a pronoun, the brain must access matching entities or concepts that have been encoded in memory from previous linguistic context. Models of language processing propose that internally stored linguistic concepts, accessed via exogenous cues such as phonological input of a word, are represented as (a)synchronous activities across a population of neurons active at specific frequency bands. Converging evidence suggests that delta band activity (1-3 Hz) is involved in temporal and representational integration during sentence processing. Moreover, recent advances in the neurobiology of memory suggest that recollection engages neural dynamics similar to those which occurred during memory encoding. Integrating from these two research lines, we here tested the hypothesis that neural dynamic patterns, especially in delta frequency range, underlying referential meaning representation, would be reinstated during pronoun resolution. By leveraging neural decoding techniques (i.e., representational similarity analysis) on a magnetoencephalogram data set acquired during a naturalistic story-listening task, we provide evidence that delta-band activity underlies referential meaning representation. Our findings suggest that, during spoken language comprehension, endogenous linguistic representations such as referential concepts may be proactively retrieved and represented via activation of their underlying dynamic neural patterns.

Relations between supply chain performance and circular economy implementation: A fuzzy cognitive map‐based analysis for sustainable development

AbstractSupply chain sustainability is now an imperative, particularly considering the circular supply chain (CSC) paradigm, which offers opportunities for performance improvement. Thus, it is possible to infer that there is a causal link between circularity and supply chain performance. However, the analysis of this relationship occurs under subjective perspectives. To computationally process human language can overcome this issue. Hence, this paper aims to propose an approach for assessing the influence of circular economy (CE) implementation principles on supply chain performance using the fuzzy cognitive map (FCM), a well‐established soft computing technique. The study develops a computational model and brings an illustrative application. Methodologically, is model‐based, quantitative, axiomatic and descriptive. It contributes by providing means to support the formulation of strategies for aligning CE implementation efforts with supply chain performance improvement efforts. The FCM visually represents how supply chain performance attributes are influenced by CE principles, supporting informed decision‐making towards circularity.

DL-TBAM: Deep Learning Transformer based Architecture Model for Sentiment Analysis on Tamil-English Dataset

NLP, or natural language processing, is a subfield of AI that aims to equip computers with the ability to understand and analyze human language. Sentiment analysis is a widely used application of NLP, particularly for examining attitudes expressed in online conversations. Nevertheless, many social media comments are written in languages that are not native to the authors, making sentiment analysis more difficult, especially for languages with limited resources, such as Tamil. To tackle this issue, a code-mixed and sentiment-annotated corpus in Tamil and English was created. This article will explain how the corpus was established, including the process of data collection and the assignment of polarities. The article will also explore the agreement between annotators and the results of sentiment analysis performed on the corpus. This work signifies various performance metrics such as precision, recall, support, and F1-score for the transformer-based model such as BERT, RoBerta, and XLM-RoBerta. Among the various models, XLM-Robert shows slightly significant positive results on the code-mixed corpus when compared to the state of art models.

A machine-based corpus optimization method for extracting domain-oriented technical words: an example of COVID-19 corpus data

Although natural language processing (NLP) refers to a process involving the development of algorithms or computational models that empower machines to understand, interpret, and generate human language, machines are still unable to fully grasp the meanings behind words. Specifically, they cannot assist humans in categorizing words with general or technical purposes without predefined standards or baselines. Empirically, prior researches have relied on inefficient manual tasks to exclude these words when extracting technical words (i.e., terminology or terms used within a specific field or domain of expertise) for obtaining domain information from the target corpus. Therefore, to enhance the efficiency of extracting domain-oriented technical words in corpus analysis, this paper proposes a machine-based corpus optimization method that compiles an advanced general-purpose word list (AGWL) to serve as the exclusion baseline for the machine to extract domain-oriented technical words. To validate the proposed method, this paper utilizes 52 COVID-19 research articles as the target corpus and an empirical example. After compared to traditional methods, the proposed method offers significant contributions: (1) it can automatically eliminate the most common function words in corpus data; (2) through a machine-driven process, it removes general-purpose words with high frequency and dispersion rates –57% of word types belonging to general-purpose words, constituting 90% of the total words in the target corpus. This results in 43% of word types representing domain-oriented technical words that makes up 10% of the total words in the target corpus are able to be extracted. This allows future researchers to focus exclusively on the remaining 43% of word types in the optimized word list (OWL), enhancing the efficiency of corpus analysis for extracting domain knowledge. (3) The proposed method establishes a set of standard operation procedure (SOP) that can be duplicated and generally applied to optimize any corpus data.

Evolution of Natural Language Processing: A Review

Over the years, Natural Language Processing (NLP) has evolved dramatically, moving from early rule based systems to the current era dominated by advanced deep learning models. An overview of the significant turning points and patterns that have influenced the development of NLP is given in this study. In the early days of Natural Language Processing (NLP), rule based methods were the main focus. Linguists would manually create rules to analyze and comprehend human language. Although these systems were somewhat successful, they were unable to handle the complexity and unpredictability of spoken language. A major change was brought about by the introduction of probabilistic models and machine learning techniques with the emergence of statistical approaches. The development of methods like n gram models and hidden Markov models during this time allowed computers to handle linguistic patterns. Large scale linguistic resources like word embeddings and annotated corpora started to appear, which further accelerated the development of NLP. Machine learning algorithms have led to notable advancements in tasks such as machine translation, named entity recognition, and part of speech tagging. NLP has seen a revolution in recent years thanks to deep learning, which uses neural networks to learn intricate language representations. Sequential dependencies in language can now be better understood because of models like Long Short Term Memory Networks (LSTMs) and Recurrent Neural Networks (RNNs). The addition of attention mechanisms, as demonstrated by Transformer and other models, improves the model's ability to manage long range dependencies and perform better on a variety of NLP tasks. In the future, NLP will develop in ways that go beyond performance measurements, exploring interpretability, ethical issues, and the incorporation of multimodal data. As the area develops, it becomes increasingly important to eliminate biases, ensure ethical AI deployment, and improve user centric experiences. This introduction lays the groundwork for an in depth examination of the development of NLP, highlighting significant turning points, difficulties, and potential future directions in this vibrant and quickly developing subject.

Beyond the Myth of Chinese Ideograms

Published in The New Yorker in May 2016, Ted Chiang’s short piece “Bad Character” has raised fervent debates on the linguistic properties of the Chinese writing system, as well as on the peculiar, if not perplexing, nature of the language itself. The mixed responses among scholars, from both the East and the West, towards Ted Chiang’s position against Chinese characters reflect the underlying entanglement of disparate discourses, including the universal language, orientalization/self-orientalization, language reform, Asian-American struggles, Chinese exceptionalism, and most importantly, the entrenched myth of Chinese ideograms. By situating Ted Chiang’s short story “Story of Your Life” (1998) in the midst of the debate, this paper explores not only how Chiang broaches Chinese’s linguistic otherness through the science-fictional trope of alien communication, but also how the author dismantles the discursive baggage of Chinese ideograms by shifting toward technical description of linguistic details. Reading “Story” in joint with Liu Cixin’s seminal Three Body trilogy (2008–10) and a more recent work “Curse” (2015) by Chen Zijun, this paper further contends that a new trend can be discerned that seeks to depart from previous exploitations of Chinese’s otherness through orientalizing gestures and essentialist representations. Unlike their predecessors who either valorize or degrade the non-phonetic alien language allusive to allegedly ideographic Chinese, these authors refrain from setting up a hierarchy between human languages and their alien counterparts, channeling the utopian impulse of sf into treating language as a technical object that is perfectible through constant refinement of its linguistic configurations. The end product of these discursive efforts is a notion of linguistic utopianism, which not only harkens back to the generic affinity of sf to utopia as well as to the long-lived, ubiquitous quest for a perfect language, but also envisions a new ethics of alien communication through explicating the distinct technicality of each language for a non-hierarchical paradigm.

“The Poetry of a Dingo’s Bite”

Science fiction has an extensive history of attempting to breach the communication boundary between humans and nonhuman animals by giving nonhuman animals some semblance of human language, with many uplift stories having them speak near-perfect English, their minds being filtered through a human linguistic framework, partly or wholly erasing their voice. Building on the examination of nonhuman animal gestural communication in Brian Massumi’s What Animals Teach Us about Politics (2014), this paper analyses how two works, Ursula K. Le Guin’s “‘The Author of the Acacia Seeds’ and Other Extracts from the Journal of the Association of Therolinguistics” (1974) and Laura Jean McKay’s The Animals in That Country (2020) depict animal behavior in itself as being creative and language-like. Neither story offers a straightforward translation from nonhuman to human, each showing how human linguistic frameworks leave gaps for the untranslatable complexities in nonhuman animal gestures. This I suggest shows that further exploration of nonhuman animal communication in science fiction can allow us to move beyond ideas of human exceptionalism and logocentrism and can turn the hierarchical scale of communication into more of a spectrum with various communication types.

Benchmarking Large Language Models for Code Generation

As the landscape of software development continues to evolve, the need for efficient and innovative coding practices becomes increasingly apparent. This research endeavors to explore the effectiveness of Large Language Models (LLMs) in code generation, focusing on benchmarking their performance across various coding tasks. Leveraging advanced Natural Language Processing (NLP) techniques and deep learning architectures, our study investigates how LLMs, such as the codellama-13b-instruct.Q5_K_S.gguf engine, interpret and generate code from natural language instructions. With an emphasis on accuracy, efficiency, and user accessibility, our research seeks to shed light on the capabilities of LLMs in bridging the gap between human language and executable code. By evaluating factors such as model architecture, training data quality, and task complexity, we aim to provide insights into the potential of LLMs for revolutionizing the coding experience. Through meticulous benchmarking and analysis, this study aims to contribute to the advancement of LLM development and its applications in code generation, paving the way for more efficient and inclusive coding practices in the future.

English Vocabulary Learning Aid System Using Digital Twin Wasserstein Generative Adversarial Network Optimized With Jelly Fish Optimization Algorithm

ABSTRACT Natural Language Processing (NLP) is a technology that permits computers to recognize human languages. Words are the fundamental unit of analysis in deep-level grammatical and semantic analysis. The main goal of NLP is typically word segmentation. Since the machine learning techniques cannot be directly applied to the practical issue of significant structural disparities between various data modalities in a multi-modal context. In this paper, English Vocabulary Learning Aid System Using Digital Twin Wasserstein Generative Adversarial Network Optimized using Jelly Fish Optimization Algorithm is proposed. The problematic of multiple modal data heterogeneity is handled by the feature extraction of Parameterized Local Maximum Synchro squeezing Transform and extract the features such as Phonetic features, sentence length, word embedding’s, part of speech tags, word frequencies, N-grams. Then, the Digital twin Wasserstein generative adversarial network classifies the English vocabulary to easy words, intermediate words, and difficult words. The performance of the proposed EVLS-DtwinWGAN-NLP approach attains 3.101%, 7.12%, 7.73% higher accuracy, 24.13%, 13.04%, 29.51% lower computation Time and 2.292%, 5.365%, 1.551% higher AUC compared with existing methods like Feature extraction and analysis of natural language processing for deep learning English language (EVLS-BiLSTM-NLP), State of art for semantic analysis of natural language processing (EVLS-SA-NLP) respectively.

Translating Ulyssei@s: Work in progress between general and specialised translation in light of NMT

It is common knowledge that the publication of translation projects carried out by students is a very motivating factor for training. Since the second semester of 2015-2016, undergraduate translation students of the Faculty of Arts and Humanities of the University of Porto have participated in the development of the French and English versions of the digital encyclopaedia Ulyssei@s, created by the Institute for Comparative Literature Margarida Losa (ILCML) in the early 2010s. Besides motivating students, this translation project published on the Internet allows us to develop translation skills, foster teamwork, consolidate the three-phase methodology proposed by Gouadec (2002, 2007), and experiment with several essential tasks in language services: collaborative glossary-making, translation, revision of human translation and post-editing neural machine translation (NMT). Some of the challenges posed by the translation of Ulyssei@s are common to all types of translation, while others are specific to the translation of entries of this sui generis encyclopaedia, such as a variety of textual genres (biography, literary criticism, prose, poetry, theatre, essay) in hybrid texts and the need to find the original or the official translation of the works cited. This paper focuses on the data collected in the spring semester of 2022 and is based on the results of a survey submitted to students at the end of the project. It aims to share the experience of developing an inevitably unfinished project and adapting training and learning to the latest advances in Human Language Technology, since NMT has become a valuable tool for human translators, and Ulyssei@s is a digital encyclopaedia regularly enriched by ILCML collaborators with new entries.

Assessing the Acceptance of a Mid-Air Gesture Syntax for Smart Space Interaction: An Empirical Study

Mid-gesture interfaces have become popular for specific scenarios, such as interactions with augmented reality via head-mounted displays, specific controls over smartphones, or gaming platforms. This article explores the use of a location-aware mid-air gesture-based command triplet syntax to interact with a smart space. The syntax, inspired by human language, is built as a vocative case with an imperative structure. In a sentence like “Light, please switch on!”, the object being activated is invoked via making a gesture that mimics its initial letter/acronym (vocative, coincident with the sentence’s elliptical subject). A geometrical or directional gesture then identifies the action (imperative verb) and may include an object feature or a second object with which to network (complement), which also represented by the initial or acronym letter. Technically, an interpreter relying on a trainable multidevice gesture recognition layer makes the pair/triplet syntax decoding possible. The recognition layer works on acceleration and position input signals from graspable (smartphone) and free-hand devices (smartwatch and external depth cameras), as well as a specific compiler. On a specific deployment at a Living Lab facility, the syntax has been instantiated via the use of a lexicon derived from English (with respect to the initial letters and acronyms). A within-subject analysis with twelve users has enabled the analysis of the syntax acceptance (in terms of usability, gesture agreement for actions over objects, and social acceptance) and technology preference of the gesture syntax within its three device implementations (graspable, wearable, and device-free ones). Participants express consensus regarding the simplicity of learning the syntax and its potential effectiveness in managing smart resources. Socially, participants favoured the Watch for outdoor activities and the Phone for home and work settings, underscoring the importance of social context in technology design. The Phone emerged as the preferred option for gesture recognition due to its efficiency and familiarity. The system, which can be adapted to different sensing technologies, addresses the scalability concerns (as it can be easily extended for new objects and actions) and allows for personalised interaction.

Listen closely: Prosodic signals in podcast support learning

Based on the assumptions of Cognitive Load Theory and its derived signaling principle, previous research on instructional material has mainly investigated the effect of including visual cues to support the processing and integration of information. In the context of the renewed interest in commented videos and podcasts as instructional materials, the present study investigates the influence of prosodic signals on learning with digital media. An online experiment was conducted with 102 German students using an audio podcast as digital learning material. The audio recording was varied following the prosody of human language in terms of a 2 (volume: regular vs. higher) × 2 (pace: regular vs. slower) between-subject design to examine signaling key concepts. The results showed a positive effect of both prosodic cues manipulations (main effects) on learning outcomes and the most substantial impact when cumulated. This aligns with previous research on visual cues and thus extends findings on the signaling effect to the auditory modality. However, the picture is not so clear-cut. Indeed, higher learning outcome was also associated with higher mental effort and load with higher volume and no difference in effort but a lower load for a slower pace. Further, the presence of signals was also paired with an underestimation of learning. Overall, this could indicate a difficulty in processing the prosodic cues and integrating the signaled elements in the mental model, with an unknown effect on longer-term learning. Future research could further investigate additional possibilities of prosody (e.g., neutral vs. euphoric tone) as prosodic cues and characteristics linked to the speaker (e.g., age, gender) in podcasts and multimedia documents.

A Bibliometric Analysis of Text Mining: Exploring the Use of Natural Language Processing in Social Media Research

Natural language processing (NLP) plays a pivotal role in modern life by enabling computers to comprehend, analyze, and respond to human language meaningfully, thereby offering exciting new opportunities. As social media platforms experience a surge in global usage, the imperative to capture and better understand the messages disseminated within these networks becomes increasingly crucial. Moreover, the occurrence of adverse events, such as the emergence of a pandemic or conflicts in various parts of the world, heightens social media users’ inclinations towards these platforms. In this context, this paper aims to explore the scientific literature dedicated to the utilization of NLP in social media research, with the goal of highlighting trends, keywords, and collaborative networks within the authorship that contribute to the proliferation of papers in this field. To achieve this objective, we extracted and analyzed 1852 papers from the ISI Web of Science database. An initial observation reveals a remarkable annual growth rate of 62.18%, underscoring the heightened interest of the academic community in this domain. This paper includes an n-gram analysis and a review of the most cited papers in the extracted database, offering a comprehensive bibliometric analysis. The insights gained from these efforts provide essential perspectives and contribute to identifying pertinent issues in social media analysis addressed through the application of NLP.

Measurement and Mind: Unveiling the Self-Delusion of Metrification in Psychology

ABSTRACT This paper critically evaluates the quantification of psychological attributes through metric measurement. Drawing on epistemological considerations by Immanuel Kant, the development of measurement theory in the natural and social sciences is outlined. This includes an examination of Fechner’s psychophysical law and the fundamental criticism initially raised by von Kries. The distinction between theoretical and practical measurability is illuminated, addressing the question of equality within mental entities ( Ψ ) and their measures ( θ ). Psychometric scaling procedures such as Rasch scaling are argued to enable interval-scaled quantification on a real number line θ , but they are insufficient to establish a genuine interval scale level of Ψ . Instead, the values of θ should be regarded as qualitative statements that indicate ordinal relationships within Ψ . Two principles of scaling – the Guttman “model” and the Rasch model – are introduced, with their theoretical foundations explained, referencing the Rasch paradox. In the empirical section, data simulation is conducted to illustrate the Rasch paradox and to substantiate the theoretical considerations of the article. The research underscores the significance of linguistic analysis in understanding quantitative claims, suggesting a shift toward ordinal quantification within psychological measurement, drawing upon the linguistic principle of localism. Spatial metaphors are argued to play a central role in human language, even in natural sciences like physics, suggesting that systematic analysis of human language could offer a valuable method for the quantitative analysis of psychological attributes.

Diversity and Standards in Writing for Publication in the Age of AI—Between a Rock and a Hard Place

Abstract Research communities across disciplines recognize the need to diversify and decolonize knowledge. While artificial intelligence-supported large language models (LLMs) can help with access to knowledge generated in the Global North and demystify publication practices, they are still biased toward dominant norms and knowledge paradigms. LLMs lack agency, metacognition, knowledge of the local context, and understanding of how the human language works. These limitations raise doubts regarding their ability to develop the kind of rhetorical flexibility that is necessary for adapting writing to ever-changing contexts and demands. Thus, LLMs are likely to drive both language use and knowledge construction towards homogeneity and uniformity, reproducing already existing biases and structural inequalities. Since their output is based on shallow statistical associations, what these models are unable to achieve to the same extent as humans is linguistic creativity, particularly across languages, registers, and styles. This is the area where key stakeholders in academic publishing—authors, reviewers, and editors—have the upper hand, as our applied linguistics community strives to increase multilingual practices in knowledge production.