Hasil untuk "Computational linguistics. Natural language processing"

David M. Magerman

Wei Chen, Shanqing Wan

Abstract The human pose detection in marathon sports faces challenges such as large motion amplitude, multiple limb occlusions, and limited computing resources. Traditional detection models are prone to accuracy degradation and response delay in practical applications. Therefore, the study introduces an attention mechanism module based on multi-scale channel weighting and deformable convolution to enhance feature expression ability. The detection head is designed to be lightweight through channel by channel convolution mechanism and Squeeze channel compression mechanism. Finally, a lightweight Center Net pose detection model that integrates multi-module optimization is proposed. The proposed model achieved F1 values of 92.83% and 94.37% on the Human 3.6 M Human Motion Capture Dataset-Running Subset and the AI Challenger Human Keypoint Detection Dataset-Running Category, respectively, with an average response time of less than 0.65 s, significantly better than that of the other three advanced models. The joint prediction error under different running poses was less than 4.5°, and the missing rate of key points in multi-light and camera shake scenes was controlled within 5%, with a frame rate of up to 35FPS. The model performs well in accuracy, robustness, and real-time performance, which is suitable for human pose recognition and analysis tasks in intelligent terminals and sports scenes.

Ndèye Maty PAYE

Résumé : Notre contribution propose un bain linguistique au cœur de la ville de Banjul, une immersion grâce à l’observation et à l’analyse des enseignes publicitaires (administratives commerciales, culturelles) afin de rendre compte de sa configuration sociolinguistique. Cette étude se réalisera en considérant le marquage linguistique, identitaire et culturel sur les inscriptions publicitaires tout en examinant les habitudes et les activités. Mots-clés : plurilinguisme, alternance codique, sociolinguistique urbaine, publicité, Gambie

Lucía Gil de Montes Garín

Dilawar Khan, Iftikhar Ahmed, Inam Ullah et al.

M. Karyotaki, Athanasios Drigas, C. Skianis

Chatbots are dialogue systems that utilize computational linguistics (CL), including automatic speech recognition (ASR) and natural language processing (NLP). Artificially intelligent conversational agents combine personalization, interoperability, and scalability with the aim of promoting safe information monitoring, management, and retrieval. AI chatbots offer user-friendly engagement for innovative e-learning, care assistance, and multilingual digital content creation, promoting inclusiveness and AI-enhanced communication. They are a breakthrough for future societies and economies as they can offer cost-effective, tailor-made, and instant exchange of knowledge and skills, including on-site assistance, health monitoring, and e-consultation. AI chatbots are constantly improving to the benefit of their users. Their economic and social impact is expected to rise as individuals, especially vulnerable populations, are trained to use them for lifelong learning, decision-making, and problem-solving.

Khin Sandar Kyaw, Praman Tepsongkroh, Chanwut Thongkamkaew et al.

Since trading has been transformed into online platforms, marketing strategies have adapted to digital systems in order to enhance the Customer Relationship Management (CRM) in the E-commerce era. E-commerce systems are the most widely used digital platforms where customer information including personal, and behavioral information, flows as a big data stream. Conducting business intelligent observation on digital big data assists to improve digital marketing policy through the customer intention prediction, decision-making to advertise based on the target group clustering, and customer assist recommendation. To discover the business intelligent, sentiment analysis technology can assist as a solution to understand the customer behavior through the opinion mining where the natural language processing, text analysis, computational linguistics, and biometrics are conducted to analysis the customer information and feedbacks, for smart digital marketing applications. This research observes the applications of sentiment analysis in E-commerce systems as a comprehensive study, and the critical role of discovering business intelligent for smart digital marketing in E-commerce platforms is pointed out according to the technical perspective. Furthermore, the concept of a business intelligent framework integrated with the modelling of decision-making, prediction, and recommendation systems using the contribution of hybrid feature selection which is based on rule-based and machine learning-based sentiment analysis, is proposed for the future innovative smart digital marketing trend.

Priyanka Prajapati, Vishal Goyal, Kawaljit Kaur

Francesco Periti, S. Picascia, S. Montanelli et al.

The study of semantic shift, that is, of how words change meaning as a consequence of social practices, events and political circumstances, is relevant in Natural Language Processing, Linguistics, and Social Sciences. The increasing availability of large diachronic corpora and advance in computational semantics have accelerated the development of computational approaches to detecting such shift. In this paper, we introduce a novel approach to tracing the evolution of word meaning over time. Our analysis focuses on gradual changes in word semantics and relies on an incremental approach to semantic shift detection (SSD) called What is Done is Done (WiDiD). WiDiD leverages scalable and evolutionary clustering of contextualised word embeddings to detect semantic shift and capture temporal transactions in word meanings. Existing approaches to SSD: (a) significantly simplify the semantic shift problem to cover change between two (or a few) time points, and (b) consider the existing corpora as static. We instead treat SSD as an organic process in which word meanings evolve across tens or even hundreds of time periods as the corpus is progressively made available. This results in an extremely demanding task that entails a multitude of intricate decisions. We demonstrate the applicability of this incremental approach on a diachronic corpus of Italian parliamentary speeches spanning eighteen distinct time periods. We also evaluate its performance on seven popular labelled benchmarks for SSD across multiple languages. Empirical results show that our results are comparable to state-of-the-art approaches, while outperforming the state-of-the-art for certain languages.

Mallika Boyapati, Ramazan S. Aygun

In recent years, transformer-based models, particularly BERT (Bidirectional encoder Representations from Transformers), have revolutionized natural language processing tasks, achieving state-of-the-art performance in various domains. In the context of natural language processing (NLP) and linguistics, understanding the semantic aspects of text is crucial for tasks like information retrieval, sentiment analysis, machine translation, and many others. However, the high dimensionality of BERT embeddings presents challenges in real-world applications due to increased memory and computational requirements. Reducing the dimensionality of BERT embeddings would benefit many application downstream tasks by reducing the computational requirements. Although there are prevalently used dimensionality reduction methods which focus on feature representation with lower dimensions, their application on NLP tasks may not yield semantically correct results. We propose a novel framework named as semanformer (semantics-aware encoder-decoder dimensionality reduction method) that leverages transformer-based encoder-decoder model architecture to perform dimensionality reduction on BERT embeddings for a corpus while preserving crucial semantic information. To evaluate the effectiveness of our approach, we conduct a comprehensive use case evaluation on diverse text datasets by sentence reconstruction. Our experiments show that our proposed method achieves high sentence reconstruction accuracy (SRA) more than 83% compared to the traditional dimensionality reduction methods such as PCA (SRA < 66%) and t-SNE (SRA < 9%).

Raia Abu Ahmad, E. Borisova, Georg Rehm

The steep increase in the number of scholarly publications has given rise to various digital repositories, libraries and knowledge graphs aimed to capture, manage, and preserve scientific data. Efficiently navigating such databases requires a system able to classify scholarly documents according to the respective research (sub-)field. However, not every digital repository possesses a relevant classification schema for categorising publications. For instance, one of the largest digital archives in Computational Linguistics (CL) and Natural Language Processing (NLP), the ACL Anthology, lacks a system for classifying papers into topics and sub-topics. This paper addresses this gap by constructing a corpus of 1,500 ACL Anthology publications annotated with their main contributions using a novel hierarchical taxonomy of core CL/NLP topics and sub-topics. The corpus is used in a shared task with the goal of classifying CL/NLP papers into their respective sub-topics.

S. Lakshmi

Kristen Hawley Turner

Yamina BENACHOUR

Résumé : Cette contribution consiste à dévoiler le champ des neurosciences et son impact sur le domaine éducatif, qui a vécu des changements, préparant le terrain pour une évolution bouleversante. En effet, son essor était bien marqué dans les différents domaines : la médecine, la physiologie, la biologie, la psychologie, la marchandise, les études computationnelles, arrivant au processus enseignement / apprentissage. Aujourd’hui, les neurosciences s’invitent dans la classe de langue pour assurer une bonne maitrise de l’opération éducative à travers la compréhension du fonctionnement cérébral, des processus mentaux et de la cognition de l’apprenant. Mots-clés : Enseignement / apprentissage, neurosciences de l’éducation, styles d’apprentissage, classe de langue.

KATO NZITA Orelis

Résumé : Cet article aborde la question de la communication politique à l’échéance électorale de décembre 2023. Plus concrètement, il présente le profil des candidats et leur appartenance. Il identifie et catégorise les thèmes portés par ces acteurs pendant la campagne. Ceci a conduit à les analyser, à dégager l’orientation d’axe des thèmes les plus récurrents tout en appuyant par des argumentations qui justifient les raisons de ces résultats. A ces jours, la participation féminine à ce scrutin reste faible et minoritaire. L’on note la présence plus des candidats hommes que des femmes, soit deux candidats sur les vingt-six. L’échéance électorale de décembre 2023 connaît une multitude des candidats. Plus d’une vingtaine des candidats à la magistrature suprême dont la majorité est inscrite en indépendant ou des partis /regroupements politiques. La plus grande sensibilité des thèmes de campagne portés par les candidats est dans la promesse d’un changement dans un futur proche qu’ils promettent de réaliser une fois élue. Pour tenter de répondre à ces questions, le recours à la méthode d’analyse de contenu dans son approche qualitative, soutenue par les techniques documentaire et d’observation directe, s’est avéré nécessaire. Sur le plan temporal, cette étude couvre la période de la campagne électorale, du 19 novembre au 19 décembre 2023, soit un mois de campagne. Et, au volet spatial, elle concerne que l’élection présidentielle. Mots-clés : Communication Politique, Election, Campagne, Marketing Politique

Dilem Dinc, Asli Aslan, Tolgay Ergenoglu

This study investigates whether cognitive styles have an effect on the interpretation of implications hidden in speech and examines the Event-Related Potential (ERP) pattern of this effect. In the first study (104 participants), a Cognitive Style Analysis (CSA) test, an interpretation task (meaning), Indirectness Scale, Cultural Communication Scale-Turkish (CCS-TUR), and information collection forms were used as data collection tools. In the second study (29 participants), an interpretation task (implicitness) and the EEG-ERP system were used. In the meaning interpretation task, the analyses revealed that individuals with an Analytic CS tendency preferred interpretations containing implications less than individuals with Holistic CS. In addition, it has been observed that individuals with an Analytic CS tendency focus their attention more when asking questions for the texts in the implicitness interpretation task according to the ERP patterns. This may be an indication that brain function is physically different in all individuals when interacting with each other.

S. Salloum, Mostafa Al-Emran, A. A. Monem et al.

Text mining has become one of the trendy fields that has been incorporated in several research fields such as computational linguistics, Information Retrieval (IR) and data mining. Natural Language Processing (NLP) techniques were used to extract knowledge from the textual text that is written by human beings. Text mining reads an unstructured form of data to provide meaningful information patterns in a shortest time period. Social networking sites are a great source of communication as most of the people in today’s world use these sites in their daily lives to keep connected to each other. It becomes a common practice to not write a sentence with correct grammar and spelling. This practice may lead to different kinds of ambiguities like lexical, syntactic, and semantic and due to this type of unclear data, it is hard to find out the actual data order. Accordingly, we are conducting an investigation with the aim of looking for different text mining methods to get various textual orders on social media websites. This survey aims to describe how studies in social media have used text analytics and text mining techniques for the purpose of identifying the key themes in the data. This survey focused on analyzing the text mining studies related to Facebook and Twitter; the two dominant social media in the world. Results of this survey can serve as the baselines for future text mining research.

Giovanni Salvagnini Zanazzo

Una lettura del celebre racconto borgesiano come allegoria dell’offerta libraria del colosso di Bezos. In esso, non solo il potenziale acquirente è portato a smarrirsi tra i libri già scritti nella sezione dedicata del sito, ma una pagina apposita lo invita ad autoprodurne altri, contribuendo in prima persona all’incremento di quella quantità che lo disorienta. Eppure la vertigine di infinito e impossibilità su cui punta lo scrittore argentino si mescolano nel contemporaneo all’euforia dei percorsi che ancora riescono, che bucano il marasma per affermarsi. Impossibile e possibile convivono come un’altra capriola magica di Internet.

J. Pustejovsky

. This chapter briefly reviews the research conducted on the representation of events, from the perspectives of natural language processing, artificial intelligence (AI), and linguistics. AI approaches to modeling change have traditionally focused on situations and state descriptions. Linguistic approaches start with the description of the propositional content of sentences (or natural language expressions generally). As a result, the focus in the two fields has been on different problems. Namely, linguistic theories try to maintain compositionality in the expressions associated with linguistic units, or what is known as semantic compositionality . In AI and in the planning community in particular the focus has been on maintaining compositionality in the way plans are constructed, as well as the correctness of the algorithm that searches and traverses the state space. This can be called plan compositionality . I argue that these approaches have common elements that can be drawn on to view event semantics from a unifying perspective, where we can distinguish between the surface events denoted by verbal predicates and what I refer to as the latent event structure of a sentence. Latent events within a text refer to the finer-grained subeventual representations of events denoted by verbs or nominal expressions, as well as to hidden events connoted by nouns. By clearly distinguishing between surface and latent event structures of sentences and texts, we move closer to a general computational theory of event structure, one permitting a common vocabulary for events and the relations between them, while enabling reasoning at multiple levels of interpretation.

Joel R. Tetreault