Hasil untuk "Computational linguistics. Natural language processing"

Olivier LONGI NZASI

Résumé : Par une approche bibliométrique, cette étude procède à l’évaluation sommaire de la production universitaire des élèves ingénieurs en sciences du pétrole et Gaz de la République Démocratique du Congo. Il résulte d’un travail d’inventaire métrique du corpus constitué essentiellement des mémoires des étudiants. Elle met en exergue la valeur de l’information scientifique et technique produite dans le cadre de la formation universitaire de ces étudiants. On y trouvera également le rôle du bibliothécaire universitaire en sa qualité de médiateur du savoir dans un contexte marqué par le mouvement du libre accès. L’étude a constaté l’usage des technologies de l’information et de la communication dans la valorisation de ce type de ressources documentaires. Cette valorisation passe par la politique du dépôt institutionnel qui est la vitrine de la production universitaire. Mots clés : Bibliométrie, valorisation, archive ouverte et littérature grise.

Heng Wu, Zijie Guo, Chunhua He et al.

Abstract Terahertz imaging technology has great potential applications in areas, such as remote sensing, navigation, security checks, and so on. However, terahertz images usually have the problems of heavy noises and low resolution. Previous terahertz image denoising methods are mainly based on traditional image processing methods, which have limited denoising effects on the terahertz noise. Existing deep learning‐based image denoising methods are mostly used in natural images and easily cause a large amount of detail loss when denoising terahertz images. Here, a residual‐learning‐based multiscale hybrid‐convolution residual network (MHRNet) is proposed for terahertz image denoising, which can remove noises while preserving detail features in terahertz images. Specifically, a multiscale hybrid‐convolution residual block (MHRB) is designed to extract rich detail features and local prediction residual noise from terahertz images. Specifically, MHRB is a residual structure composed of a multiscale dilated convolution block, a bottleneck layer, and a multiscale convolution block. MHRNet uses the MHRB and global residual learning to achieve terahertz image denoising. Ablation studies are performed to validate the effectiveness of MHRB. A series of experiments are conducted on the public terahertz image datasets. The experimental results demonstrate that MHRNet has an excellent denoising effect on synthetic and real noisy terahertz images. Compared with existing methods, MHRNet achieves comprehensive competitive results.

Lijia Deng, Qinghua Zhou, Shuihua Wang et al.

Abstract Counting high‐density objects quickly and accurately is a popular area of research. Crowd counting has significant social and economic value and is a major focus in artificial intelligence. Despite many advancements in this field, many of them are not widely known, especially in terms of research data. The authors proposed a three‐tier standardised dataset taxonomy (TSDT). The Taxonomy divides datasets into small‐scale, large‐scale and hyper‐scale, according to different application scenarios. This theory can help researchers make more efficient use of datasets and improve the performance of AI algorithms in specific fields. Additionally, the authors proposed a new evaluation index for the clarity of the dataset: average pixel occupied by each object (APO). This new evaluation index is more suitable for evaluating the clarity of the dataset in the object counting task than the image resolution. Moreover, the authors classified the crowd counting methods from a data‐driven perspective: multi‐scale networks, single‐column networks, multi‐column networks, multi‐task networks, attention networks and weak‐supervised networks and introduced the classic crowd counting methods of each class. The authors classified the existing 36 datasets according to the theory of three‐tier standardised dataset taxonomy and discussed and evaluated these datasets. The authors evaluated the performance of more than 100 methods in the past five years on different levels of popular datasets. Recently, progress in research on small‐scale datasets has slowed down. There are few new datasets and algorithms on small‐scale datasets. The studies focused on large or hyper‐scale datasets appear to be reaching a saturation point. The combined use of multiple approaches began to be a major research direction. The authors discussed the theoretical and practical challenges of crowd counting from the perspective of data, algorithms and computing resources. The field of crowd counting is moving towards combining multiple methods and requires fresh, targeted datasets. Despite advancements, the field still faces challenges such as handling real‐world scenarios and processing large crowds in real‐time. Researchers are exploring transfer learning to overcome the limitations of small datasets. The development of effective algorithms for crowd counting remains a challenging and important task in computer vision and AI, with many opportunities for future research.

Agustín Gravano, Julia Hirschberg, Štefan Beňuš

Jian Dou, Xuan Liu, Xingqi Liu et al.

Abstract The complexity and diversity brought by the distributed architecture of the new generation electric information collection system have deepened the difficulty of constructing evaluation verification index systems and quality evaluation models. Moreover, the presence of differentiated components has made fair and scientific verification challenging. Therefore, leveraging graph neural networks and siamese networks, a integrated construction quality evaluation system based on comprehensive weighted assessment in multiple scenarios was developed. Firstly, a graph neural network was constructed based on terminal data of the branches electricity usage information collection system and the link topology structure. Subsequently, this network was deployed on the headquarters side to directly acquire terminal data and generate mirror network input from the branches data, enabling real-time acquisition of various system operational indicators. Finally, the similarity between the headquarters and branches data was calculated using siamese networks to compute accuracy compensation weights for checking and evaluating various indicators, thereby obtaining comprehensive weighted quality evaluation indicators of the branches new generation electric information collection system. We use three types of services including electricity data collection, load forecasting, and task scheduling as experimental scenarios. The results showed that the multidimensional comprehensive weighted quality assessment combined with accuracy compensation obtained from the siamese network resulted in business construction quality assessment values of 97.92%, 95.95%, and 99.96% in branch. This value is approximately equal to the quality evaluation value of manual work, so the method can effectively verify the construction quality of new systems in the branch.

Antonella Catone, Daniela Sorrentino

The present work aims at showing the didactic potential of the novel Zweinhalb Störche: Roman einer Kindheit in Siebenbürgen, written in 2008 by the German-Romanian author Claudiu M. Florian, for multilingual learning in GFL classes. The paper focuses on the possible use of corpus-based learning tasks and consists of two parts: the first will introduce the main features of multilingual didactics and multilingual competence and the possible teaching approaches of inter- and transcultural literature through the use of corpora; the second will focus on the use of the novel to promote multilingual competence within the GFL classroom. In particular, specific tasks will be suggested to achieve a didactic surplus through the use of corpus compilation and analysis tools such as Sketch Engine.

Fangyu Liu, Qianchu Liu, Shruthi Bannur et al.

Waseem Abbas, Dr. Aziz Ibn ul Hassan

Shaukat Siddiqui is well known progressive short story writer and novelist in Urdu Literature. His novel "Jangloos" completely portrays the Pakistani society. The following research is an attempt to analyze novel "Jangloos" through a feminist lens, but this critical approach has been localized at length. Therefore, the analysis of "Jangloos" will be carried out by using local feminist approaches. The research will be focusing on the issues like exploitation, marginalization, and oppression that women face in "Jangloos". The research therefore is not only a textual analysis of but also a contextual and cultural study of the novel. In the context of this novel, an attempt has been made to explore the role of women in agricultural production and the venerability of women according to rural customs.

Sergio Dalmasso

Marcos Garcia

Maite Taboada, Julian Brooke, Milan Tofiloski et al.

Adam Kilgarriff, Gregory Grefenstette

Piotr Bojanowski, Edouard Grave, Armand Joulin et al.

Yanai Elazar, Shauli Ravfogel, Alon Jacovi et al.

AbstractA growing body of work makes use of probing in order to investigate the working of neural models, often considered black boxes. Recently, an ongoing debate emerged surrounding the limitations of the probing paradigm. In this work, we point out the inability to infer behavioral conclusions from probing results, and offer an alternative method that focuses on how the information is being used, rather than on what information is encoded. Our method, Amnesic Probing, follows the intuition that the utility of a property for a given task can be assessed by measuring the influence of a causal intervention that removes it from the representation. Equipped with this new analysis tool, we can ask questions that were not possible before, for example, is part-of-speech information important for word prediction? We perform a series of analyses on BERT to answer these types of questions. Our findings demonstrate that conventional probing performance is not correlated to task importance, and we call for increased scrutiny of claims that draw behavioral or causal conclusions from probing results.1

Petra Hendriks, Margreet Vogelzang

How do second language learners acquire form-meaning associations in the second language that are inconsistent with their first language? In this study, we focus on subject pronouns in Italian and Dutch. A native speaker of the non-null subject language Dutch learning the null subject language Italian as a second language will not only have to learn to use and comprehend null pronouns, but will also have to learn to use and comprehend overt pronouns differently in the L2 than in the L1. The interpretation of Italian overt pronouns, but not of Dutch overt pronouns or Italian null pronouns, has been argued to require perspective taking, specifically the use of hypotheses about the conversational partner’s communicative choices to guide one’s own choices. Therefore, a related question is how perspective taking and cognitive constraints influence L2 acquisition of such forms. Using computational cognitive modelling, this study explores two learning scenarios. In cognitive model 1, second language acquisition proceeds in the same way as first language acquisition and is based on the same grammar. In cognitive model 2, second language acquisition differs from first language acquisition and involves the construction of a partly different grammar. Our results suggest that the second scenario may be cognitively more plausible than the first one. Furthermore, our models explain why second language learners of Italian perform less native-like on overt pronouns than on null pronouns.

Bhupendra Gupta, Mayank Tiwari, Subir Singh Lamba

In this work, the authors develop a working software-based approach named ‘linearly quantile separated histogram equalisation-grey relational analysis’ for mammogram image (MI). This approach improves overall contrast (local and global) of given MI and segments breast-region with a specific end goal to acquire better visual elucidation, examination, and grouping of mammogram masses to help radiologists in settling on more precise choices. The fundamental commitment of this work is to demonstrate that results of good quality of breast-region segmentation can be accomplished from basic breast-region segmentation if the input image has good contrast and a better interpretation of hidden details. They have evaluated the proposed strategy for MIAS-MIs. Experimental results have shown that the proposed approach works better than state-of-the-art.

Ana Díaz-Negrillo

English neoclassical compounds rely on a distinct vocabulary stock and present morphological features which raise a number of theoretical questions. Generalisations about neoclassical compounds are also problematic because the output is by no means homogeneous, that is, defining features of neoclassical compounds sometimes co-exist with features that are not prototypical of these formations. The paper looks at neoclassical compounds with a view to exploring patterns of morphological behaviour and development in this class of compounds. The approach is both synchronic and diachronic: it researches whether the morphological behaviour of recently formed compounds is different from that of earlier compounds and, if so, in which respects. This is assessed on data from the BNC with respect to some of the features that are cited in the literature as defining properties of neoclassical compounds, specifically, their internal configuration, the occurrence or not of a linking vowel, and their productivity.

Begoña Crespo

This paper seeks to contribute to the study of the vernacularisation process in late Middle English by measuring up to what an extent concrete and abstract noun suffixes (in line with Dalton-Puffer 1996) attach to either Germanic or Romance bases in the medical texts extracted from the MEMT (Middle English Medical Texts) corpus. The findings obtained have been further described according to text type or genre and to target audience/readership. The description of these suffixes in relation to all the parameters already mentioned has confirmed the predominance of abstract suffixes of Romance origin although Germanic abstract suffixes are also abundant. More hybrid formations have been found with Germanic noun suffixes than with Romance ones which might be indicative of their versatility towards vernacularisation.

Mohammad Aliakbari, Mohammad Baghery Shabani, Fereshteh Khosravian

This study sought answers related to the distribution of colour terms in Persian poems and their metaphoric reflection in poets' beliefs, ideas, or values. In so doing, 137 Persian verses from two poetry books with colour terms in content were considered for the analysis. Four raters who studied literature of Persian scrutinized the verses for the evaluation of the colour metaphoric conceptualizations. To validate the raters' suggestions, a focus group of sixteen commented on the recommended connotations. Results indicated that colours are not similarly distributed in Persian poems, are used with different conceptualizations and stood for both positive and negative connotations. Therefore, since colours are part of the authors' and speakers' daily lives to express information, knowledge of metaphoric expressions is suggested to be an inseparable part of language classes.

Alexander Clark, Shalom Lappin