Search

Emotion detection (ED) plays a vital role in determining individual interest in any field. Humans use gestures, facial expressions, and voice pitch and choose words to describe their emotions. Significant work has been done to detect emotions from the textual data in English, French, Chinese, and other high-resource languages. However, emotion classification has not been well studied in low-resource languages (i.e., Urdu) due to the lack of labeled corpora. This article presents a publicly available Urdu Nastalique Emotions Dataset ( UNED ) of sentences and paragraphs annotated with different emotions and proposes a deep learning (DL)-based technique for classifying emotions in the UNED corpus. Our annotated UNED corpus has six emotions for both paragraphs and sentences. We perform extensive experimentation to evaluate the quality of the corpus and further classify it using machine learning and DL approaches. Experimental results show that the developed DL-based model performs better than generic machine learning approaches with an F1 score of 85% on the UNED sentence-based corpus and 50% on the UNED paragraph-based corpus.

Neural document ranking models perform impressively well due to superior language understanding gained from pre-training tasks. However, due to their complexity and large number of parameters, these (typically transformer-based) models are often non-interpretable in that ranking decisions can not be clearly attributed to specific parts of the input documents. In this paper we propose ranking models that are inherently interpretable by generating explanations as a by-product of the prediction decision. We introduce the Select-and-Rank paradigm for document ranking, where we first output an explanation as a selected subset of sentences in a document. Thereafter, we solely use the explanation or selection to make the prediction, making explanations first-class citizens in the ranking process. Technically, we treat sentence selection as a latent variable trained jointly with the ranker from the final output. To that end, we propose an end-to-end training technique for Select-and-Rank models utilizing reparameterizable subset sampling using the Gumbel-max trick. We conduct extensive experiments to demonstrate that our approach is competitive to state-of-the-art methods. Our approach is broadly applicable to numerous ranking tasks and furthers the goal of building models that are interpretable by design. Finally, we present real-world applications that benefit from our sentence selection method., Comment: Accepted to ACM TOIS

Parallel sentence pairs play a very important role in many natural language processing tasks, especially cross-lingual tasks such as machine translation. So far, many Asian language pairs lack bilingual parallel sentences. As collecting bilingual parallel data is very time-consuming and difficult, it is very important for many low-resource Asian language pairs. While existing methods have shown encouraging results, they rely on bilingual data seriously or have some drawbacks in an unsupervised situation. To address these issues, we propose a new unsupervised similarity calculation and dynamic selection metric to obtain parallel sentence pairs in an unsupervised situation. First, our method maps bilingual word embedding by postdoc adversarial training, which rotates the source space to match the target without parallel data. Then, we introduce a new cross-domain similarity adaption to obtain parallel sentence pairs. Experimental results on real-world datasets show that our model can obtain better accuracy and recall on mining parallel sentence pairs. We also show that the extracted bilingual sentence corpora can significantly improve the performance of neural machine translation.

Recent advancements in deep learning techniques have transformed the area of semantic text matching (STM). However, most state-of-the-art models are designed to operate with short documents such as tweets, user reviews, comments, and so on. These models have fundamental limitations when applied to long-form documents such as scientific papers, legal documents, and patents. When handling such long documents, there are three primary challenges: (i) the presence of different contexts for the same word throughout the document, (ii) small sections of contextually similar text between two documents, but dissimilar text in the remaining parts (this defies the basic understanding of “similarity”), and (iii) the coarse nature of a single global similarity measure which fails to capture the heterogeneity of the document content. In this article, we describe CoLDE : Co ntrastive L ong D ocument E ncoder—a transformer-based framework that addresses these challenges and allows for interpretable comparisons of long documents. CoLDE uses unique positional embeddings and a multi-headed chunkwise attention layer in conjunction with a supervised contrastive learning framework to capture similarity at three different levels: (i) high-level similarity scores between a pair of documents, (ii) similarity scores between different sections within and across documents, and (iii) similarity scores between different chunks in the same document and across other documents. These fine-grained similarity scores aid in better interpretability. We evaluate CoLDE on three long document datasets namely, ACL Anthology publications, Wikipedia articles, and USPTO patents. Besides outperforming the state-of-the-art methods on the document matching task, CoLDE is also robust to changes in document length and text perturbations and provides interpretable results. The code for the proposed model is publicly available at https://github.com/InterDigitalInc/CoLDE .

The problem of Region of Interest (RoI) in document layout analysis and document recognition has recently become an essential topic in OCRing systems. Arabic manuscript layout analysis and OCRing recognition using language detection, document category, and RoI with Keras and TensorFlow are terms of the state-of-the-art that should be investigated. This article investigates the problem of Arabic manuscript recognition problems with respect to in OCRing-based recognition. A new framework architecture, which integrates Fast Gradient Sign Method (FGSM) using Keras and TensorFlow with adversarial image generation during training procedure is proposed. Also, the article tries to improve the OCRing accuracy of the image enhancement, alignment, layout analysis, and recognition using deep learning in multilingual system. RoIs detections will be performed using a custom trained deep learning model using bounding box regression with Keras and TensorFlow. This topic investigates an extension of Page Segmentation Method (PSM) to enhance OCRing parameter modes and enhances Arabic OCRing system accuracy from reinforcement strategy. Therefore, the article achieves a significant improvement of OCRing results due to the three parameters: language identification, document category, and RoI types (Table, Title, Paragraph, figure, and list). This model is based on “region proposal algorithm” as a basis of CNN object detectors to find the number of the RoIs. Therefore, the proposed framework performs three distinctive tasks: (1) CNN architecture for adversarial training, (2) an implementation of the FGSM with Keras and TensorFlow, and (3) an adversarial training script implementation with the CNN and the FGSM method. The experiments on Arabic manuscript dataset including Arabic text, English/Arabic documents, and Latin digits’ datasets, demonstrate the accuracy of the proposed method. Moreover, the proposed framework performs well and succeeded in defending against adversarial attacks or adversarial images. The experimental results on our collected dataset illustrate the novelty of our proposed framework over the other existing PSM methods to be extended and updated to improve the quality of the OCRing system. The results show that the influence of PSM after expanding using the RoI types, language ID, and document/manuscript category can improve the OCRing accuracy. Also, the experimental results show significant performance by the new framework model with accuracy reached to 99% compared to relative methods.

En este trabajo presentamos el proyecto de investigación Post Scriptum, que tiene por objeto la búsqueda, edición y estudio históricolingüístico de cartas privadas escritas en España y Portugal durante la Edad Moderna. Post Scriptum reúne una amplia colección epistolar y la ofrece en dos formatos preparados para la búsqueda: el de la edición crítica digital y el del corpus lingüísticamente anotado. En esta presentación se exponen los aspectos fundamentales sobre el diseño y elaboración de Post Scriptum, desde la búsqueda de los manuscritos en archivos históricos hasta la edición digital y anotación semiautomática de los textos y su publicación en línea; también se recogen resultados definitivos y se aportan algunos ejemplos de explotación del corpus en diferentes niveles de análisis., In this paper we present the project Post Scriptum, which aims to build up a campaign of collection, edition and historical-linguistic study of private letters written in Portugal and Spain along the Early Modern Ages. Not only does the Post Scriptum project present a wide collection of private letters, but it also makes it available as a scholarly digital edition and as an annotated corpus. Key aspects about the development of Post Scriptum are explained in this paper, from the finding of manuscripts in historical archives to the digital edition and semi-automatic annotation of texts and their publication online. Final results and some examples that illustrate how the exploitation of this corpus works at different linguistic levels are also included.

Unconstrained handwritten text recognition remains challenging for computer vision systems. Paragraph text recognition is traditionally achieved by two models: the first one for line segmentation and the second one for text line recognition. We propose a unified end-to-end model using hybrid attention to tackle this task. This model is designed to iteratively process a paragraph image line by line. It can be split into three modules. An encoder generates feature maps from the whole paragraph image. Then, an attention module recurrently generates a vertical weighted mask enabling to focus on the current text line features. This way, it performs a kind of implicit line segmentation. For each text line features, a decoder module recognizes the character sequence associated, leading to the recognition of a whole paragraph. We achieve state-of-the-art character error rate at paragraph level on three popular datasets: 1.91% for RIMES, 4.45% for IAM and 3.59% for READ 2016. Our code and trained model weights are available at https://github.com/FactoDeepLearning/VerticalAttentionOCR.

In this paper, we propose cryptanalytic results on two lightweight stream ciphers: Fountain v1 and Lizard. The main results of this paper are the followings: \begin{document}$ - $\end{document} We propose a zero-sum distinguisher on reduced round Fountain v1. In this context, we study the non-randomness of the cipher with a careful selection of cube variables. Our obtained cube provides a zero-sum on Fountain v1 till \begin{document}$ 188 $\end{document} initialization rounds and significant non-randomness till \begin{document}$ 189 $\end{document} rounds. This results in a distinguishing attack on Fountain v1 with \begin{document}$ 189 $\end{document} initialization rounds. \begin{document}$ - $\end{document} Further, we find that the same cipher has a weakness against conditional Time-Memory-Data-Tradeoff (TMDTO). We show that TMDTO attack using sampling resistance has online complexity \begin{document}$ 2^{110} $\end{document} and offline complexity \begin{document}$ 2^{146} $\end{document} . \begin{document}$ - $\end{document} Finally, we revisit the Time-Memory-Data-Tradeoff attack on Lizard by Maitra et al. (IEEE Transactions on Computers, 2018) and provide our observations on their work. We show that instead of choosing any random string, some particular strings would provide better results in their proposed attack technique.

Handwritten Text Recognition has achieved an impressive performance in public benchmarks. However, due to the high inter- and intra-class variability between handwriting styles, such recognizers need to be trained using huge volumes of manually labeled training data. To alleviate this labor-consuming problem, synthetic data produced with TrueType fonts has been often used in the training loop to gain volume and augment the handwriting style variability. However, there is a significant style bias between synthetic and real data which hinders the improvement of recognition performance. To deal with such limitations, we propose a generative method for handwritten text-line images, which is conditioned on both visual appearance and textual content. Our method is able to produce long text-line samples with diverse handwriting styles. Once properly trained, our method can also be adapted to new target data by only accessing unlabeled text-line images to mimic handwritten styles and produce images with any textual content. Extensive experiments have been done on making use of the generated samples to boost Handwritten Text Recognition performance. Both qualitative and quantitative results demonstrate that the proposed approach outperforms the current state of the art., Comment: Accepted to TPAMI

The W3C Generating RDF from Tabular Data on the Web Recommendation provides a mechanism for mapping CSV-formatted data to any RDF graph model. Since the Wikibase data model used by Wikidata can be expressed as RDF, this Recommendation can be used to document tabular snapshots of parts of the Wikidata knowledge graph in a simple form that is easy for humans and applications to read. Those snapshots can be used to document how subgraphs of Wikidata have changed over time and can be compared with the current state of Wikidata using its Query Service to detect vandalism and value added through community contributions.

A robotic platform for mobile manipulation needs to satisfy two contradicting requirements for many real-world applications: A compact base is required to navigate through cluttered indoor environments, while the support needs to be large enough to prevent tumbling or tip over, especially during fast manipulation operations with heavy payloads or forceful interaction with the environment. This paper proposes a novel robot design that fulfills both requirements through a versatile footprint. It can reconfigure its footprint to a narrow configuration when navigating through tight spaces and to a wide stance when manipulating heavy objects. Furthermore, its triangular configuration allows for high-precision tasks on uneven ground by preventing support switches. A model predictive control strategy is presented that unifies planning and control for simultaneous navigation, reconfiguration, and manipulation. It converts task-space goals into whole-body motion plans for the new robot. The proposed design has been tested extensively with a hardware prototype. The footprint reconfiguration allows to almost completely remove manipulation-induced vibrations. The control strategy proves effective in both lab experiment and during a real-world construction task., Comment: 8 pages, accepted for RA-L and IROS 2022

The subtleties of human perception, as measured by vision scientists through the use of psychophysics, are important clues to the internal workings of visual recognition. For instance, measured reaction time can indicate whether a visual stimulus is easy for a subject to recognize, or whether it is hard. In this paper, we consider how to incorporate psychophysical measurements of visual perception into the loss function of a deep neural network being trained for a recognition task, under the assumption that such information can enforce consistency with human behavior. As a case study to assess the viability of this approach, we look at the problem of handwritten document transcription. While good progress has been made towards automatically transcribing modern handwriting, significant challenges remain in transcribing historical documents. Here we describe a general enhancement strategy, underpinned by the new loss formulation, which can be applied to the training regime of any deep learning-based document transcription system. Through experimentation, reliable performance improvement is demonstrated for the standard IAM and RIMES datasets for three different network architectures. Further, we go on to show feasibility for our approach on a new dataset of digitized Latin manuscripts, originally produced by scribes in the Cloister of St. Gall in the the 9th century.

Nominal automata are models for recognising languages over infinite alphabets, based on the algebraic notion of nominal set. Motivated by their use in automata theory, we show how to compute efficiently with nominal sets over the so-called total order symmetry, a variant which allows to compare alphabet letters for equality as well as their respective order. We develop an explicit finite representation of such nominal sets and basic constructions thereon. The approach is implemented as the library Ons (Ordered Nominal Sets), enabling programming with infinite sets. Returning to our motivation of nominal automata, we evaluate Ons in two applications: minimisation of automata and active automata learning. In both cases, Ons is competitive compared to existing implementations and outperforms them for certain classes of inputs.

Software projects capture information in various kinds of artifacts, including source code, tests, and documentation. Such artifacts routinely encode information that is redundant, i.e., when a specification encoded in the source code is also separately tested and documented. Without supporting technology, such redundancy easily leads to inconsistencies and a degradation of documentation quality. We designed a tool-supported technique, called DScribe, that leverages redundancy between tests and documentation to generate consistent and checkable documentation and unit tests based on a single source of information. DScribe generates unit tests and documentation fragments based on a novel template and artifact generation technology. By pairing tests and documentation generation, DScribe provides a mechanism to automatically detect and replace outdated documentation. Our evaluation of the Apache Commons IO library revealed that of 835 specifications about exception handling, 85% of them were not tested or correctly documented, and DScribe could be used to automatically generate 97% of the tests and documentation.

Extracting relevant information from a large amount of data is a challenging task. Automatic text summarization is a potential solution for obtaining this information. In this paper, a nature inspired swarm intelligence-based algorithm viz. firefly algorithm for multi-document text summarization is proposed. A new fitness function consisting of three features viz. topic relation factor, cohesion factor and readability factor is utilized. The experiments are performed on datasets from Document Understanding Conference i.e. DUC-2002, DUC-2003 and DUC-2004. The performance of the algorithm has been evaluated using ROUGE score. The performance of the proposed algorithm is compared with some other nature inspired ones such as particle swarm optimization (PSO) and genetic algorithm (GA). The performance of the proposed algorithm outperforms the other adopted ones.

Natural language processing (NLP) is a rapidly growing research field in computer science and cognitive science. Automatic correction of lexical errors is one of the applications of NLP, which aims to detect errors in the text and suggest possible corrections based on computer and linguistic models. After a state of the art and a comparison of spelling correction approaches, we developed a spelling error correction system for the Amazigh language combining the Damerau-Levenshtein algorithm and N-gram. This tool will propose possible corrections for each misspelled word in the text. Successful tests have been carried out using an Amazigh corpus.

Despite the significant success of document image analysis techniques, efficient Optical Character Recognition (OCR) of degraded document images still remains an open problem. Although a body of work has been reported on degraded document recognition for English language, only little attention has been paid to Indic scripts. In this work, we focus on developing a degraded OCR for Bangla, a major Indian language. In general, an OCR system includes segmentation of the foreground text part from the background followed by recognition of the extracted text. The text segmentation module aims to assign the foreground or background label to each pixel of the document image. In this paper, we present a new OCR system which is particularly suitable for degraded quality Bangla document images. The contribution is two fold. In the first phase, we use a semi-supervised Markov Random Field (MRF)- based Generative Adversarial Network (GAN) model (which we call MRF-GAN ) for foreground segmentation of texts from degraded text. In the proposed MRF-GAN , we extend the concept of GAN to a multitask learning mechanism where discriminator-classifier networks differentiate between real/fake images and also assign a foreground or background label to each pixel. In the second phase, we propose to use a new encoder-decoder based recognizer that incorporates an attention-based character to a word prediction model, which has the capability of minimizing Word Error Rate (WER) . We optimize this network using a Multitask based Transfer Learning scheme (MTTL) . We perform experiments on a publicly available degraded Bangla document image dataset as well as on a new degraded printed Hindi document image dataset, which has been created as a part of the present study. Results of the experimentations demonstrate the efficacy of the proposed OCR.

Let H be a binary-labeled concept class. We prove that H can be PAC learned by an (approximate) differentially private algorithm if and only if it has a finite Littlestone dimension. This implies a qualitative equivalence between online learnability and private PAC learnability.

We study the role of markup dispersion and aggregate TFP for monetary transmission. Empirically, we show that the response of markup dispersion to monetary policy shocks can account for a significant fraction of the aggregate TFP response in the first two years after the shock. Analytically, we show that heterogeneous price rigidity can explain the response of markup dispersion if firms have a precautionary price setting motive, which is present in common New Keynesian environments. We provide empirical evidence in support of this explanation. Finally, we study the mechanism and its implications in a quantitative model.

This paper presents EXMARaLDA, a system for the computer-assisted creation and analysis of spoken language corpora. The first part contains some general observations about technological and methodological requirements for doing corpus-based pragmatics. The second part explains the system’s architecture and gives an overview of its most important software components – a transcription editor, a corpus management tool and a corpus query tool. The last part presents some corpora which have been or are currently being compiled with the help of EXMARaLDA.

English Profile (EP) is an ongoing empirical exploration of learner English initiated by Cambridge University Press and Cambridge English, among others. EP aims to create a set of empirically-based descriptions of language competencies for English. ‘Reference Level Descriptors’ already exist as part of the Common European Framework of Reference (CEFR) but are intuitively derived and not designed for one specific language. The English Grammar Profile (EGP, www.englishprofile.org/english-grammar-profile) is a sub-project of EP which aims to profile learner competence in grammar. This paper details the rationale for the study and the methodology that was developed to investigate the Cambridge Learner Corpus to arrive at over 1,200 grammatical competence statements. Key findings which link to existing corpus-based second language acquisition work are also presented.

The establishment of English and French corpora has provided great convenience for language application and research. However, in the field of Japanese language research, the construction of Japanese corpus has been slow due to the limitation of Japanese markup format. This paper discusses the scientificity, rationality, feasibility, and construction of “microcorpus” and “specialized corpus” for the application of Japanese corpus in Japanese language teaching. Textual corpus is a corpus that contains all text but no media such as audio and pictures, and it is mostly used in teaching. The Japanese language corpus is a corpus created by analyzing the existing Japanese classroom teaching situation in response to the current reform of Japanese language teaching mode. It is important for teaching Japanese in colleges and universities because it can help students to learn independently and improve their learning initiative and motivation. The teaching-based text corpus is a small corpus for Japanese language teaching and learning, which is derived from the teaching process. The corpus can be created independently on an ordinary PC machine through software, and the collected corpus can be imported into the corpus and used, which provides another way to improve students’ interest and learning ability on their own. Based on the search software, this paper selects representative novels from the Aozora Library and creates a simple corpus to serve the teaching of Japanese interpretation, which improves the teaching effect. At the same time, this paper discusses the boundaries and difficulties of individual self-built corpora with a view to making breakthroughs and progress in future research and development.

Recognition of Arabic-like scripts such as Persian and Urdu is more challenging than Latin-based scripts. This is due to the presence of a two-dimensional structure, context-dependent character shapes, spaces and overlaps, and placement of diacritics. Not much research exists for offline handwritten Urdu script which is the 10th most spoken language in the world. We present an attention based encoder-decoder model that learns to read Urdu in context. A novel localization penalty is introduced to encourage the model to attend only one location at a time when recognizing the next character. In addition, we comprehensively refine the only complete and publicly available handwritten Urdu dataset in terms of ground-truth annotations. We evaluate the model on both Urdu and Arabic datasets and show that contextual attention localization outperforms both simple attention and multi-directional LSTM models., 25 pages, 15 figures and 6 tables

Image captioning has emerged as an interesting research field in recent years due to its broad application scenarios. The traditional paradigm of image captioning relies on paired image-caption datasets to train the model in a supervised manner. However, creating such paired datasets for every target language is prohibitively expensive, which hinders the extensibility of captioning technology and deprives a large part of the world population of its benefit. In this work, we present a novel unpaired cross-lingual method to generate image captions without relying on any caption corpus in the source or the target language. Specifically, our method consists of two phases: (i) a cross-lingual auto-encoding process, which utilizing a sentence parallel (bitext) corpus to learn the mapping from the source to the target language in the scene graph encoding space and decode sentences in the target language, and (ii) a cross-modal unsupervised feature mapping, which seeks to map the encoded scene graph features from image modality to language modality. We verify the effectiveness of our proposed method on the Chinese image caption generation task. The comparisons against several existing methods demonstrate the effectiveness of our approach., Accepted by AAAI-2022

3D printing is a disruptive technology that is a key driver of the new industrial revolution. Among the various 3D printing methods, direct-ink-writing (DIW) takes a viscous ink material, extrudes it through a nozzle, and deposits it layer-by-layer to create 3D objects. DIW is a versatile method that can print ceramics, polymers, metals, living cells, etc. Yet, the ink formulation is critical for the success of printing. One major challenge to operate the transition to Industry 4.0 is to educate laypersons on 3D printing, without the need to master physics and chemistry. In this paper, we propose a protocol to familiarize laypersons with ink formulation for DIW. Using this protocol, a clay-based ink was optimized and the best ink composition containing 48 wt% clay and 2.4 wt% bamboo fibers was used for printing. The experimental set-ups and details used in the work are easily available, cheap, sustainable, and safe, enabling its implementation in various settings from classrooms to workshops, without the need for specialized equipment. Nanyang Technological University Published version The authors acknowledge financial support from Nanyang Technological University, Start-up grant, and the URECA undergraduate program. The authors thank Alireza Javadian from Singapore ETH Centre for providing bamboo microfibers.

Research work in the field of offline Arabic handwriting recognition has seen an exponential growth during past decades. Despite much work dedicated to the recognition of handwritten Arabic text, there remains a lot to achieve in this regard. Though there exists a lot of work that is confined to the Arabic text, this paper presents an approach towards classifying and recognizing text written in one of the famous scripts of Arabic language i.e. Kufic script. The approach based on character segmentation does not perform well in recognizing Kufic text due to various complexities. The proposed system is based on word segmentation and employs a Histogram of Oriented Gradient (HOG) and Local Binary Pattern (LBP) feature extraction techniques. Later in the paper a comparison is given between the numerical results of proposed technique with previous Arabic text recognition techniques to show the effectiveness of present work. This approach yields effective results with 97.05% accuracy in recognizing the Arabic text written in Kufic script using Polynomial kernel of SVM classifier. Experimental results show that the proposed system for recognition of Kufic script performs better than the previous recognition systems for Arabic text.

Readability is a measure that associates a written text to a reader’s skill or grade level. Readability assessment is very important in the field of second or foreign language (L2) learning. The complexity of reading in some languages, such as Arabic, presents a great challenge to overcome and increases the need for such a measure before giving texts to a learner. In order to develop powerful tools that automate this choice, we must first choose the optimal feature set to be used in the development of such a tool. In this paper, we present an approach to automatically measure the readability of Arabic as a foreign language through a series of experiments. We begin by using a wide range of features plausibly relevant to readability, as found in the literature, and reduce them in subsequent experiments by eliminating features that appear to have little significance in readability prediction. Our objective is to keep the smallest set of features that gives good readability prediction accuracy based on three different corpora for learners of Arabic as a foreign language, annotated with five difficulty levels. Our best L2 readability accuracy result is 86.15%.

This paper studies the performance of greedy matching algorithms on bipartite graphs [Formula: see text]. We focus primarily on three classical algorithms: [Formula: see text], which sequentially selects random edges from [Formula: see text]; [Formula: see text], which sequentially matches random vertices in [Formula: see text] to random neighbors; and [Formula: see text], which generates a random priority order over vertices in [Formula: see text] and then sequentially matches random vertices in [Formula: see text] to their highest-priority remaining neighbor. Prior work has focused on identifying the worst-case approximation ratio for each algorithm. This guarantee is highest for [Formula: see text] and lowest for [Formula: see text]. Our work instead studies the average performance of these algorithms when the edge set [Formula: see text] is random. Our first result compares [Formula: see text] and [Formula: see text] and shows that on average, [Formula: see text] produces more matches. This result holds for finite graphs (in contrast to previous asymptotic results) and also applies to “many to one” matching in which each vertex in [Formula: see text] can match with multiple vertices in [Formula: see text]. Our second result compares [Formula: see text] and [Formula: see text] and shows that the better worst-case guarantee of [Formula: see text] does not translate into better average performance. In “one to one” settings where each vertex in [Formula: see text] can match with only one vertex in [Formula: see text], the algorithms result in the same number of matches. When each vertex in [Formula: see text] can match with two vertices in [Formula: see text] produces more matches than [Formula: see text].

The Convex Hull Membership (CHM) tests whether \( p \in conv(S) \) , where p and the n points of S lie in \( \mathbb { R}^m \) . CHM finds applications in Linear Programming, Computational Geometry, and Machine Learning. The Triangle Algorithm (TA), previously developed, in \( O(1/\varepsilon ^2) \) iterations computes \( p^{\prime } \in conv(S) \) , either an \( \varepsilon \) - approximate solution , or a witness certifying \( p \not\in conv(S) \) . We first prove the equivalence of exact and approximate versions of CHM and Spherical -CHM, where \( p=0 \) and \( \Vert v\Vert =1 \) for each v in S . If for some \( M \ge 1 \) every non-witness with \( \Vert p^{\prime }\Vert \gt \varepsilon \) admits \( v \in S \) satisfying \( \Vert p^{\prime } - v\Vert \ge \sqrt {1+\varepsilon /M} \) , we prove the number of iterations improves to \( O(M/\varepsilon) \) and \( M \le 1/\varepsilon \) always holds. Equivalence of CHM and Spherical-CHM implies Minimum Enclosing Ball (MEB) algorithms can be modified to solve CHM. However, we prove \( (1+ \varepsilon) \) -approximation in MEB is \( \Omega (\sqrt {\varepsilon }) \) -approximation in Spherical-CHM. Thus, even \( O(1/\varepsilon) \) iteration MEB algorithms are not superior to Spherical-TA. Similar weakness is proved for MEB core sets. Spherical-TA also results a variant of the All Vertex Triangle Algorithm (AVTA) for computing all vertices of \( conv(S) \) . Substantial computations on distinct problems demonstrate that TA and Spherical-TA generally achieve superior efficiency over algorithms such as Frank–Wolfe, MEB, and LP-Solver.

Writing is a long process; therefore, students need to do some steps to write, beginning from the considerations of choosing a good topic till writing a final copy, includedto review and to revise again and again, from time to time. Peer and self editing strategies are social and metacognitive strategies used in the steps of sharing, revising, and editing in writing. The aim of writing this article is to see how peer and self editing strategies are able to improve students’ writing skill. Classroom action research design was used and 64 students were taken as subjects of the research. The instruments used were peer editing worksheet, self editing worksheet, and test sheet. Data analysis method used was based on the procedures of planning, acting, observing, and reflecting phases. The research results showed that there were improvementsin all elements of writing: the quality of format, punctuation and mechanics, content, organization, and grammar and sentence structure.Based on the research results shown and the criteria of success determined, it can be concluded that peer and self editing strategies are able to improve students’ writing skill.

In this work, we present a hybrid image and document filing system that we have built. When a user wants to store a file in the system, it is processed to generate tags using an appropriate open-source machine learning system. Presently, we use OpenCV and Tesseract OCR for tagging files. OpenCV recognizes objects in the images and TesserAct recognizes text in the image. An image file is processed for object recognition using OpenCV as well for text/captions process using TesserAct, which are used for tagging the file. All other files are processed using Tesseract only for generating tags. The user can also enter their own tags. A database system has been built that stores tags and the image path. Every file is stored with its owner identification and it is time-stamped. The system has a client-server architecture and can be used for storing and retrieving a large number of files. This is a highly scalable system.

Recently, the emergence of the digital language division and the availability of cross-lingual benchmarks make researches of cross-lingual texts more popular. However, the performance of existing methods based on mapping relation are not good enough, because sometimes the structures of language spaces are not isomorphic. Besides, polysemy makes the extraction of interaction features hard. For cross-lingual word embedding, a model named Cross-lingual Word Embedding Space Based on Pseudo Corpus (CWE-PC) is proposed to obtain cross-lingual and multilingual word embedding. For cross-lingual sentence pair interaction feature capture, a Cross-language Feature Capture Based on Similarity Matrix (CFC-SM) model is built to extract cross-lingual interaction features. ELMo pretrained model and multiple layer convolution are used to alleviate polysemy and extract interaction features. These models are evaluated on multiple language pairs and results show that they outperform the state-of-the-art cross-lingual word embedding methods.

With the rapid development of electronic information technology and Internet technology, people's ability to generate and collect data is also increasing. With the rapid development of international exchanges, the number of literary translation texts has also increased dramatically. The information contained in the huge data of literary translation texts is huge, but these data are disorganized at this stage. Therefore, the classification of literary translation texts has become the key to efficient management of translated text information. Literary translation text classification is the process of classifying a given text as one or several of several predetermined text categories according to the content of the text. As one of the key steps in processing huge amounts of text data, text classification is generally regarded as the orderly organization of text sets, that is, grouping similar and related texts together. In this way, the problem of information clutter can be solved to a greater extent, and the efficiency of users' discovery, filtering, and analysis of text information resources can be effectively improved. At present, the basis of text classification is mainly based on the characteristics of words in the article, to analyze the correlation between words and categories. This approach ignores information such as word order and collocations in literary translation texts. To solve this problem, this paper introduces the distributed incremental sequence data mining algorithm into the classification of literary translation texts. This method can fully mine the features of syntactic order and other features based on considering the words and phrasing characteristics of articles in different application fields. The text classification effect is strengthened by discovering more effective information. The experimental results show that the method can improve the classification performance of literary translation texts.

With the rapid development of information collection technology and natural language processing technology, the construction of English-Chinese bilingual parallel corpus has developed rapidly. The scale of corpus and related technology have a large research space; and how to obtain effective data and knowledge from massive resources, in order to better serve the basic and applied research, is becoming a trend. Based on the research of parallel bilingual corpora at home and abroad, this article extracts the text features of medical English and constructs English-Chinese bilingual corpora with different levels aligned. Based on the statistical analysis of the distribution characteristics of phrase structures and the acquisition of characteristic knowledge, an English-Chinese bilingual translation model is constructed based on the bilingual corpus, and then the phrase structure knowledge in English and Chinese sentences is extracted from the data-driven English-Chinese bilingual corpus through the model. The results show that the accuracy of the test set is 91.63% and the F value is 90.05% under the condition of keeping the recall rate stable. The accuracy of the text structure features has been significantly improved, and the expected effect has been achieved through the test.

Historical archives provide invaluable insights into societies of the past, including social networks. However, the required amount of traditional archival work makes historical network studies usually small-scaled. We consider the problem of processing a large corpus of unstructured textual information to extract network data. The corpus consists of almost 170,000 documents of administrative correspondence of the Portuguese Empire, from 1610 to 1833, catalogued in the Portuguese Overseas Archives of Lisbon. Our contribution is twofold: the method and the result. Firstly, grounded in the review of manual, semi-manual and automatic methods of network data extraction from natural language corpora, we propose and demonstrate an approach using modern natural language processing algorithms. This approach tries to mimic traditional archivist’s coding practices and is applicable to large corpora of texts, for which manual coding is infeasible because of scale. We believe our approach is generic and adaptable to other substantive contexts, languages, and types of historical archives. Secondly, the dataset created is rich in additional information such as occupation, administrative affiliation, and geographical location of senders and recipients. We provide a preliminary network analysis suggesting that the dataset is an attractive material for historians and social network researchers for addressing research questions about the political and social evolution of the early modern Portuguese Empire, spanning the reign of seven Portuguese monarchs.

According to a recent Deloitte study, the COVID-19 pandemic continues to place a huge strain on the global health care sector. Covid-19 has also catalysed digital transformation across the sector for improving operational efficiencies. As a result, the amount of digitally stored patient data such as discharge letters, scan images, test results or free text entries by doctors has grown significantly. In 2020, 2314 exabytes of medical data was generated globally. This medical data does not conform to a generic structure and is mostly in the form of unstructured digitally generated or scanned paper documents stored as part of a patient’s medical reports. This unstructured data is digitised using Optical Character Recognition (OCR) process. A key challenge here is that the accuracy of the OCR process varies due to the inability of current OCR engines to correctly transcribe scanned or handwritten documents in which text may be skewed, obscured or illegible. This is compounded by the fact that processed text is comprised of specific medical terminologies that do not necessarily form part of general language lexicons. The proposed work uses a deep neural network based self-supervised pre-training technique: Robustly Optimized Bidirectional Encoder Representations from Transformers (RoBERTa) that can learn to predict hidden (masked) sections of text to fill in the gaps of non-transcribable parts of the documents being processed. Evaluating the proposed method on domain-specific datasets which include real medical documents, shows a significantly reduced word error rate demonstrating the effectiveness of the approach.

Let [Formula: see text] be the set of connected unicyclic graphs of order [Formula: see text] and girth [Formula: see text]. Let [Formula: see text] be obtained from a cycle [Formula: see text] (in an anticlockwise direction) by identifying [Formula: see text] with the root of a rooted tree [Formula: see text] of order [Formula: see text] for each [Formula: see text], where [Formula: see text] and [Formula: see text]. In this note, the graph with the minimal least eigenvalue (and the graph with maximal spread) in [Formula: see text] is determined.

Let $n\geq 3$ be an integer and $d$ an odd square-free integer. We shall compute the rank of the $2$-class group of $L_{n,d}:=\mathbb{Q}(\zeta_{2^n},\sqrt{d})$, when all the prime divisors of $d$ are congruent to $\pm 3\pmod 8$ or $9\pmod{16}$., Comment: 9 pages

3D printing is called as desktop fabrication. It is a process of prototyping where by a structure is synthesized from a 3d model. The 3d model is stored in as a STL format and then forwarded to a 3D printer. It can use a good range of materials like ABS, PLA, and composites also .3D printing may be a rapidly developing and price optimized sort of rapid prototyping. The 3D printer prints the CAD design layer by layer forming a true object. 3D printing springs from inkjet desktop printers during which multiple deposit jets and therefore the printing material, layer by layer derived from the CAD 3D data. 3D printing significantly challenges production processes within the future. This type of printing is predicted to influence industries, like automotive, medical, education, equipment, consumer products industries and various businesses. Keywords: 3d printing, Rapid Prototyping, ABS, PLA

The dependence on people over technology has never been higher, to the point where deep learning and machine learning algorithms can conduct anything from object detection in images to adding sound to silent movies. Similarly, handwritten text recognition is a major field of research and development with a plethora of possibilities. Using this method, the system is taught to look for similarities as well as differences between diverse handwriting samples. This program turns a picture of a handwritten transcription into digital text. Convolution Neural Network (CNN) with the help of IAM databases are used on the proposed work to recognize the handwritten text. Our main goal is to integrate the aforementioned models, with their release times, in order to create the best text recognition possible, model. Keywords: Handwritten Text Recognition (HTR), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Connectionist Temporal Classification (CTC)

Let [Formula: see text] be a commutative ring with unity, [Formula: see text] be a unitary [Formula: see text]-module and [Formula: see text] be a simple connected graph. We examine different equivalence relations on subsets [Formula: see text], [Formula: see text] and [Formula: see text] of [Formula: see text], where [Formula: see text] is the set of full-annihilators, [Formula: see text] is the set of semi-annihilators and [Formula: see text] is the set of star-annihilators in [Formula: see text]. We prove that elements [Formula: see text] are neighborhood similar in the annihilating graph [Formula: see text] if and only if the submodules [Formula: see text] and [Formula: see text] of [Formula: see text] are equal. We study the isomorphism of annihilating graphs arising from [Formula: see text] and the tensor product [Formula: see text], where [Formula: see text], [Formula: see text].

Let [Formula: see text] be a ring with non-zero identity. The unit graph of [Formula: see text], denoted by [Formula: see text], is an undirected graph with all the elements of [Formula: see text] as vertices and where distinct vertices [Formula: see text], [Formula: see text] are adjacent if and only if [Formula: see text] is a unit of [Formula: see text]. In this paper, we investigate the Wiener index and hyper-Wiener index of [Formula: see text] and explicitly determine their values.

Traditional searchable encryption schemes construct document vectors based on the term frequency-inverse document frequency (TF-IDF) model. Such vectors are not only high-dimensional and sparse but also ignore the semantic information of the documents. The Sentence Bidirectional Encoder Representations from Transformers (SBERT) model can be used to train vectors containing document semantic information to realize semantic-aware multi-keyword search. In this paper, we propose a privacy-preserving searchable encryption scheme based on the SBERT model. The SBERT model is used to train vectors containing the semantic information of documents, and these document vectors are then used as input to the Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) clustering algorithm. The HDBSCAN algorithm generates a soft cluster membership vector for each document. We treat each cluster as a topic, and the vector represents the probability that the document belongs to each topic. According to the clustering process in the schemes, the topic-term frequency-inverse topic frequency (TTF-ITF) model is proposed to generate keyword topic vectors. Through the SBERT model, searchable encryption scheme can achieve more precise semantic-aware keyword search. At the same time, the special index tree is used to improve search efficiency. The experimental results on real datasets prove the effectiveness of our scheme.

Researchers studying human interaction, such as conversation analysts, psychologists, and linguists, all rely on detailed transcriptions of language use. Ideally, these should include so-called paralinguistic features of talk, such as overlaps, prosody, and intonation, as they convey important information. However, creating conversational transcripts that include these features by hand requires substantial amounts of time by trained transcribers. There are currently no Speech to Text (STT) systems that are able to integrate these features in the generated transcript. To reduce the resources needed to create detailed conversation transcripts that include representation of paralinguistic features, we developed a program called GailBot. GailBot combines STT services with plugins to automatically generate first drafts of transcripts that largely follow the transcription standards common in the field of Conversation Analysis. It also enables researchers to add new plugins to transcribe additional features, or to improve the plugins it currently uses. We describe GailBot’s architecture and its use of computational heuristics and machine learning. We also evaluate its output in relation to transcripts produced by both human transcribers and comparable automated transcription systems. We argue that despite its limitations, GailBot represents a substantial improvement over existing dialogue transcription software.

This article describes the process of digitizing traditional methods of Bario salt extraction based on documentation and experiences during a field trip to Pa' Umor, Bario, Sarawak. The process of making salt is described in an orderly manner, beginning with the extraction of the salt water, and ending with the packing process. Bario salt is extracted from a salt spring by boiling the brine in a large pot until the salt forms a gray layer, and then collecting the salt from the bottom. This process is still practiced today. However, the production of Bario salt is not widely known because it is a lengthy and laborious process. Moreover, the conventional methods of information transfer are no longer relevant to current technological developments. Therefore, through an interdisciplinary and visual experience approach, all images are recorded in a digital documentation using the latest digital tools and then analyzed through the art of formalism. The result is a short video production and digital interactive poster called ID-Poster that uses the augmented reality application. It is hoped that this article will provide new ideas and visual insights that can help in promoting rural tourism. Keywords: Bario Salt; Visual Experience; Interdisciplinary; Digital Documentation; Rural Tourism

Let [Formula: see text] and [Formula: see text] count the 8-colored partitions of n into odd parts and the 2k-color partitions of n into odd parts, respectively, where the multiples of r can appear in 2k colors and the others can appear in k colors. In this paper, we find infinite families of congruences modulo powers of 2 for [Formula: see text], [Formula: see text], [Formula: see text], and [Formula: see text].

Let [Formula: see text] be the additive group of residue classes modulo [Formula: see text]. For any positive integers [Formula: see text] and [Formula: see text], let [Formula: see text] and [Formula: see text] denote the total number of subgroups and cyclic subgroups of the group [Formula: see text], respectively. Define [Formula: see text] In this paper, we study the asymptotic behavior of the functions [Formula: see text] and [Formula: see text].

An oriented graph is called singular or nonsingular according as its adjacency matrix is singular or nonsingular. In this note, by a new approach, we determine the singularity of oriented quasi-trees. The main results of Chen et al. [‘Singularity of oriented graphs from several classes’, Bull. Aust. Math. Soc.102(1) (2020), 7–14] follow as corollaries. Furthermore, we give a necessary condition for an oriented bipartite graph to be nonsingular. By applying this condition, we characterise nonsingular oriented bipartite graphs $B_{m,n}$ when $\min \{m,n\}\leq 3$ .

Foil stamping is one of the special printing techniques which plays an important role in the packaging design and attention of the customer. We discussed about the different types of foils available in the market and the different layers in the foils. Different concepts and terminology used in hot foiling process and factors like temperature, pressure, thickness of the foil, equipment and tools, and their contribution towards the machine efficiency. How the speed of the machine determines the consumption of foil. We also discussed the concept of single pass run and double pass run, reducing the consumption of electricity by using the relay timer for the heating zones of the machine. Studying and analyzing the consumption and reduction in it through the samples taken from different jobs. Analyzing how MUDAs TIMWOOD can help in increasing efficiency in the industry and how all the factors contribute towards the OEE of the machine.

We reside in the community that produce enormous amount of information. The magnitude of digitation in document is about transforming its movement into paperless form. The electronic document is secure with digital signature that bind with approval accepted by authorities and members of the organization. The evolving digitization use the document structure algorithm to add value tailored its services to develop as solution that improve that document flow of one university in Manila. The electronic document has the structure that can be partitioned in an order level and hierarchy pf physical elements and use the indexing to manage the document information. Documents are the most important source of knowledge and experience for any institution. Today, universities produce and use many documents in several types. These documents are paper or digital trails generated to coordinate and cooperate. Producing, sharing, copying, and archiving documents in a specific and strict document format. These documents are also needed for future decision-making based on analytics over historic data. Document Management System is a process or activity that starts from the making, receiving, collecting, organizing, controlling, maintaining, and storing. With this research, the documents from the creation, distribution, approval, modification, accessibility, recovery, storage, the printing of copies are controlled in one place. The system was developed to manage and create a centralized repository of documents. These documents can be retrieved and can be tracked online at anytime and anywhere.