Search results for: text processing

Authors: Beier Zhu, Rui Zhang, Qi Song

Abstract:

Text contained within fixed-layout documents can be of great semantic value and so requires a high localization accuracy, such as ID cards, invoices, cheques, and passports. Recently, algorithms based on deep convolutional networks achieve high performance on text detection tasks. However, for text localization in fixed-layout documents, such algorithms detect word bounding boxes individually, which ignores the layout information. This paper presents a novel architecture built on convolutional neural networks (CNNs). A global text localization network and a regional bounding-box regression network are introduced to tackle the problem in a coarse-to-fine manner. The text localization network simultaneously locates word bounding points, which takes the layout information into account. The bounding-box regression network inputs the features pooled from arbitrarily sized RoIs and refine the localizations. These two networks share their convolutional features and are trained jointly. A typical type of fixed-layout documents: ID cards, is selected to evaluate the effectiveness of the proposed system. These networks are trained on data cropped from nature scene images, and synthetic data produced by a synthetic text generation engine. Experiments show that our approach locates high accuracy word bounding boxes and achieves state-of-the-art performance.

Keywords: bounding box regression, convolutional networks, fixed-layout documents, text localization

Procedia PDF Downloads 165

Authors: Hsin-Yang Wang, K. M. A. Salam, Ying-Jia Lin, Daniel Tan, Tzu-Hsuan Chou, Hung-Yu Kao

Abstract:

Detecting user intent from natural language expression has a wide variety of use cases in different natural language processing applications. Recently few-shot training has a spike of usage on commercial domains. Due to the lack of significant sample features, the downstream task performance has been limited or leads to an unstable result across different domains. As a state-of-the-art method, the pre-trained BERT model gathering the sentence-level information from a large text corpus shows improvement on several NLP benchmarks. In this research, we are proposing a method to change multi-class classification tasks into binary classification tasks, then use the confidence score to rank the results. As a language model, BERT performs well on sequence data. In our experiment, we change the objective from predicting labels into finding the relations between words in sequence data. Our proposed method achieved 71.0% accuracy in the internal intent detection dataset and 63.9% accuracy in the HuffPost dataset. Acknowledgment: This work was supported by NCKU-B109-K003, which is the collaboration between National Cheng Kung University, Taiwan, and SoftBank Corp., Tokyo.

Keywords: OSML, BERT, text classification, one shot

Procedia PDF Downloads 78

Authors: Chayanika Hazarika Bordoloi

Abstract:

This paper is an attempt to work on a highly inflectional language called Assamese. This is also one of the national languages of India and very little has been achieved in terms of computational research. Building a language processing tool for a natural language is not very smooth as the standard and language representation change at various levels. This paper presents inflectional suffixes of Assamese verbs and how the statistical tools, along with linguistic features, can improve the tagging accuracy. Conditional random fields (CRF tool) was used to automatically tag and train the text data; however, accuracy was improved after linguistic featured were fed into the training data. Assamese is a highly inflectional language; hence, it is challenging to standardizing its morphology. Inflectional suffixes are used as a feature of the text data. In order to analyze the inflections of Assamese word forms, a list of suffixes is prepared. This list comprises suffixes, comprising of all possible suffixes that various categories can take is prepared. Assamese words can be classified into inflected classes (noun, pronoun, adjective and verb) and un-inflected classes (adverb and particle). The corpus used for this morphological analysis has huge tokens. The corpus is a mixed corpus and it has given satisfactory accuracy. The accuracy rate of the tagger has gradually improved with the modified training data.

Keywords: CRF, morphology, tagging, tagset

Procedia PDF Downloads 169

Authors: Rabi Mouhcine, Amrouch Mustapha, Mahani Zouhir, Mammass Driss

Abstract:

In this paper, we present a system for offline recognition cursive Arabic handwritten text based on Hidden Markov Models (HMMs). The system is analytical without explicit segmentation used embedded training to perform and enhance the character models. Extraction features preceded by baseline estimation are statistical and geometric to integrate both the peculiarities of the text and the pixel distribution characteristics in the word image. These features are modelled using hidden Markov models and trained by embedded training. The experiments on images of the benchmark IFN/ENIT database show that the proposed system improves recognition.

Keywords: recognition, handwriting, Arabic text, HMMs, embedded training

Procedia PDF Downloads 323

Authors: Mahmoud al-Ashiriy

Abstract:

This paper begins from the idea that the real history of literature is the history of its style. And since the rhyme –as known- is not merely the last letter, that have received a lot of analysis and investigation, but it is a collection of other values in addition to its different markings. This paper will explore the work of the connecting ha’ and its effectiveness in shaping the text of poetry, since it establishes vocal rhythms in addition to its role in indicating references through the pronoun, vertically through the poem through the sequence of its verses, also horizontally through what environs the one verse of sentences. If the scientific formation of prosody stopped at the possibilities and prohibitions; literary criticism and poetry studies should explore what is above the rule of aesthetic horizon of poetic effectiveness that varies from a text to another, a poet to another, a literary period to another, or from a poetic taste to another. Then the paper will explore this poetic essence in the texts of the famous Andalusian Poet Al-Husari Al-Qayrawani through his well-known Daliyya (a poem that its verses end with the letter D), and the role of the connecting ha’ in fulfilling its text and the accomplishment of its poetics, departing from this to the diwan (the big collection of poems) also as a higher text that surpasses the text/poem, and through what it represents of effectiveness the work of the phenomenon in accomplishing the poetics of the poem of Al-Husari Al-Qayrawani who is one of the pillars of Arabic poetics in Andalusia.

Keywords: Al-Husari Al-Qayrawni, poetics, rhyme, stylistics, science of the text

Procedia PDF Downloads 533

Authors: Jihee Jang, Seowon Yoon, Gaeun Son, Minjung Kang, Joon Yeon Choeh, Kee-Hong Choi

Abstract:

Background: Self-report multiple choice questionnaires have been widely utilized to quantitatively measure one’s personality and psychological constructs. Despite several strengths (e.g., brevity and utility), self-report multiple-choice questionnaires have considerable limitations in nature. With the rise of machine learning (ML) and Natural language processing (NLP), researchers in the field of psychology are widely adopting NLP to assess psychological constructs to predict human behaviors. However, there is a lack of connections between the work being performed in computer science and that psychology due to small data sets and unvalidated modeling practices. Aims: The current article introduces the study method and procedure of phase II, which includes the interview questions for the five-factor model (FFM) of personality developed in phase I. This study aims to develop the interview (semi-structured) and open-ended questions for the FFM-based personality assessments, specifically designed with experts in the field of clinical and personality psychology (phase 1), and to collect the personality-related text data using the interview questions and self-report measures on personality and psychological distress (phase 2). The purpose of the study includes examining the relationship between natural language data obtained from the interview questions, measuring the FFM personality constructs, and psychological distress to demonstrate the validity of the natural language-based personality prediction. Methods: The phase I (pilot) study was conducted on fifty-nine native Korean adults to acquire the personality-related text data from the interview (semi-structured) and open-ended questions based on the FFM of personality. The interview questions were revised and finalized with the feedback from the external expert committee, consisting of personality and clinical psychologists. Based on the established interview questions, a total of 425 Korean adults were recruited using a convenience sampling method via an online survey. The text data collected from interviews were analyzed using natural language processing. The results of the online survey, including demographic data, depression, anxiety, and personality inventories, were analyzed together in the model to predict individuals’ FFM of personality and the level of psychological distress (phase 2).

Keywords: personality prediction, psychological distress prediction, natural language processing, machine learning, the five-factor model of personality

Procedia PDF Downloads 54

Authors: Yassine Jamoussi, Ameni Youssfi, Henda Ben Ghezala

Abstract:

With the growing interest in social networking, the interaction of social actors evolved to a source of knowledge in which it becomes possible to perform context aware-reasoning. The information extraction from social networking especially Twitter and Facebook is one of the problems in this area. To extract text from social networking, we need several lexical features and large scale word clustering. We attempt to expand existing tokenizer and to develop our own tagger in order to support the incorrect words currently in existence in Facebook and Twitter. Our goal in this work is to benefit from the lexical features developed for Twitter and online conversational text in previous works, and to develop an extraction model for constructing a huge knowledge based on actions

Keywords: social networking, information extraction, part-of-speech tagging, natural language processing

Procedia PDF Downloads 276

Authors: Ming Liu, Chong Wu, Bingquan Liu, Lei Chen

Abstract:

Internet users have to face the massive amount of textual data every day. Organizing texts into categories can help users dig the useful information from large-scale text collection. Clustering, in fact, is one of the most promising tools for categorizing texts due to its unsupervised characteristic. Unfortunately, most of traditional clustering algorithms lose their high qualities on large-scale text collection. This situation mainly attributes to the high- dimensional vectors generated from texts. To effectively and efficiently cluster large-scale text collection, this paper proposes a vector reconstruction based clustering algorithm. Only the features that can represent the cluster are preserved in cluster’s representative vector. This algorithm alternately repeats two sub-processes until it converges. One process is partial tuning sub-process, where feature’s weight is fine-tuned by iterative process. To accelerate clustering velocity, an intersection based similarity measurement and its corresponding neuron adjustment function are proposed and implemented in this sub-process. The other process is overall tuning sub-process, where the features are reallocated among different clusters. In this sub-process, the features useless to represent the cluster are removed from cluster’s representative vector. Experimental results on the three text collections (including two small-scale and one large-scale text collections) demonstrate that our algorithm obtains high quality on both small-scale and large-scale text collections.

Keywords: vector reconstruction, large-scale text clustering, partial tuning sub-process, overall tuning sub-process

Procedia PDF Downloads 404

Authors: Kayode A. Olaniyi, Olabanji F. Omotoye, Adeola A. Ogunleye

Abstract:

The skew detection and correction form an important part of digital document analysis. This is because uncompensated skew can deteriorate document features and can complicate further document image processing steps. Efficient text document analysis and digitization can rarely be achieved when a document is skewed even at a small angle. Once the documents have been digitized through the scanning system and binarization also achieved, document skew correction is required before further image analysis. Research efforts have been put in this area with algorithms developed to eliminate document skew. Skew angle correction algorithms can be compared based on performance criteria. Most important performance criteria are accuracy of skew angle detection, range of skew angle for detection, speed of processing the image, computational complexity and consequently memory space used. The standard Hough Transform has successfully been implemented for text documentation skew angle estimation application. However, the standard Hough Transform algorithm level of accuracy depends largely on how much fine the step size for the angle used. This consequently consumes more time and memory space for increase accuracy and, especially where number of pixels is considerable large. Whenever the Hough transform is used, there is always a tradeoff between accuracy and speed. So a more efficient solution is needed that optimizes space as well as time. In this paper, an improved Hough transform (HT) technique that optimizes space as well as time to robustly detect document skew is presented. The modified algorithm of Hough Transform presents solution to the contradiction between the memory space, running time and accuracy. Our algorithm starts with the first step of angle estimation accurate up to zero decimal place using the standard Hough Transform algorithm achieving minimal running time and space but lacks relative accuracy. Then to increase accuracy, suppose estimated angle found using the basic Hough algorithm is x degree, we then run again basic algorithm from range between ±x degrees with accuracy of one decimal place. Same process is iterated till level of desired accuracy is achieved. The procedure of our skew estimation and correction algorithm of text images is implemented using MATLAB. The memory space estimation and process time are also tabulated with skew angle assumption of within 00 and 450. The simulation results which is demonstrated in Matlab show the high performance of our algorithms with less computational time and memory space used in detecting document skew for a variety of documents with different levels of complexity.

Keywords: hough-transform, skew-detection, skew-angle, skew-correction, text-document

Procedia PDF Downloads 126

Authors: Aishwarya Talapuru, Sri Silpa Padmanabhuni, B. Jyoshna

Abstract:

Cryptography helps in preventing threats to information security by providing various algorithms. This study introduces a new symmetric key encryption algorithm for information security which is linked with the "raagas" which means Indian traditional scale and pattern of music notes. This algorithm takes the plain text as input and starts its encryption process. The algorithm then randomly selects a raaga from the list of raagas that is assumed to be present with both sender and the receiver. The plain text is associated with the thus selected raaga and an intermediate cipher-text is formed as the algorithm converts the plain text characters into other characters, depending upon the rules of the algorithm. This intermediate code or cipher text is arranged in various patterns in three different rounds of encryption performed. The total number of rounds in the algorithm is equal to the multiples of 3. To be more specific, the outcome or output of the sequence of first three rounds is again passed as the input to this sequence of rounds recursively, till the total number of rounds of encryption is performed. The raaga selected by the algorithm and the number of rounds performed will be specified at an arbitrary location in the key, in addition to important information regarding the rounds of encryption, embedded in the key which is known by the sender and interpreted only by the receiver, thereby making the algorithm hack proof. The key can be constructed of any number of bits without any restriction to the size. A software application is also developed to demonstrate this process of encryption, which dynamically takes the plain text as input and readily generates the cipher text as output. Therefore, this algorithm stands as one of the strongest tools for information security.

Keywords: cipher text, cryptography, plaintext, raaga

Procedia PDF Downloads 261

Authors: Ganfeng Yu, Yuefeng Ma, Shanliang Yang

Abstract:

The word discovery is a key problem in text information retrieval technology. Methods in new word discovery tend to be closely related to words because they generally obtain new word results by analyzing words. With the popularity of social networks, individual netizens and online self-media have generated various network texts for the convenience of online life, including network words that are far from standard Chinese expression. How detect network words is one of the important goals in the field of text information retrieval today. In this paper, we integrate the word embedding model and clustering methods to propose a network word discovery framework based on sentence semantic similarity (S³-NWD) to detect network words effectively from the corpus. This framework constructs sentence semantic vectors through a distributed representation model, uses the similarity of sentence semantic vectors to determine the semantic relationship between sentences, and finally realizes network word discovery by the meaning of semantic replacement between sentences. The experiment verifies that the framework not only completes the rapid discovery of network words but also realizes the standard word meaning of the discovery of network words, which reflects the effectiveness of our work.

Keywords: text information retrieval, natural language processing, new word discovery, information extraction

Procedia PDF Downloads 61

Authors: ShyamKrishna Kirithivasan, Shreyas Battula, Aditi Soori, Richa Ramesh, Ramamoorthy Srinath

Abstract:

The human brain, among the most complex and mysterious aspects of the body, harbors vast potential for extensive exploration. Unraveling these enigmas, especially within neural perception and cognition, delves into the realm of neural decoding. Harnessing advancements in generative AI, particularly in Visual Computing, seeks to elucidate how the brain comprehends visual stimuli observed by humans. The paper endeavors to reconstruct human-perceived visual stimuli using Functional Magnetic Resonance Imaging (fMRI). This fMRI data is then processed through pre-trained deep-learning models to recreate the stimuli. Introducing a new architecture named LatentNeuroNet, the aim is to achieve the utmost semantic fidelity in stimuli reconstruction. The approach employs a Latent Diffusion Model (LDM) - Stable Diffusion v1.5, emphasizing semantic accuracy and generating superior quality outputs. This addresses the limitations of prior methods, such as GANs, known for poor semantic performance and inherent instability. Text conditioning within the LDM's denoising process is handled by extracting text from the brain's ventral visual cortex region. This extracted text undergoes processing through a Bootstrapping Language-Image Pre-training (BLIP) encoder before it is injected into the denoising process. In conclusion, a successful architecture is developed that reconstructs the visual stimuli perceived and finally, this research provides us with enough evidence to identify the most influential regions of the brain responsible for cognition and perception.

Keywords: BLIP, fMRI, latent diffusion model, neural perception.

Procedia PDF Downloads 42

Authors: Alev Atak

Abstract:

In this paper, we aim to create a financial sentiment index by investigating the company’s voluntary information disclosures. We retrieve structured content from BIST 100 companies’ financial reports for the period 1998-2018 and extract relevant financial information for sentiment analysis through Natural Language Processing. We measure strategy-related disclosures and their cross-sectional variation and classify report content into generic sections using synonym lists divided into four main categories according to their liquidity risk profile, risk positions, intra-annual information, and exposure to risk. We use Word Error Rate and Cosin Similarity for comparing and measuring text similarity and derivation in sets of texts. In addition to performing text extraction, we will provide a range of text analysis options, such as the readability metrics, word counts using pre-determined lists (e.g., forward-looking, uncertainty, tone, etc.), and comparison with reference corpus (word, parts of speech and semantic level). Therefore, we create an adequate analytical tool and a financial dictionary to depict the importance of granular financial disclosure for investors to identify correctly the risk-taking behavior and hence make the aggregated effects traceable.

Keywords: financial sentiment, machine learning, information disclosure, risk

Procedia PDF Downloads 70

Authors: Vaidehi Murarka, Sneha Mehta, Dishant Upadhyay

Abstract:

Our project topic is “Alphabet Recognition using pixel probability distribution”. The project uses techniques of Image Processing and Machine Learning in Computer Vision. Alphabet recognition is the mechanical or electronic translation of scanned images of handwritten, typewritten or printed text into machine-encoded text. It is widely used to convert books and documents into electronic files etc. Alphabet Recognition based OCR application is sometimes used in signature recognition which is used in bank and other high security buildings. One of the popular mobile applications includes reading a visiting card and directly storing it to the contacts. OCR's are known to be used in radar systems for reading speeders license plates and lots of other things. The implementation of our project has been done using Visual Studio and Open CV (Open Source Computer Vision). Our algorithm is based on Neural Networks (machine learning). The project was implemented in three modules: (1) Training: This module aims “Database Generation”. Database was generated using two methods: (a) Run-time generation included database generation at compilation time using inbuilt fonts of OpenCV library. Human intervention is not necessary for generating this database. (b) Contour–detection: ‘jpeg’ template containing different fonts of an alphabet is converted to the weighted matrix using specialized functions (contour detection and blob detection) of OpenCV. The main advantage of this type of database generation is that the algorithm becomes self-learning and the final database requires little memory to be stored (119kb precisely). (2) Preprocessing: Input image is pre-processed using image processing concepts such as adaptive thresholding, binarizing, dilating etc. and is made ready for segmentation. “Segmentation” includes extraction of lines, words, and letters from the processed text image. (3) Testing and prediction: The extracted letters are classified and predicted using the neural networks algorithm. The algorithm recognizes an alphabet based on certain mathematical parameters calculated using the database and weight matrix of the segmented image.

Keywords: contour-detection, neural networks, pre-processing, recognition coefficient, runtime-template generation, segmentation, weight matrix

Procedia PDF Downloads 357

Authors: A. M. John-Otumu, M. M. Rahman, O. C. Nwokonkwo, M. C. Onuoha

Abstract:

Online social media networks have long served as a primary arena for group conversations, gossip, text-based information sharing and distribution. The use of natural language processing techniques for text classification and unbiased decision-making has not been far-fetched. Proper classification of this textual information in a given context has also been very difficult. As a result, we decided to conduct a systematic review of previous literature on sentiment classification and AI-based techniques that have been used in order to gain a better understanding of the process of designing and developing a robust and more accurate sentiment classifier that can correctly classify social media textual information of a given context between hate speech and inverted compliments with a high level of accuracy by assessing different artificial intelligence techniques. We evaluated over 250 articles from digital sources like ScienceDirect, ACM, Google Scholar, and IEEE Xplore and whittled down the number of research to 31. Findings revealed that Deep learning approaches such as CNN, RNN, BERT, and LSTM outperformed various machine learning techniques in terms of performance accuracy. A large dataset is also necessary for developing a robust sentiment classifier and can be obtained from places like Twitter, movie reviews, Kaggle, SST, and SemEval Task4. Hybrid Deep Learning techniques like CNN+LSTM, CNN+GRU, CNN+BERT outperformed single Deep Learning techniques and machine learning techniques. Python programming language outperformed Java programming language in terms of sentiment analyzer development due to its simplicity and AI-based library functionalities. Based on some of the important findings from this study, we made a recommendation for future research.

Keywords: artificial intelligence, natural language processing, sentiment analysis, social network, text

Procedia PDF Downloads 91

Authors: Faiza Hussain, Usman Qamar

Abstract:

Synonym-based searching is recognized to be a complicated problem as text mining from unstructured data of web is challenging. Finding useful information which matches user need from bulk of web pages is a cumbersome task. In this paper, a novel and practical synonym retrieval technique is proposed for addressing this problem. For replacement of semantics, user intent is taken into consideration to realize the technique. Parts-of-Speech tagging is applied for pattern generation of the query and a thesaurus for this experiment was formed and used. Comparison with Non-Context Based Searching, Context Based searching proved to be a more efficient approach while dealing with linguistic semantics. This approach is very beneficial in doing intent based searching. Finally, results and future dimensions are presented.

Keywords: natural language processing, text mining, information retrieval, parts-of-speech tagging, grammar, semantics

Procedia PDF Downloads 279

Authors: Amirreza Karami, Hawraa Nafea Hameed Alzouwain, Freddie A. Bowles

Abstract:

This study investigates the effects of watching text-relevant video segments with/without subtitles on vocabulary development of Arabic as a Foreign Language (AFL) learners. The participants of the study were assigned to two groups: one control group and one experimental group. The control group received no video-based instruction while the experimental group watched a text-relevant video segment in three stages: pre, while, and post-instruction. The preliminary results of the pre-test and post-test show that watching text-relevant video segments through following a pre-while-post procedure can help the vocabulary development of AFL learners more than non-video-based instruction.

Keywords: text-relevant video segments, vocabulary development, Arabic as a Foreign Language, AFL, pre-while-post instruction

Procedia PDF Downloads 135

Authors: Yangze Lan, Ruihua Xv, Feng Zhou, Yijia Shan, Longhao Zhang, Qinghui Xv

Abstract:

Receiving and dispatching trains is an important part of railroad organization, and the risky evaluation of operating personnel is still reflected by scores, lacking further excavation of wrong answers and operating accidents. With natural language processing (NLP) technology, this study extracts the keywords and key phrases of 40 relevant risk events about receiving and dispatching trains and reclassifies the risk events into 8 categories, such as train approach and signal risks, dispatching command risks, and so on. Based on the historical risk data of personnel, the K-Means clustering method is used to classify the risk level of personnel. The result indicates that the high-risk operating personnel need to strengthen the training of train receiving and dispatching operations towards essential trains and abnormal situations.

Keywords: receiving and dispatching trains, natural language processing, risk evaluation, K-means clustering

Procedia PDF Downloads 42

Authors: Fatima Al-Aswadi, Chan Yong

Abstract:

With the large volume of unstructured data that increases day by day on the web, the motivation of representing the knowledge in this data in the machine processable form is increased. Ontology is one of the major cornerstones of representing the information in a more meaningful way on the semantic Web. The goal of Ontology learning from text is to elicit and represent domain knowledge in the machine readable form. This paper aims to give a follow-up review on the ontology learning systems from text and some of their defects. Furthermore, it discusses how far the ontology learning process will enhance in the future.

Keywords: concept discovery, deep learning, ontology learning, semantic relation, semantic web

Procedia PDF Downloads 478

Authors: Aiman Elragig, Hanan Dreiwi, Dung Ly, Idriss Elmabrook

Abstract:

This paper highlights a new approach to look at online principle components analysis (OPCA). Given a data matrix X ∈ R,^m x n we characterise the online updates of its covariance as a matrix perturbation problem. Up to the principle components, it turns out that online updates of the batch PCA can be captured by symmetric matrix perturbation of the batch covariance matrix. We have shown that as n→ n0 >> 1, the batch covariance and its update become almost similar. Finally, utilize our new setup of online updates to find a bound on the angle distance of the principle components of X and its update.

Keywords: online data updates, covariance matrix, online principle component analysis, matrix perturbation

Procedia PDF Downloads 167

Authors: Sarah Werner, Michael J. Pritchard

Abstract:

From pilots to engineers, the skills development within the aerospace industry is exceptionally broad. Employers often struggle with finding the right mixture of qualified skills to fill their organizational demands. This effort to find qualified talent is further complicated by the industrial delineation between two key areas: aviation and aerospace. In a broad sense, the aerospace industry overlaps with the aviation industry. In turn, the aviation industry is a smaller sector segment within the context of the broader definition of the aerospace industry. Furthermore, it could be conceptually argued that -in practice- there is little distinction between these two sectors (i.e., aviation and aerospace). However, through our unstructured text analysis of over 6,000 job listings captured, our team found a clear delineation between aviation-related jobs and aerospace-related jobs. Using techniques in natural language processing, our research identifies an integrated workforce skill pattern that clearly breaks between these two sectors. While the aviation sector has largely maintained its need for pilots, mechanics, and associated support personnel, the staffing needs of the aerospace industry are being progressively driven by integrative engineering needs. Increasingly, this is leading many aerospace-based organizations towards the acquisition of 'system level' staffing requirements. This research helps to better align higher educational institutions with the current industrial staffing complexities within the broader aerospace sector.

Keywords: aerospace industry, job demand, text mining, workforce development

Procedia PDF Downloads 234

Authors: Aleksandra Jonas, Aleksandra Gronowska, Maciej Ścigacz, Szymon Jadczak

Abstract:

Exact Data is a smart tool which helps with meaningful marketing content creation. It helps marketers achieve this by analyzing the text of an advertisement before and after its publication on social media sites like Facebook or Instagram. In our research we focus on four areas of natural language processing (NLP): grammar correction, sentiment analysis, irony detection and advertisement interpretation. Our research has identified a considerable lack of NLP tools for the Polish language, which specifically aid online marketers. In light of this, our research team has set out to create a robust and versatile NLP tool for the Polish language. The primary objective of our research is to develop a tool that can perform a range of language processing tasks in this language, such as sentiment analysis, text classification, text correction and text interpretation. Our team has been working diligently to create a tool that is accurate, reliable, and adaptable to the specific linguistic features of Polish, and that can provide valuable insights for a wide range of marketers needs. In addition to the Polish language version, we are also developing an English version of the tool, which will enable us to expand the reach and impact of our research to a wider audience. Another area of focus in our research involves tackling the challenge of the limited availability of linguistically diverse corpora for non-English languages, which presents a significant barrier in the development of NLP applications. One approach we have been pursuing is the translation of existing English corpora, which would enable us to use the wealth of linguistic resources available in English for other languages. Furthermore, we are looking into other methods, such as gathering language samples from social media platforms. By analyzing the language used in social media posts, we can collect a wide range of data that reflects the unique linguistic characteristics of specific regions and communities, which can then be used to enhance the accuracy and performance of NLP algorithms for non-English languages. In doing so, we hope to broaden the scope and capabilities of NLP applications. Our research focuses on several key NLP techniques including sentiment analysis, text classification, text interpretation and text correction. To ensure that we can achieve the best possible performance for these techniques, we are evaluating and comparing different approaches and strategies for implementing them. We are exploring a range of different methods, including transformers and convolutional neural networks (CNNs), to determine which ones are most effective for different types of NLP tasks. By analyzing the strengths and weaknesses of each approach, we can identify the most effective techniques for specific use cases, and further enhance the performance of our tool. Our research aims to create a tool, which can provide a comprehensive analysis of advertising effectiveness, allowing marketers to identify areas for improvement and optimize their advertising strategies. The results of this study suggest that a smart tool for advertisement analysis can provide valuable insights for businesses seeking to create effective advertising campaigns.

Keywords: NLP, AI, IT, language, marketing, analysis

Procedia PDF Downloads 52

Authors: Joy Aworo-Okoroh

Abstract:

Literary texts are mirrors of a real-life situation. Thus, authors choose the linguistic items that would best encode their intended meanings and messages. However, words mean more than they seem. The meaning of words is not static rather, it is dynamic as they constantly enter into relationships within a context. Literary texts can only be meaningful if all pragmatic cues are identified and interpreted. Drawing upon Teun Van Djik's theory of local pragmatic coherence, it is established that words enter into relations in a text and these relations account for sequential speech acts in the texts. Comprehension of the text is dependent on the interpretation of these relations.To show the relevance of pragmatic coherence in literary text analysis, ten conversations were selected in Americanah in order to give a clear idea of the pragmatic relations used. The conversations were analysed, identifying the speech act and epistemic relations inherent in them. A subtle analysis of the structure of the conversations was also carried out. It was discovered that justification is the most commonly used relation and the meaning of the text is dependent on the interpretation of these instances' pragmatic coherence. The study concludes that to effectively teach literature in English, pragmatic coherence should be incorporated as words mean more than they say.

Keywords: pragmatic coherence, epistemic coherence, speech act, Americanah

Procedia PDF Downloads 107

Authors: Mariam Matiashvili

Abstract:

Argumentation is an integral part of our daily communications - formal or informal. Argumentative reasoning, techniques, and language tools are used both in personal conversations and in the business environment. Verbalization of the opinions requires the use of extraordinary syntactic-pragmatic structural quantities - arguments that add credibility to the statement. The study of argumentative structures allows us to identify the linguistic features that make the text argumentative. Knowing what elements make up an argumentative text in a particular language helps the users of that language improve their skills. Also, natural language processing (NLP) has become especially relevant recently. In this context, one of the main emphases is on the computational processing of argumentative texts, which will enable the automatic recognition and analysis of large volumes of textual data. The research deals with the linguistic analysis of the argumentative structures of Georgian political speeches - particularly the linguistic structure, characteristics, and functions of the parts of the argumentative text - claims, support, and attack statements. The research aims to describe the linguistic cues that give the sentence a judgmental/controversial character and helps to identify reasoning parts of the argumentative text. The empirical data comes from the Georgian Political Corpus, particularly TV debates. Consequently, the texts are of a dialogical nature, representing a discussion between two or more people (most often between a journalist and a politician). The research uses the following approaches to identify and analyze the argumentative structures Lexical Classification & Analysis - Identify lexical items that are relevant in argumentative texts creating process - Creating the lexicon of argumentation (presents groups of words gathered from a semantic point of view); Grammatical Analysis and Classification - means grammatical analysis of the words and phrases identified based on the arguing lexicon. Argumentation Schemas - Describe and identify the Argumentation Schemes that are most likely used in Georgian Political Speeches. As a final step, we analyzed the relations between the above mentioned components. For example, If an identified argument scheme is “Argument from Analogy”, identified lexical items semantically express analogy too, and they are most likely adverbs in Georgian. As a result, we created the lexicon with the words that play a significant role in creating Georgian argumentative structures. Linguistic analysis has shown that verbs play a crucial role in creating argumentative structures.

Keywords: georgian, argumentation schemas, argumentation structures, argumentation lexicon

Procedia PDF Downloads 48

Authors: Liu Si, Wang Chunmei, Liu Huangmei

Abstract:

A prominent component of the semantic versus pragmatic debate, scalar implicature (SI) has been gaining great attention ever since it was proposed by Horn. The constant debate is between the structural and pragmatic approach. The former claims that generation of SI is costless, automatic, and dependent mostly on the structural properties of sentences, whereas the latter advocates both that such generation is largely dependent upon context, and that the process is costly. Many experiments, among which Katsos’s text comprehension experiments are influential, have been designed and conducted in order to verify their views, but the results are not conclusive. Besides, most of the experiments were conducted in English language materials. Katsos conducted one off-line and three on-line text comprehension experiments, in which the previous shortcomings were addressed on a certain extent and the conclusion was in favor of the pragmatic approach. We intend to test the results of Katsos’s experiment in Chinese scalar implicature. Four experiments in both off-line and on-line conditions to examine the generation and response time of SI in Chinese "yixie" (some) and "quanbu (dou)" (all) will be conducted in order to find out whether the structural or the pragmatic approach could be sustained. The study mainly aims to answer the following questions: (1) Can SI be generated in the upper- and lower-bound contexts as Katsos confirmed when Chinese language materials are used in the experiment? (2) Can SI be first generated, then cancelled as default view claimed or can it not be generated in a neutral context when Chinese language materials are used in the experiment? (3) Is SI generation costless or costly in terms of processing resources? (4) In line with the SI generation process, what conclusion can be made about the cognitive processing model of language meaning? Is it a parallel model or a linear model? Or is it a dynamic and hierarchical model? According to previous theoretical debates and experimental conflicts, presumptions could be made that SI, in Chinese language, might be generated in the upper-bound contexts. Besides, the response time might be faster in upper-bound than that found in lower-bound context. SI generation in neutral context might be the slowest. At last, a conclusion would be made that the processing model of SI could not be verified by either absolute structural or pragmatic approaches. It is, rather, a dynamic and complex processing mechanism, in which the interaction of language forms, ad hoc context, mental context, background knowledge, speakers’ interaction, etc. are involved.

Keywords: cognitive linguistics, pragmatics, scalar implicture, experimental study, Chinese language

Procedia PDF Downloads 338

Authors: Siti Azrina B. A. Aziz, Siti Hafizah A. Hamid

Abstract:

New approaches to analyze and visualize data stream in real-time basis is important in making a prompt decision by the decision maker. Financial market trading and surveillance, large-scale emergency response and crowd control are some example scenarios that require real-time analytic and data visualization. This situation has led to the development of techniques and tools that support humans in analyzing the source data. With the emergence of Big Data and social media, new techniques and tools are required in order to process the streaming data. Today, ranges of tools which implement some of these functionalities are available. In this paper, we present chronological evolution evaluation of technologies for supporting of real-time analytic and visualization of the data stream. Based on the past research papers published from 2002 to 2014, we gathered the general information, main techniques, challenges and open issues. The techniques for streaming text visualization are identified based on Text Visualization Browser in chronological order. This paper aims to review the evolution of streaming text visualization techniques and tools, as well as to discuss the problems and challenges for each of identified tools.

Keywords: information visualization, visual analytics, text mining, visual text analytics tools, big data visualization

Procedia PDF Downloads 373

Authors: Tadesse Anberbir, Bankole Felix, Tomio Takara

Abstract:

In the development of a text-to-speech synthesizer, automatic derivation of correct pronunciation from the grapheme form of a text is a central problem. Particularly deriving phonological features which are not shown in orthography is challenging. In the Amharic language, geminates and epenthetic vowels are very crucial for proper pronunciation, but neither is shown in orthography. In this paper, to proposed and integrated a morphological analyzer into an Amharic Text-to-Speech system, mainly to predict geminates and epenthetic vowel positions and prepared a duration modeling method. Amharic Text-to-Speech system (AmhTTS) is a parametric and rule-based system that adopts a cepstral method and uses a source filter model for speech production and a Log Magnitude Approximation (LMA) filter as the vocal tract filter. The naturalness of the system after employing the duration modeling was evaluated by sentence listening test, and we achieved an average Mean Opinion Score (MOS) 3.4 (68%), which is moderate. By modeling the duration of geminates and controlling the locations of epenthetic vowel, we are able to synthesize good quality speech. Our system is mainly suitable to be customized for other Ethiopian languages with limited resources.

Keywords: amharic, gemination, Speech synthesis, morphology, epenthesis

Procedia PDF Downloads 55

Authors: Trisha Malhotra

Abstract:

Sentiment analysis is a recent field of study that computationally assesses the emotional nature of a body of text. To assess its test-validity, sentiment analysis was carried out on the emotional corpus of text from a personal 15-day mood diary. Self-reported mood scores varied more or less accurately with daily mood evaluation score given by the software. On further assessment, it was found that while sentiment analysis was good at assessing ‘global’ mood, it was not able to ‘locally’ identify and differentially score synonyms of various emotional words. It is further critiqued for treating the intensity of an emotion as universal across cultures. Finally, the software is shown not to account for emotional complexity in sentences by treating emotions as strictly positive or negative. Hence, it is posited that a better output could be two (positive and negative) affect scores for the same body of text.

Keywords: analysis, data, diary, emotions, mood, sentiment

Procedia PDF Downloads 238

Authors: Azyz Sharafy

Abstract:

3D Text Toys is an innovative and creative approach that utilizes 3D text objects to enhance creativity, literacy, and basic learning in an enjoyable and gamified manner. By using 3D Text Toys, children can develop their creativity, visually learn words and texts, and apply their artistic talents within their creative abilities. This process incorporates haptic engagement with 2D and 3D texts, word building, and mechanical construction of everyday objects, thereby facilitating better word and text retention. The concept involves constructing visual objects made entirely out of 3D text/words, where each component of the object represents a word or text element. For instance, a bird can be recreated using words or text shaped like its wings, beak, legs, head, and body, resulting in a 3D representation of the bird purely composed of text. This can serve as an art piece or a learning tool in the form of a 3D text toy. These 3D text objects or toys can be crafted using natural materials such as leaves, twigs, strings, or ropes, or they can be made from various physical materials using traditional crafting tools. Digital versions of these objects can be created using 2D or 3D software on devices like phones, laptops, iPads, or computers. To transform digital designs into physical objects, computerized machines such as CNC routers, laser cutters, and 3D printers can be utilized. Once the parts are printed or cut out, students can assemble the 3D texts by gluing them together, resulting in natural or everyday 3D text objects. These objects can be painted to create artistic pieces or text toys, and the addition of wheels can transform them into moving toys. One of the significant advantages of this visual and creative object-based learning process is that students not only learn words but also derive enjoyment from the process of creating, painting, and playing with these objects. The ownership and creation process further enhances comprehension and word retention. Moreover, for individuals with learning disabilities such as dyslexia, ADD (Attention Deficit Disorder), or other learning difficulties, the visual and haptic approach of 3D Text Toys can serve as an additional creative and personalized learning aid. The application of 3D Text Toys extends to both the English language and any other global written language. The adaptation and creative application may vary depending on the country, space, and native written language. Furthermore, the implementation of this visual and haptic learning tool can be tailored to teach foreign languages based on age level and comprehension requirements. In summary, this creative, haptic, and visual approach has the potential to serve as a global literacy tool.

Keywords: 3D text toys, creative, artistic, visual learning for world literacy

Procedia PDF Downloads 34

Authors: Ibrahim Hassan

Abstract:

Motion typography is one of the most important types of visual communication based on display. Through the digital display media, we can control the text properties (size, direction, thickness, color, etc.). The use of motion typography in visual communication made it have several images. We need to adjust the terminology and clarify the different differences between them, so relying on the word motion typography -considered a general term- is not enough to separate the different communicative functions of the moving text. In this paper, we discuss the different effects of motion typography on Arabic writing and how we can achieve harmony between the movement and the letterform, and we will, during our experiments, present a new type of text movement.

Keywords: Arabic typography, motion typography, kinetic typography, fluid typography, temporal typography

Procedia PDF Downloads 122