Speech Tagging Research Articles

ALGORITHM FOR COMPREHENSIBILITY EVALUATION OF BUSINESS PROCESS MODELS USING NATURAL LANGUAGE PROCESSING

This research paper is devoted to solving the problem of assessing the quality of business process models, in particular, evaluating the comprehensibility of text labels in these models. The purpose of the work is to increase the understandability of text labels in business process models to improve the overall quality of these models. This problem is relevant, since poorly understandable business process models may cause errors when described workflows are executed, or when they are analyzed for process improvement. Moreover, such errors may decrease the performance of business processes if involved parties misunderstand required tasks and lead to monetary losses or even more dangerous consequences for critical business processes. Thus, to achieve the goal, it is necessary to create an algorithmic solution to solve the specified problem. In this work, the issues that existing studies did not resolve or did not reveal properly, and the main shortcomings of the existing software solutions that should solve the problem mentioned above are identified. The proposed algorithm is based on the natural language processing techniques, such as tokenization and part of speech tagging. The proposed algorithm considers the recommended “verb-object” labeling style of activity text labels in business process models. The comprehensibility of a sample business process model is evaluated using the Python implementation of the proposed algorithmic solution. Obtained results are discussed, a conclusion is made, and future research directions are formulated.

Deep Learning based Part-of-Speech tagging for Assamese using RNN and GRU

Deep Learning (DL) techniques have been widely used in different Natural Language Processing (NLP) tasks. Parts of Speech (PoS) tagging is one where a wide variety of DL techniques have been experimented with across the languages. Here in the present work, Recurrent Neural Network (RNN) and Gated Recurrent Unit (GRU) based Parts of Speech taggers have been trained and modelled for Assamese, an Indo Aryan family language. Universal Parts of Speech (UPoS) tag set of 17 tags were used for the experiment. A dataset of 30000 sequences has been used for the work, which is originally a BIS tag set tagged dataset, and customized through conversion from BIS tagged sequences to UPoS tagged sequences. RNN and GRU based systems have been configured using tensorflow platform and the performance measurement was done through accuracy, precision, recall and F1 scores. The accuracy of the RNN based system has been found to be 93.78%. Precision of 94.75 and recall of 93.28 were recorded for the RNN model. Accuracy of 94.38%, precision of 95.44 and recall of 93.7 were recorded for the GRU model. RNN and GRU models respectively yield F1 scores of 94.01 and 94.56. Although PoS tagging with other tag sets like BIS have been attempted by other researchers, UPoS tagging using DL approaches for Assamese is attempted for the first time. And this baseline work with observed accuracies of 93.78 and 94.38 for RNN and GRU respectively, shall serve as reference models for further works.

Syntactic Category based Assamese Question Pattern Extraction using N-grams

Syntactic categories are important because they play a major role in analysis of sentences. Assamese is a versatile language added with diversified linguistic features. Analysis and manipulation of such a rich language in terms of its vocabulary is really challenging. It requires incorporation of syntactic level annotations like Parts of Speech (PoS) tags into the text for the purpose of efficient and effective processing for different Natural Language Processing (NLP) tasks. Our research mainly focuses on extraction of patterns of syntactic categories in Assamese question sentences. We have also worked on extracting the Bi-grams and Tri-grams of these patterns so that analysis and processing can be done on more basic level. In this paper, we have tried to focus on extraction of PoS tag based Assamese question patterns. We also have tried to generate the Bi-grams and Tri-grams with their frequencies of occurrences throughout the patterns. The work is a noval attempt in modeling question sentence patterns with the embedded PoS patterns.

A Deep Learning-Based Approach for Part of Speech (PoS) Tagging in the Pashto Language

A Deep Learning-Based Approach for Part of Speech (PoS) Tagging in the Pashto Language

Optimizing Machine Learning-based Sentiment Analysis Accuracy in Bilingual Sentences via Preprocessing Techniques

With the recent advances in Natural Language Processing (NLP) technologies, the ability to process, analyze, and understand sentiments expressed in user-generated reviews regarding the products and services they use is becoming more achievable. Despite the latest improvements in this field, little attention has been given to multilingual sentiment analysis. In this article, a framework is presented for sentiment analysis in Arabic and English using two datasets (ASTD, AJGT) along with their translations. Preprocessing techniques, including n-gram tokenization, Arabic-specific stop words removal, punctuation removal, removing repeating characters, parts of speech tagging, stemming, and lemmatization, are applied. Four machine learning classifiers, namely Logistic Regression (LR), Random Forest (RF), Naive Bayes (NB), and Support Vector Machine (SVM), are employed. We highlight existing specialized research in sentiment analysis for Arabic and English, as well as the employed techniques in each. Furthermore, the impact of preprocessing on accuracy results for both Arabic and English languages is investigated through separate experiments for each step. Experimental results on the ASTD dataset demonstrate close performance across classifiers, with the SVM classifier achieving the highest accuracy of 70%. However, the accuracy varied when using the AJGT dataset, with the NB classifier yielding the best accuracy at approximately 87%. The experiments on the translated datasets from Arabic to English did not exhibit significant differences, although some features performed slightly better using the Arabic datasets.

The Scope of Part of Speech Tagging: A Bibliometric Study

The Scope of Part of Speech Tagging: A Bibliometric Study

Test

With the recent advances in Natural Language Processing (NLP) technologies, the ability to process, analyze, and understand sentiments expressed in user-generated reviews regarding the products and services they use is becoming more achievable. Despite the latest improvements in this field, little attention has been given to multilingual sentiment analysis. In this article, a framework is presented for sentiment analysis in Arabic and English using two datasets (ASTD, AJGT) along with their translations. Preprocessing techniques, including n-gram tokenization, Arabic-specific stop words removal, punctuation removal, removing repeating characters, parts of speech tagging, stemming, and lemmatization, are applied. Four machine learning classifiers, namely Logistic Regression (LR), Random Forest (RF), Naive Bayes (NB), and Support Vector Machine (SVM), are employed. We highlight existing specialized research in sentiment analysis for Arabic and English, as well as the employed techniques in each. Furthermore, the impact of preprocessing on accuracy results for both Arabic and English languages is investigated through separate experiments for each step. Experimental results on the ASTD dataset demonstrate close performance across classifiers, with the SVM classifier achieving the highest accuracy of 70%. However, the accuracy varied when using the AJGT dataset, with the NB classifier yielding the best accuracy at approximately 87%. The experiments on the translated datasets from Arabic to English did not exhibit significant differences, although some features performed slightly better using the Arabic datasets

Use of speech tags in various emotional-expressive communication situations

Use of speech tags in various emotional-expressive communication situations

Characterizing Legal Stylistics with a TXM textometric tool

Textometry tools can be used to characterize specialized varieties of English, such as Legal English. Our goal is to use the TXM textometry tool (Heiden et al., 2010) on Sales and Purchase Agreements (SPAs) to show agreements are drafted following a rigid structure, either in their form and shape (macrostructure) or their content (microstructure). We assume that the choice of words (Weisberg, 2014), and the construction of sentences or paragraphs [in agreements] shape how agreements are written and comprise the deal, that is, what is being sold. We hypothesize that there exists legal stylistics based on structural features. We built a corpus comprising Sales and Purchase Agreements of different sizes and topics to which the TXM tool was applied: parts of speech tagging help single out structure, linking words, word variety, frequencies, and writing routines. All descriptive details resulting from our implementation build legal stylistics that thus helps legal professionals, translators, teachers or clients better understand and draft agreements.

User's learning capability aware E-content recommendation system for enhanced learning experience

E-learning is inevitable during these pandemic days and most of the learners find it comfortable to learn online. However, the main challenge is to locate the appropriate data in line with the learner's requirement. Considering the necessity of this issue, this article presents an e-content recommendation system that considers the user's learning capability. This work categorizes the documents into three categories such as basic, intermediate and advanced levels. Based on the users' learning capability, corresponding documents are recommended and this idea enhances the overall learning experience. This work is based on three phases such as data pre-processing, feature extraction and classification. The collected documents are pre-processed for preparing the documents suitable for further processes. Features such as Parts–OF–Speech (POS) tagging, Term Frequency - Inverse Document Frequency (TF-IDF) and semantic similarity based on WordNet are extracted and the multiclass Support Vector Machine (SVM) is employed for distinguishing between the classes. The performance of the work is tested and the results prove the efficacy of the work with 98 % accuracy rates, in contrast to the comparative techniques.

Shahmukhi named entity recognition by using contextualized word embeddings

Named Entity Recognition (NER) is an imperative Natural Language Processing (NLP) task which intents to identify and classify predefined named entities in a given span of text. For many Western and Asian languages, NER is a systematically premeditated and established task, however, a little work has been done for Shahmukhi. This paper presents Shahmukhi NER with four key contributions. First, a Bi-directional Long-Short Term Memory (BiLSTM) network based NER model has been developed by incorporating various features including character and word embeddings and Part of Speech (POS) tagging. Second, transfer learning has been employed by training context-free Word2Vec and contextualized Embeddings from Language Models (ELMo) word representations. The word representations have been trained using a Shahmukhi corpus of 14.9 million words. Third, we prepared a cleaner version of an existing Shahmukhi NER corpus by performing Unicode normalization and tokenization errands. The corpus has been deduplicated and results are reported on an unseen evaluation set which produced valid results. Fourth, we have studied the impact of two annotation schemes; Inside-Outside (IO) and Inside-Outside-Beginning (IOB) for Shahmukhi. Transfer learning was quite helpful to enhance the performance of NER models especially ELMo embeddings significantly improved the results by prompting contextualized embedding vectors. This is the first study to use character embeddings, POS tagging and transfer learning for Shahmukhi named entity recognition. The IO scheme based model achieved an accuracy of 98.60% with an f-score of 83.75. The IOB scheme based model performed with an accuracy of 98.43% and an f-score of 75.55. These scores are quite promising for an under-resourced morphologically-rich language.

The Forgotten Speech Tag: An In-depth Look into the Translation of Speech Tags into Lithuanian in George Orwell's "Animal Farm"

This paper analyses and compares the three currently available Lithuanian translations of George Orwell’s novel Animal Farm (1945) by Arvydas Sabonis (1991), Edita Mažonienė (2021) and Jovita Liutkutė (2022) with special attention given to the frequently overlooked translation of speech tags. It aims to reveal the peculiarities as well as assess the quality of the translations of the collected speech tags. This is achieved by applying quantitative and qualitative analysis methods, i.e. by systematising the relevant elements of the text and analysing them according to the chosen classification of translation shifts as well as comparing the collected data of each individual translation. One of the most notable aspects of the translations, as observed during the analysis, is a significant variety in the translations of pronouns and verbs, occurring due to the application of the translation shifts of specification and implicitation, which function on a semantic level. These aspects reflect the linguistic preferences of translators when translating into synthetic languages and highlight the richness of the Lithuanian language. Key words: translation shifts, speech tags, Animal Farm

Research on Automatic Recognition of New Words on Weibo

To effectively capture emerging vocabulary on Weibo, this article proposes a new Weibo new word recognition strategy that combines Weibo data and support vector machine. Firstly, select positive and negative example sentences from Weibo corpus and trained corpus with part of speech tagging. Then, the lexical features in these sentences are transformed into vectors, and then trained using support vector machines to obtain classification support vectors for Weibo new words. Finally, input the vectorized features into the already trained support vector machine classifier to identify new Weibo words. Based on the experimental results, the system found the optimal feature combination.

A hybrid part-of-speech tagger with annotated Kurdish corpus: advancements in POS tagging

Abstract With the rapid growth of online content written in the Kurdish language, there is an increasing need to make it machine-readable and processable. Part of speech (POS) tagging is a critical aspect of natural language processing (NLP), playing a significant role in applications such as speech recognition, natural language parsing, information retrieval, and multiword term extraction. This study details the creation of the DASTAN corpus, the first POS-annotated corpus for the Sorani Kurdish dialect. The corpus, containing 74,258 words and thirty-eight tags, employs a hybrid approach utilizing the bigram hidden Markov model in combination with the Kurdish rule-based approach to POS tagging. This approach addresses two key problems that arise with rule-based approaches, namely misclassified words and ambiguity-related unanalyzed words. The proposed approach’s accuracy was assessed by training and testing it on the DASTAN corpus, yielding a 96% accuracy rate. Overall, this study’s findings demonstrate the effectiveness of the proposed hybrid approach and its potential to enhance NLP applications for Sorani Kurdish.

A New Sentiment and Fuzzy Aware Product Recommendation System Using Weighted Aquila Optimization and GRNN in e-Commerce

Customer reviews are playing an important role in e-commerce for increasing sales by knowing the customer’s purchase pattern and expectations. The reviews that are collected after completing their purchase reflect the quality and services in e-commerce. The user’s reviews are characterized and categorized through sentiment and semantic analysis. Moreover, the sentiment and semantic classification processes are also performed to predict the user’s purchase patterns and liked products. However, the available classification is not able to predict the user’s purchase patterns. In this paper, we propose a new Product Recommendation System (PRS) to predict the appropriate product for users based on their purchase behavior and pattern. The proposed recommendation system incorporates the standard data preprocessing tasks like tokenization process, Parts of Speech (PoS) tagging process, and parsing, a new sentiment and semantic score calculation procedure, and a new feature optimization technique called the Weighted Aquila Optimization Method (WAOM). Moreover, the sentiment and semantic classification processes are performed by applying a General Regression Neural Network with the incorporation of fuzzy temporal features (FTGRNN) and obtaining better classification results. The newly developed PRS is evaluated by conducting experiments in this work and also proved as superior than other systems available in this direction in terms of prediction accuracy, precision, recall, serendipity and nDCG.

PGST: A Persian gender style transfer method

Abstract Recent developments in text style transfer have led this field to be more highlighted than ever. There are many challenges associated with transferring the style of input text such as fluency and content preservation that need to be addressed. In this research, we present PGST, a novel Persian text style transfer approach in the gender domain, composed of different constituent elements. Established on the significance of parts of speech tags, our method is the first that successfully transfers the gendered linguistic style of Persian text. We have proceeded with a pre-trained word embedding for token replacement purposes, a character-based token classifier for gender exchange purposes, and a beam search algorithm for extracting the most fluent combination. Since different approaches are introduced in our research, we determine a trade-off value for evaluating different models’ success in faking our gender identification model with transferred text. Our research focuses primarily on Persian, but since there is no Persian baseline available, we applied our method to a highly studied gender-tagged English corpus and compared it to state-of-the-art English variants to demonstrate its applicability. Our final approach successfully defeated English and Persian gender identification models by 45.6% and 39.2%, respectively.

Similar Questions Identification on Indonesian Language Subject Using Machine Learning

Question similarity is carried out to evaluate similarities between questions in a collection of questions in the question and answer forum and on other platforms. This is done to improve the performance of the question-and-answer forum so that new questions submitted by users can be identified as similar to existing questions in the database. Currently, research related to question similarity is still being carried out on foreign language datasets. The purpose of this research is to identify the similarity of questions in a collection of questions in Indonesian. The method used is Support Vector Machine and IndoBERT. For feature extraction, we evaluate the lexical features and syntax features of each question. For lexical feature extraction, we use the cosine similarity algorithm to calculate the distance between two objects which are represented as vectors. For syntax feature extraction we use the Indonesian part of speech tagger (POS Tag). The dataset used is a collection of questions on Indonesian subjects at the primary and secondary school levels. The results of this study show that the best performance of the Support Vector Machine is obtained from the use of the cosine similarity feature with an accuracy of 85%. While the use of the POS Tag feature or the combination of POS Tag and cosine similarity causes the model to be overfitted and the accuracy decreases to 77%. Meanwhile, for the IndoBERT model, an accuracy of 95% was obtained.

A Social Media Text Analysis Technique Using ML Algorithm

Data mining and ML approaches are used for analyzing the raw data. The analysis consequences has depends on the applications requirements. The use of ML has also been become popular in analyzing the social media data based on NLP for uncovering the sentiments on the social media text post. Social media has two sides brighten and dark. There are a number of creative ways to use the social media, but there are also some users that are accomplishing their toxic intensions using social media. The use of machine learning algorithms with the social media helps us to performing prediction, classification, categorization and finding relationship among social media data attributes. Therefore, in this paper we have exploring the difference among the social media data text mining technique based data analysis and also by using NLP based text classification. In this context a publically available social media dataset from Kaggle has been collected and a data model has been presented to classify social media text using support vector machine (SVM) and backpropagation neural network (BPN) classifiers. In order to extract the features we have used the TF-IDF and in second scenario we have used the Part of speech (POS) tagger. The obtained results demonstrate the performance of BPN based classifier is higher in both the scenarios of feature classification. Additionally in simple subject classification the TF-IDF based features providing more yield as compared to POS based features. Keywords—machine learning algorithm, supervised learning, social media data, NLP based features, classification performance.

Kencorpus: A Kenyan Language Corpus of Swahili, Dholuo and Luhya for Natural Language Processing Tasks

Indigenous African languages are categorized as under-served in Natural Language Processing. They therefore experience poor digital inclusivity and information access. The processing challenge with such languages has been how to use machine learning and deep learning models without the requisite data. The Kencorpus project intends to bridge this gap by collecting and storing text and speech data that is good enough for data-driven solutions in applications such as machine translation, question answering and transcription in multilingual communities. The Kencorpus dataset is a text and speech corpus for three languages predominantly spoken in Kenya: Swahili, Dholuo and Luhya (three dialects of Lumarachi, Lulogooli and Lubukusu). Data collection was done by researchers who were deployed to the various data collection sources such as communities, schools, media, and publishers. The Kencorpus' dataset has a collection of 5,594 items, being 4,442 texts of 5.6 million words and 1,152 speech files worth 177 hours. Based on this data, other datasets were also developed such as Part of Speech tagging sets for Dholuo and the Luhya dialects of 50,000 and 93,000 words tagged respectively. We developed 7,537 Question-Answer pairs from 1,445 Swahili texts and also created a text translation set of 13,400 sentences from Dholuo and Luhya into Swahili. The datasets are useful for downstream machine learning tasks such as model training and translation. Additionally, we developed two proof of concept systems: for Kiswahili speech-to-text and a machine learning system for Question Answering task. These proofs provided results of a performance of 18.87% word error rate for the former, and 80% Exact Match (EM) for the latter system. These initial results give great promise to the usability of Kencorpus to the machine learning community. Kencorpus is one of few public domain corpora for these three low resource languages and forms a basis of learning and sharing experiences for similar works especially for low resource languages. Challenges in developing the corpus included deficiencies in the data sources, data cleaning challenges, relatively short project timelines and the Coronavirus disease (COVID-19) pandemic that restricted movement and hence the ability to get the data in a timely manner.

Context-aware Answer Selection in Community Question Answering Exploiting Spatial Temporal Bidirectional Long Short-Term Memory

Community Question Answering (CQA) sites provide knowledge sharing facility as the users can post questions and other users can share their answers. The selection of top-quality answers from the set of answers in a thread is a significant and challenging task in Natural Language Processing (NLP). To address this issue, we propose a deep learning based spatial temporal Bidirectional Long Short-Term Memory (Bi-LSTM) algorithm. The existing studies mainly focus only computing semantic similarity between questions and answers using votes given by the users. The proposed hybrid approach, based on both forward and backward, consider question to answer and answer to answer similarity. The forward LSTM captures the spatial impact of the answer to estimate the relevancy, whereas the backward LSTM learns temporal features with the answer to predict the best quality answer. Moreover, spatial Bi-LSTM captures past and future dependencies for a better understanding of context and to improve the effectiveness of answer selection. For extracting meaningful information from noisy text data, data is preprocessed following standard steps such as tokenization, parsing, lemmatization, stop words removal, part of speech tagging and entities extraction. Word embeddings-based Paragraph to vector (par2vec) has additional input nodes to represent paragraph information in vector for context understanding. The empirical analysis carried out on the SemEval CQA dataset shows that the proposed model outperforms state-of-art answer selection approaches.