Semantic Similarity Analysis for Corpus Development and Paraphrase Detection in Arabic

An integrated approach for intrinsic plagiarism detection

Like any other science, research in natural language processing (NLP) depends on the ability to draw correct conclusions from experiments. A key tool for this is statistical significance testing: We use it to judge whether a result provides meaningful, generalizable findings or should be taken with a pinch of salt. When comparing new methods against others, performance metrics often differ by only small amounts, so researchers turn to significance tests to show that improved models are genuinely better. Unfortunately, this reasoning often fails because we choose inappropriate significance tests or carry them out incorrectly, making their outcomes meaningless. Or, the test we use may fail to indicate a significant result when a more appropriate test would find one. NLP researchers must avoid these pitfalls to ensure that their evaluations are sound and ultimately avoid wasting time and money through incorrect conclusions.This book guides NLP researchers through the whole process of significance testing, making it easy to select the right kind of test by matching canonical NLP tasks to specific significance testing procedures. As well as being a handbook for researchers, the book provides theoretical background on significance testing, includes new methods that solve problems with significance tests in the world of deep learning and multidataset benchmarks, and describes the open research problems of significance testing for NLP.The book focuses on the task of comparing one algorithm with another. At the core of this is the p-value, the probability that a difference at least as extreme as the one we observed could occur by chance. If the p-value falls below a predetermined threshold, the result is declared significant. Leaving aside the fundamental limitation of turning the validity of results into a binary question with an arbitrary threshold, to be a valid statistical significance test, the p-value must be computed in the right way. The book describes the two crucial properties of an appropriate significance test: The test must be both valid and powerful. Validity refers to the avoidance of type 1 errors, in which the result is incorrectly declared significant. Common mistakes that lead to type 1 errors include deploying tests that make incorrect assumptions, such as independence between data points. The power of a test refers to its ability to detect a significant result and therefore to avoid type 2 errors. Here, knowledge of the data and experiment must be used to choose a test that makes the correct assumptions. There is a trade-off between validity and power, but for the most common NLP tasks (language modeling, sequence labeling, translation, etc.), there are clear choices of tests that provide a good balance.Beginning with a detailed background on significance testing, the book then shows the reader how to carry out tests for specific NLP tasks. There is a mix of styles, with the first four chapters providing reference material that will be extremely useful to both new and experienced researchers. Here, it is easy to find the material related to a given NLP task. The next two chapters discuss more recent research into the application of significance tests to deep neural networks and for testing across multiple datasets. Alongside open research questions, these later chapters provide clear guidelines on how to apply the proposed methods. It is this mix of background material and reference guidelines that I believe makes this book so compelling and nicely self-contained.The introduction in Chapter 1 motivates the need for a comprehensive textbook and outlines challenges that the later chapters address more deeply. The theoretical background material begins in Chapter 2, which introduces core concepts, including hypothesis testing, type 1 and type 2 errors, validity and power, and p-values. The reader does not need to have any prior knowledge of statistical significance tests to follow this part. However, experienced readers could still benefit from reading this chapter, as concepts such as p-values are widely misunderstood and misused (Amrhein, Greenland, and McShane 2019).The significance tests themselves are introduced in Chapter 3, categorized into parametric and nonparametric tests. The chapter begins with the intuitively simple paired z-test, then builds up to more commonly-applied techniques, showing the connections and assumptions that each test makes. Step-by-step algorithms help the reader to implement each test. Although the chapter does cite uses of tests in NLP research, the main purpose is to present the theory behind each test and point out their differences.Chapter 4 provides perhaps the most handy part of the book for reference: a correspondence between common NLP tasks and statistical tests. Each task is discussed in terms of the evaluation metrics used, then a decision tree is introduced to guide the reader toward a choice between a parametric test, bootstrap or randomization test, or sampling-free nonparametric test. Section 4.3 then links each NLP evaluation measure to a specific significance test, presenting a large table that helps readers identify which test they need for a specific task. Particular considerations for each task are also pointed out to provide more detail about the appropriate options. The final part of this chapter describes the issue of p-hacking, in which dataset sizes are increased until a significance threshold is reached without consideration for biases in the data (discussed, for example, in Hofmann [2015]). The chapter proposes a simple solution to ensure robust significance testing with large datasets.Where Chapter 4 presents well-established methods, Chapter 5 introduces the current research question of how best to apply statistical significance testing to deep learning. Non-convex loss functions, stochastic optimization, random initialization, and a multitude of hyperparameters limit the conclusions we can draw from a single test run of a deep neural network (DNN). This chapter, which is based on the authors’ ACL paper (Dror, Shlomov, and Reichart 2019), explains how the comparison process can be overhauled to provide more meaningful evaluations. Beginning by explaining the difficulties of evaluating DNNs, the chapter then introduces criteria for a comparison framework, then discusses the limitations of current methods. Reimers and Gurevych (2018) have previously tackled this problem, but their approach has limited power and does not provide a confidence score. Other works, such as Clark et al. (2011), compare DNNs using a collection of statistics, such as the mean or standard deviation of performance across runs. This book shows how such an approach violates the assumptions of the significance tests. The authors propose almost stochastic dominance as the basis for a better alternative. The chapter explains how to use the proposed method, evaluates it in an empirical case study, and finally analyzes the errors made by each testing approach.Large NLP models are often tested across a range of datasets, which presents another problem for standard significance testing. Chapter 6 discusses the challenges of assessing two questions: (1) On how many datasets does algorithm A outperform algorithm B? (2) On which datasets does A outperform B? Applying standard significance tests individually to each dataset and counting the number of significant results is likely to overestimate the total number of significant results, as this chapter explains. The authors then present a new framework for replicability analysis, based on partial conjunction testing, and discuss two variants (Bonferroni and Fisher) for when the datasets are independent or dependent. They introduce a method based on Benjamini and Heller (2008) to count the number of datasets where one method outperforms another, then show how to use the Holm procedure (Holm 1979) to identify which datasets these are. Chapter 6 provides a lot of detailed background on the proposed replicability analysis framework, and the later sections again link the process to specific NLP case studies, and step-by-step summaries help the reader to apply the methodology. Extensive empirical results illustrate the very substantial differences in outcomes between the proposed approach and standard procedures.The final two chapters present open problems and conclude, showing that the topic has many interesting research questions of its own, such as problems when performing cross-validation, and the limited statistical power of replicability analysis.Overall, I highly recommend this book to a wide range of NLP researchers, from new students to seasoned experts who wish to ensure that they compare methods effectively. The book is excellent as both an introduction to the topic of significance testing and as a reference to use when evaluating your results. For anyone with further interest in the topic, it also points the way to future work. If one could level any criticism at this book at all, it is that it does not deeply discuss the basic flaws of significance testing or what the alternatives might be. For now, though, significance testing is an integral part of NLP research and this book provides a great resource for researchers who wish to perform it correctly and painlessly.

The progressive advancement in technology has become easy to present the language expression of someone else as one’s own with similar words semantically. This phenomenon increased the potential source of plagiarism. Its detection is a challenge especially in the case of Arabic paraphrase because of the semantic ambiguity of this language. In recent decades, researches have been hindered by the very limited availability of well-structured datasets. In this context, our main objectives are focused on constructing a corpus for Arabic and presenting thereafter its impact for identifying paraphrase. Indeed, we generated the suspect documents from the Open Source Arabic Corpora (OSAC). Distributed word representation (word2vec) and part-of-speech methods were useful for replacing each original word by its most similar one that had the same grammatical class. Moreover, we captured the structure of Arabic sentences with different window sizes and vector dimensions. Then, we studied how this corpus could be used efficiently in the evaluation of Natural Language Processing (NLP) methods (i.e. Term Frequency-Inverse Document Frequency (TF-IDF), Latent Semantic Analysis (LSA), Latent Dirichlet Allocation (LDA), word2vec, Global Vector Representation (GloVe), and Convolutional Neural Network (CNN)) for paraphrase detection. Experiments revealed which one could outperformed significantly for preserving semantic properties of Arabic words with various linear regularities, alleviating data sparseness and increasing the degree of semantic similarity, in terms of precision and recall.

Text summarization is a technique for reducing lengthy passages of text into smaller portions. The goal is to develop a logical and fluent summary that only includes the document's major ideas. It's a important task in Natural Language Processing (NLP) that undoubtedly has a significant impact on synthesization of lengthy documents. With the rise of the digital documentation and publication, devoting time to thoughtfully read an article, document, or book in order to determine its relevance is no longer an option, especially given time constraints. In machine learning and NLP, automatic text summarization is a generic problem. A comparison of text summarization applying the Term Frequency ~ Inverse Document Frequency, Latent Semantic Analysis and Text Rank algorithms for the Malayalam language is presented in this research paper.

Word embeddings, distributed word representations in a reduced linear space, show a lot of promise for accomplishing Natural Language Processing (NLP) tasks in an unsupervised manner. In this study, we investigate if the success of word2vec, a Neural Networks based word embeddings algorithm, can be replicated in an aggluginative language like Turkish. Turkish is more challenging than languages like English for complex NLP tasks because of her rich morphology. We picked ontology enrichment, again a relatively harder NLP task, as our test application. Firstly, we show how ontological relations can be extracted automaticaly from Turkish Wikipedia to construct a gold standard. Then by running experiments we show that the word vector representations produced by word2vec are useful to detect ontological relations encoded in Wikipedia. We propose a simple but yet effective weakly supervised ontology enrichment algorithm where for a given word a few know ontologically related concepts coupled with similarity scores computed via word2vec models can result in discovery of other related concepts. We argue how our algorithm can be improved and augmented to make it a viable component of an ontoloy learning and population framework.

A trademark may be a word, phrase, symbol, sound, color, scent or design, or combination of these, that identifies and distinguishes the goods or services of a particular source from those of others. Obtaining a trademark is a complex, time intensive and costly process that involves varied steps before the trademark can be registered including searching prior trademarks, filing of the trademark application, review of the trademark application and final publication for opposition by the public. One of the crucial aspect in the review of the trademark application is determining the international classes of the filed marks based on their goods and services description. Currently, the process of identifying the international classes of a filed mark is performed manually in the United States Patent and Trademark Office (USPTO) and takes significant amount of time. Recently, word embeddings and deep neural networks (DNNs) have revolutionized the field of computer vision and demonstrated excellent performance in various natural language processing (NLP) tasks such as machine translation, speech recognition, sentence and document classification etc. to name a few. In this study, we explored fastText and different neural networks such as Convolution Neural Networks (CNN), Long Short Term Memory (LSTM), bidirectional versions of both LSTM and Gated Recurrent Unit (GRU) and Recurrent Convolutional Neural Network (RCNN) to automate the international class identification for the filed marks based on their goods and services description. Overall, it was found that the trademark word embeddings with RCNN model outperformed the other models. Our study thereby seeks to provide a solution towards the manual, time intensive and laborious process of identifying international classes for the trademarks.

The intelligent task of semantically assigning a paper to a reviewer with respect to his knowledge domain remains a challenging task in academic conferences. From literature, a number of automated reviewer assignment systems have been presented which are based on distributional semantic models such as Term Frequency-Inverse Document Frequency (TF-IDF), Latent Semantic Indexing (LSI) and Latent Dirichlet Allocation (LDA) have been used to capture semantics. Thus, this study presents the comparative study of the three models based on their derived suitability scores between a paper meant for review and a reviewer’s representation papers. From the experimental results obtained, it shows that TF-IDF outperformed the accuracy level of the other two models by a substantial margin.

Funding agencies such as the U.S. National Science Foundation (NSF), U.S. National Institutes of Health (NIH), and the Transportation Research Board (TRB) of The National Academies make their online grant databases publicly available which document a variety of information on grants that have been funded over the past few decades. In this paper, based on a quantitative analysis of the TRB’s Research In Progress (RIP) online database, we explore the feasibility of automatically estimating the appropriate funding level, given the textual description of a transportation research project. We use statistical Text Mining (TM) and Machine Learning (ML) technologies to build this model using the 14,000 or more records of the TRB’s RIP research grants big data. Several Natural Language Processing (NLP) based text representation models such as the Latent Dirichlet Allocation (LDA), Latent Semantic Indexing (LSI) and the Doc2Vec Machine Learning (ML) approach are used to vectorize the project descriptions and generate semantic vectors. Each of these representations is then used to train supervised regression models such as Random Forest (RF) regression. Out of the three latent feature generation models, we found LDA gives the least Mean Absolute Error (MAE) using 300 feature dimensions and RF regression model. However, based on the correlation coefficients, it was found that it is not very feasible to accurately predict the funding level directly from the unstructured project abstract, given the large variations in source agencies, subject areas, and funding levels. By using separate prediction models for different types of funding agencies, funding levels were better correlated with the project abstract.

Objective: The objective is to develop an ensemble of machine learning algorithms to identify multilingual, online articles that are relevant to biosurveillance. Language morphology varies widely across languages and must be accounted for when designing algorithms. Here, we compare the performance of a word embedding-based approach and a topic modeling approach with machine learning algorithms to determine the best method for Chinese, Arabic, and French languages.Introduction: Global biosurveillance is an extremely important, yet challenging task. One form of global biosurveillance comes from harvesting open source online data (e.g. news, blogs, reports, RSS feeds). The information derived from this data can be used for timely detection and identification of biological threats all over the world. However, the more inclusive the data harvesting procedure is to ensure that all potentially relevant articles are collected, the more data that is irrelevant also gets harvested. This issue can become even more complex when the online data is in a non-native language. Foreign language articles not only create language-specific issues for Natural Language Processing (NLP), but also add a significant amount of translation costs. Previous work shows success in the use of combinatory monolingual classifiers in specific applications, e.g., legal domain [1]. A critical component for a comprehensive, online harvesting biosurveillance system is the capability to identify relevant foreign language articles from irrelevant ones based on the initial article information collected, without the additional cost of full text retrieval and translation.Methods: The analysis text dataset contains the title and brief description of 3506 online articles in Chinese, Arabic, and French languages from the date range of August, 17, 2016 to July 5, 2017. The NLP article pre-processing steps are language-specific tokenization and stop words removal. We compare two different approaches: word embeddings and topic modeling (Fig. 1). For word embeddings, we first generate word vectors for the data using a pretrained Word2Vec (W2V) model [2]. Subsequently, the word vectors within a document are averaged to produce a single feature vector for the document. Then, we fit a machine learning algorithm (random forest classifier or Support Vector Machine (SVM)) to the training vectors and get predictions for the test documents. For topic modelling, we used a Latent Dirichlet Allocation (LDA) model to generate five topics for all relevant documents [3]. For each new document, the output is the probability measure for the document belonging to these five topics. Here, we classify the new document by comparing the probability measure with a relevancy threshold.Results: The Word2Vec model combined with a random forest classifier outperformed the other approaches across the three languages (Fig. 2); the Chinese model has an 89% F1-score, the Arabic model has 86%, and the French model has 94%. To decrease the chance of calling a potentially relevant article irrelevant, high recall was more important than high precision. In the Chinese model, the Word2Vec with a random forest approach had the highest recall at 98% (Table 1).Conclusions: We present research findings on different approaches of relevance to biosurveillance identification on non-English texts and identify the best performing methods for implementation into a biosurveillance online article harvesting system. Our initial results suggest that the word embeddings model has an advantage over topic modeling, and the random forest classifier outperforms the SVM. Directions for future work will aim to further expand the list of languages and methods to be compared, e.g., n-grams and non-negative matrix factorization. In addition, we will fine-tune the Arabic and French model for better accuracy results.

As a basic task in NLP (Natural Language Processing), feature extraction directly determines the quality of text clustering and text classification. However, the commonly used TF-IDF (Term Frequency & Inverse Document Frequency) and LDA (Latent Dirichlet Allocation) text feature extraction methods have shortcomings in not considering the text’s context and blindness to the topic of the corpus. This study builds a feature extraction algorithm and application scenarios in the field of failure diagnosis. A text-driven failure diagnosis model is designed to classify and automatically judge which failure mode the failure described in the text belongs to once a failure-description text is entered. To verify the effectiveness of the proposed feature extraction algorithm and failure diagnosis model, a long-term accumulated failure description text of an aircraft maintenance and support system was used as a subject to conduct an empirical study. The final experimental results also show that the proposed feature extraction method can effectively improve the effect of clustering, and the proposed failure diagnosis model achieves high accuracies and low false alarm rates.

Natural Language Processing (NLP) is now widely integrated into web and mobile applications, enabling natural interactions between humans and computers. Although there is a large body of NLP studies published in Information Systems (IS), a comprehensive review of how NLP research is conceptualised and realised in the context of IS has not been conducted. To assess the current state of NLP research in IS, we use a variety of techniques to analyse a literature corpus comprising 356 NLP research articles published in IS journals between 2004 and 2018. Our analysis indicates the need to move from semantics to pragmatics. More importantly, our findings unpack the challenges and assumptions underlying current research trends in NLP. We argue that overcoming these challenges will require a renewed disciplinary IS focus. By proposing a roadmap of NLP research in IS, we draw attention to three NLP research perspectives and present future directions that IS researchers are uniquely positioned to address.

Word vector is an important tool for natural language processing (NLP) tasks such as text classification. However, existing static language models such as Word2vec cannot solve the polysemy problem, leading to a decline in text classification performance. To solve this problem, this paper proposes a method for making Chinese word vector dynamic (MCWVD). The part of speech (POS) is used to solve the ambiguity problem caused by different POS. The POS structure graph is constructed and the syntactic structure information of POS features is extracted by GCN (Graph Convolutional Network). POS vector and word vector are concatenated into PW (POS-Word) vector. Parametric matrix is added to improve the fusion effect of POS and word features. Multilayer attention is used to distinguish the importance of different features and further update the vector expression of word vectors about the current context. Experiments on Chinese datasets THUCNews and SogouNews show that MCWVD effectively improves the accuracy of text classification and achieves better performance than CoVe (Context Vectors) and ELMo (Embeddings from Language Models). MCWVD also achieves similar performance to BERT and GPT-1 (Generative Pre-Training), but with a much lower computational cost and only 4% of BERT parameters.

Topic modelling is an approach in data mining, use machine learning methods to discover patterns in large amount of unstructured text. It takes a collection of documents and group the words into clusters of words that we call Bag of words, and identify topics by using process of similarity. Topic modelling provides us with methods to organize, understand and summarize large collections of textual information. There are a lot of approaches have been exposed for Topic modelling, the most in use are Latent Semantic Analysis (LSA), Latent Dirichlet Allocation (LDA) and explicit semantic analysis (ESA). In our study we describing an approach to refine Topic detection based on 2d vector space model VSM by using Apriori algorithm along with Natural language processing, to form a better connected terms in vector space for clean engagement with the query.

Topic relevance of pages and hyperlinks is the key issue in focused crawling. In this paper, an improved topic relevance algorithm for focused crawling is proposed. First, we implement a prototype system of the focused crawler - a topic-specific news gathering system which is prepared for comparative experiments on different similarity measures with the anchor text. Second, experiments on Chinese text corpus show that using LSI (Latent Semantic Indexing) outperforms using TF-IDF (term frequency- inverse document frequency) for hyperlink topic relevance prediction and pages topic relevance calculation. Third, in real crawling experiments on the prototype system, the crawler using TF-IDF has high performance with the accumulated topic relevance increasing quickly at the beginning of crawling, however the crawler using LSI can find more related pages and tunnel through. Fourth, combining their advantages of LSI and TF-IDF, we propose TFIDF+LSI algorithm to guide the crawling. Last, the crawler using TFIDF+LSI performs the same crawl task and demonstrates the combination advantage of TF-IDF and LSI. The experiment suggests that the crawler's performance using TFIDF+LSI is greatly superior to that using either TF-IDF or LSI respectively.

Conventional text embeddings, typically learned in the Euclidean space, may struggle to effectively capture word semantics based solely on the directional similarity between word vectors. In contrast, spherical text embeddings have demonstrated remarkable efficacy in various natural language processing (NLP) tasks recently. However, training spherical text generative models (STGMs) requires large representative datasets, which could potentially contain sensitive private information. To mitigate this concern, we propose a novel approach: the differential private spherical text generative model (DP-STGM), which facilitates learning text embeddings within the spherical space while ensuring privacy via efficient Riemannian optimization and the framework of differential privacy. To evaluate the efficacy of our privacy-preserving algorithm, we initially train an adversary using an external dataset without the application of differential privacy. Subsequently, we introduce two metrics to measure the model’s ability to protect privacy: (1) cosine similarity between recovered words from the adversary that generates the spherical text embeddings and those generated by DP-STGM, and (2) Top-n rank correlation. Our experimental findings demonstrate that DP-STGM outperforms baseline models, showcasing its superior performance. By leveraging the power of differential privacy in the Riemannian optimization process, our model achieves better preservation of sensitive information while simultaneously capturing the semantic nuances inherent in word embeddings. As a result, DP-STGM represents a robust and efficient solution for NLP tasks that require privacy protection without compromising on the quality of learned text embeddings. By offering a privacy-preserving alternative, DP-STGM broadens the range of applications for which STGMs can be safely employed, ensuring data privacy while harnessing the rich information contained in spherical text embeddings. Our work opens up new avenues for future research in privacy-aware NLP and advances the state-of-the-art in both privacy protection and semantic learning in this domain.