A novel unsupervised corpus-based stemming technique using lexicon and corpus statistics

Graph theory and the fields of natural language processing and information retrieval are well-studied disciplines. Traditionally, these areas have been perceived as distinct, with different algorithms, different applications and different potential end-users. However, recent research has shown that these disciplines are intimately connected, with a large variety of natural language processing and information retrieval applications finding efficient solutions within graph-theoretical frameworks. This book extensively covers the use of graph-based algorithms for natural language processing and information retrieval. It brings together topics as diverse as lexical semantics, text summarization, text mining, ontology construction, text classification and information retrieval, which are connected by the common underlying theme of the use of graph-theoretical methods for text and information processing tasks. Readers will come away with a firm understanding of the major methods and applications in natural language processing and information retrieval that rely on graph-based representations and algorithms.

With the rapid development of the Internet and social media, a large amount of text data is constantly generated, and text classification has become an important task. Text classification is an important branch in the field of natural language processing and has attracted the attention of many researchers in recent years. Due to the ease of editing text data, most texts in the network are manually constructed and uploaded by users. Therefore, the standardization of online texts and the classification of texts with different granularity are of great significance in the field of information retrieval. This article introduces the basic concepts of text classification and three text classification methods: knowledge engineering (rule) based text classification methods, traditional machine learning-based text classification methods, and deep neural network-based text classification methods. This article also analyzes the advantages and disadvantages of the three methods. Subsequently, the basic concepts and common models of graph neural networks were explored. An application case of graph neural networks in text classification is provided. This article provides effective suggestions for text classification applications in the field of natural language processing.

Abstract. Large language models (LLMs) have revolutionized the field of natural language processing (NLP), demonstrating remarkable capabilities in understanding, generating, and manipulating human language. This comprehensive review explores the development, applications, optimizations, and challenges of LLMs. This paper begin by tracing the evolution of these models and their foundational architectures, such as the Transformer, GPT, and BERT. We then delve into the applications of LLMs in natural language understanding tasks, including sentiment analysis, named entity recognition, question answering, and text summarization, highlighting real-world use cases. Next, we examine the role of LLMs in natural language generation, covering areas such as content creation, language translation, personalized recommendations, and automated responses. We further discuss LLM applications in other NLP tasks like text style transfer, text correction, and language model pre-training. Subsequently, we explore techniques for optimizing and improving LLMs, including model compression, explainability, robustness, and security. Finally, we address the challenges posed by the significant computational requirements, sample inefficiency, and ethical considerations surrounding LLMs. We conclude by discussing potential future research directions, such as efficient architectures, few-shot learning, bias mitigation, and privacy-preserving techniques, which will shape the ongoing development and responsible deployment of LLMs in NLP.

Word sense disambiguation determines the specific meaning of ambiguous words according to their specific context, a basic research in the field of natural language processing, and has a direct impact on the upper application of machine translation, information retrieval, text classification, and sentiment analysis. This paper proposes a word sense disambiguation method based on graph and knowledge base, for the insufficient utilization problem of existing knowledge base. It utilizes dependency parsing to obtain contextual knowledge and processes the examples in lexical knowledge base, which have a good ability of sense distinction, to construct disambiguation graph. Then, the disambiguation can be done by combining dependency disambiguation graph and contextual disambiguation graph. Experiments on the dataset of SemEval-2007 task#5 show that the disambiguation accuracy is 0.471, which is better than the mentioned methods.KeywordsWord sense disambiguationGraphDependency parsing

The language modeling approach centers on the issue of estimating an accurate model by choosing appropriate language models as well as smoothing techniques. In the thesis, we propose a novel context-sensitive semantic smoothing method referred to as a topic signature language model. It extracts explicit topic signatures from a document and then statistically maps them into individual words in the vocabulary. In order to support the new language model, we developed two automated algorithms to extract multiword phrases and ontological concepts, respectively, and an EM-based algorithm to learn semantic mapping knowledge from co-occurrence data. The topic signature language model is applied to three applications: information retrieval, text classification, and text clustering. The evaluations on news collection and biomedical literature prove the effectiveness of the topic signature language model. In the experiment of information retrieval, the topic signature language model consistently outperforms the baseline two-stage language model as well as the context-insensitive semantic smoothing method in all configurations. It also beats the state-of-the-art Okapi models in all configurations. In the experiment of text classification, when the size of training documents is small, the Bayesian classifier with semantic smoothing not only outperforms the classifiers with background smoothing and Laplace smoothing, but it also beats the active learning classifiers and SVM classifiers. On the task of clustering, whether or not the dataset to cluster is small, the model-based k-means with semantic smoothing performs significantly better than both the model-based k-means with background smoothing and Laplace smoothing. It is also superior to the spherical k-means in terms of effectiveness. In addition, we empirically prove that, within the framework of topic signature language models, the semantic knowledge learned from one collection could be effectively applied to other collections. In the thesis, we also compare three types of topic signatures (i.e., words, multiword phrases, and ontological concepts), with respect to their effectiveness and efficiency for semantic smoothing. In general, it is more expensive to extract multiword phrases and ontological concepts than individual words, but semantic mapping based on multiword phrases and ontological concepts are more effective in handling data sparsity than on individual words.

<span lang="EN-US">In the realm of natural language processing (NLP), a diverse array of language models has emerged, catering to a wide spectrum of tasks, ranging from speaker recognition and auto-correction to sentiment analysis and stock prediction. The significance of language models in enabling the execution of these NLP tasks cannot be overstated. This study proposes an approach to enhance accuracy by leveraging a hybrid language model, combining the strengths of long short-term memory (LSTM) and gated recurrent unit (GRU). LSTM excels in preserving long-term dependencies in data, while GRU's simpler gating mechanism expedites the training process. The research endeavors to evaluate four variations of this hybrid model: LSTM, GRU, <a name="_Hlk158992630"></a>bidirectional long short-term memory (Bi-LSTM), and a combination of LSTM with GRU. These models are subjected to rigorous testing on two distinct datasets: one focused on IBM stock price prediction, and the other on Jigsaw toxic comment classification (sentiment analysis). This work represents a significant stride towards democratizing NLP capabilities, ensuring that even in resource-constrained settings, NLP models can exhibit improved performance. The anticipated implications of these findings span a wide spectrum of real-world applications and hold the potential to stimulate further research in the field of NLP. </span>

Keyphrases are multipurpose knowledge gems, rendering keyphrase extraction a very important document processing task. They constitute a concise summary of documents that is extremely useful both for human inspection and machine consumption, in support of a number of tasks in the field of Natural Language Processing, Machine Learning and Information Retrieval. To this regard, the aim of this tutorial is two-fold: (a) to provide an overview of the automatic keyphrase extraction task and (b) to familiarize participants with the keyphrase extraction process. Specifically, we will provide a well‐structured review of the existing work, offer interesting insights on the different evaluation approaches, highlight open issues such as the need for evaluation approaches that take the semantic similarity of predicted and golden keyphrases, present a comparative experimental study of popular techniques, and familiarize the audience with the keyphrase extraction process via a demo presentation using jupyter notebook, which will be available to the audience during the practical part of the tutorial. We expect the tutorial to help newcomers and veterans alike navigate the large amount of prior art and grasp its evolution.

Measuring semantic similarity between sentences is a significant task in the fields of Natural Language Processing (NLP), Information Retrieval (IR), and biomedical text mining. For this reason, the proposal of sentence similarity methods for the biomedical domain has attracted a lot of attention in recent years. However, most sentence similarity methods and experimental results reported in the biomedical domain cannot be reproduced for multiple reasons as follows: the copying of previous results without confirmation, the lack of source code and data to replicate both methods and experiments, and the lack of a detailed definition of the experimental setup, among others. As a consequence of this reproducibility gap, the state of the problem can be neither elucidated nor new lines of research be soundly set. On the other hand, there are other significant gaps in the literature on biomedical sentence similarity as follows: (1) the evaluation of several unexplored sentence similarity methods which deserve to be studied; (2) the evaluation of an unexplored benchmark on biomedical sentence similarity, called Corpus-Transcriptional-Regulation (CTR); (3) a study on the impact of the pre-processing stage and Named Entity Recognition (NER) tools on the performance of the sentence similarity methods; and finally, (4) the lack of software and data resources for the reproducibility of methods and experiments in this line of research. Identified these open problems, this registered report introduces a detailed experimental setup, together with a categorization of the literature, to develop the largest, updated, and for the first time, reproducible experimental survey on biomedical sentence similarity. Our aforementioned experimental survey will be based on our own software replication and the evaluation of all methods being studied on the same software platform, which will be specially developed for this work, and it will become the first publicly available software library for biomedical sentence similarity. Finally, we will provide a very detailed reproducibility protocol and dataset as supplementary material to allow the exact replication of all our experiments and results.

In the past decades, sentiment analysis has become one of the most active research areas in natural language processing, data mining, web mining, and information retrieval. The great demand in everyday life and the factor of novelty coupled with the availability of data from social networks have served as strong motivation for research on sentiment-analysis. A number of technical problems, most of which had not been attempted before, either in the NLP or linguistics communities have also generated strong research interests in academia. Sentiment analysis, also called opin-ion mining, is the field of study that analyzes people’s opinions, sentiments, apprais-als, attitudes, and emotions toward entities and their attributes expressed in written text. The entities can be products, services, organizations, individuals, events, issues, or topics. The field represents a large problem space. It improves not only the field of natural language processing but also management, political science, economics, and sociology because all these areas are related to the thoughts of consumers and public. User-generated content is full of opinions, because the main reason why people post messages on social media platforms is to express their views and opinions, and therefore sentiment analysis is at the centre of social media analysis. It turned out that user messages often contain plenty of sarcastic expressions and ambiguous words. Within one opinion both positive and negative sentiments can be present. This also applies to negative particles, which do not always indicate a negative tone. This article investigates four challenges faced by researchers while conducting sentiment analysis, namely: sarcasm, negation, word ambiguity, and multipolarity. These aspects significantly affect the accuracy of the results when we determine a sentiment. Modern approaches to solving the problem are also covered. These are mainly machine learning methods, such as convolutional neural networks (CNN), deep neural networks (DNN), long short-term memory (LTSM), recurrent neural network (RNN), support vector machines (SVM), etc.

Question answering (QA) is a task in the field of natural language processing (NLP) and information retrieval, which has pivotal applications in areas such as online reading comprehension and web search engines. Currently, Bidirectional Encoder Representations from Transformers (BERT) and its biomedical variation (BioBERT) achieve impressive results on the reading comprehension QA datasets and medical-related QA datasets, and so they are widely used for a variety of passage-based QA tasks. However, their performances rapidly deteriorate when encountering passage and context ambiguities. This issue is prevalent and unavoidable in many fields, notably the web-based medical field. In this paper, we introduced a novel approach called the Multiple Synonymous Questions BioBERT (MSQ-BioBERT), which integrates question augmentation, rather than the typical single question used by traditional BioBERT, to elevate BioBERT’s performance on medical QA tasks. In addition, we constructed an ambiguous medical dataset based on the information from Wikipedia web. Experiments with both this web-based constructed medical dataset and open biomedical datasets demonstrate the significant performance gains of the MSQ-BioBERT approach, showcasing a new method for addressing ambiguity in medical QA tasks.

This article presents a literature review of computer-science-related research applied on hadith, a kind of Arabic narration which appeared in the 7th century. We study and compare existent works in several fields of Natural Language Processing (NLP), Information Retrieval (IR), and Knowledge Extraction (KE). Thus, we illicit their main drawbacks and identify some perspectives, which may be considered by the research community. We also study the characteristics of these types of documents, by enumerating the advantages/limits of using hadith as a language resource. Moreover, our study shows that previous studies used different collections of hadiths, thus making it hard to compare their results objectively. Besides, many preprocessing steps are recurrent through these applications, thus wasting a lot of time. Consequently, the key issues for building generic language resources from hadiths are discussed, taking into account the relevance of related literature and the wide community of researchers that are interested in these narrations. The ultimate goal is to structure hadith books for multiple usages, thus building common collections which may be exploited in future applications.

Text classification is one of the most popular tasks in natural language processing, especially in the context of sentiment classification. Insufficient training data poses a significant challenge in many text classification studies. This research focuses on optimizing classification performance using the Passive Aggressive (PA) algorithm, leveraging limited training data. It compares conventional text representation methods like TF-IDF with modern approaches employing word embeddings such as FastText and BERT. The primary dataset encompasses sentiment issues related to Kaesang Pangarep's appointment as the chairman of PSI, gathered through Twitter crawling, and classified into positive, negative, and neutral sentiment labels. Two versions of the training data, each containing only 300 balanced tweets for positive, negative, and neutral classes, were used. The data was split 80% for training and 20% for validation in the search for an optimal model. External data with different issues and pre-existing sentiment labels was used to augment the training data. Experimental results demonstrated that the BERT language model, used as input features for the Passive Aggressive method with hyperparameter tuning, outperformed TF-IDF features. Evaluation on the test data revealed that BERT features with Passive Aggressive achieved an F1-score of 0.52, surpassing the conventional TF-IDF representation with an F1-score of 0.42. The utilization of the BERT language model significantly contributed to improving text classification performance in the field of natural language processing, particularly for the Passive Aggressive method.

Managing complex AI systems requires insight into a model's decision-making processes. Understanding how these systems arrive at their conclusions is essential for ensuring reliability. In the field of explainable natural language processing, many approaches have been developed and evaluated. However, experimental analysis of explainability for text classification has been largely constrained to short text and binary classification. In this applied work, we study explainability for a real-world task where the goal is to assess the technological suitability of standards. This prototypical use case is characterized by large documents, technical language, and a multi-label setting, making it a complex modeling challenge. We provide an analysis of approx. 1000 documents with human-annotated evidence. We then present experimental results with two explanation methods evaluating plausibility and runtime of explanations. We find that the average runtime for explanation generation is at least 5 minutes and that the model explanations do not overlap with the ground truth. These findings reveal limitations of current explanation methods. In a detailed discussion, we identify possible reasons and how to address them on three different dimensions: task, model and explanation method. We conclude with risks and recommendations for the use of feature attribution methods in similar settings.

Text classification has always been a hot research topic in the field of natural language processing. Fasttext is a model which is simple in structure and has the advantage of fast and efficient. In order to analyze the situation of electric power intellectual property in recent years, this paper use the model of FastText to process Chinese electric power core journals and patents in recent five years. The text information in the company's intellectual property rights is divided into a series of phrases representing individual meanings though word segmentation basing on the Jieba word segmentation tool. The stop words unrelated to the power industry in the phrases are removed, and the word related the power industry frequency corresponding to the phrases and the frequency of occurrence in the text are counted. According to the characteristics of power industry word aggregation, the phrase can be divided into 26 categories. The text classification model based on keywords of power industry was designed, and the machine learning algorithm Fasttext is used to complete the text classification. Based on each subdivision field of power, the publication situation of intellectual property is analyzed and counted, and the results of power system intellectual property are visualized.

Text classification is one of the core tasks in the field of natural language processing. Aiming at the advantages and disadvantages of current deep learning-based English text classification methods in long text classification, this paper proposes an English text classification model, which intro