The methods based on the combination of word-level and character-level features can effectively boost performance on Chinese short text classification. A lot of works concatenate two-level features with little processing, which leads to losing feature information. In this work, we propose a novel framework called Mutual-Attention Convolutional Neural Networks, which integrates word and character-level

Keywords are considered to be important words in the text and can provide a concise representation of the text. With the surge of unlabeled short text on the Internet, automatic keyword extraction task has proven useful in other information processing applications. Graph-based approaches are prevalent unsupervised models for this task. However, most of these methods emphasize the importance of the

Deep neural networks (DNNs) have provably enhanced the state-of-the-art natural language process (NLP) with their capability of feature learning and representation. As one of the more challenging NLP tasks, neural machine translation (NMT) becomes a new approach to machine translation and generates much more fluent results compared to statistical machine translation (SMT). However, SMT is usually better

Text Categorization is an important task in the area of Natural Language Processing (NLP). Its goal is to learn a model that can accurately classify any textual document for a given language into one of a set of predefined categories. In the context of the Arabic language, several approaches have been proposed to tackle this problem, many of which are based on the bag-of-words assumption. Even though

Crosslingual word embeddings developed from multiple parallel corpora help in understanding the relationships between languages and improving the prediction quality of machine translation. However, in low resource languages with complex and agglutinative morphologies, inducing good-quality crosslingual embeddings becomes challenging due to the problem of complex morphological forms and rare words.

Query auto-completion (QAC) is a featured function that has been widely adopted by many sub-domains of search. It can dramatically reduce the number of typed characters and avoid spelling mistakes. These merits of QAC are highlighted to improve user satisfaction, especially when users intend to type in a query on mobile devices. In this article, we will present our industrial solution to the personalized

Research on tools for automating the proofreading of Arabic text has received much attention in recent years. There is an increasing demand for applications that can detect and correct Arabic spelling and grammatical errors to improve the quality of Arabic text content and application input. Our review of previous studies indicates that few Arabic spell-checking research efforts appropriately address

We introduced a new classifier named Learning Word-vector Quantization (LWQ) to solve morphological ambiguities in Turkish, which is an agglutinative language. First, a new and morphologically annotated corpus, and then its datasets are prepared with a series of processes. According to datasets, LWQ finds optimal word-vectors positions by moving them in the Euclidean space. LWQ does morphological disambiguation

Technology has evolved remarkably, which has led to an exponential increase in the availability of digital text documents of disparate domains over the Internet. This makes the retrieval of the information a very much time- and resource-consuming task. Thus, a system that can categorize such documents based on their domains can truly help the users in obtaining the required information with relative

Sentiment classification aims to detect polarity from a piece of text. The polarity is usually positive or negative, and the text genre is usually product review. The challenges of sentiment classification are that it is hard to capture semantic of reviews, and the labeled data is hard to annotate. Therefore, we propose neural co-training to learn the semantic representation of each review using the

No abstract available.

In this study, we create an emotion lexicon for the Hindi language called Hindi EmotionNet. It can assign emotional affinity to words in IndoWordNet. This lexicon contains 3,839 emotion words, with 1,246 positive and 2,399 negative words. We also introduce ambiguous (217 words) and neutral (95 words) emotions to Hindi. Positive emotion words covered nine types of positive emotions, negative emotion

Named Entity Recognition (NER) is a basic prerequisite of using Natural Language Processing (NLP) for information retrieval. Arabic NER is especially challenging as the language is morphologically rich and has short vowels with no capitalisation convention. This article presents a novel rule-based approach that uses linguistic grammar-based techniques to extract Arabic composite names from Arabic text

Language discrimination among similar languages, varieties, and dialects is a challenging natural language processing task. The traditional text-driven focus leads to poor results. In this article, we explore the effectiveness of speech-driven features toward language discrimination among Chinese dialects. First, we systematically explore the appropriateness of speech-driven MFCC features toward CNN-based

Emojis are frequently used to express moods, emotions, and feelings in social media. There has been much research on emojis and sentiments. However, existing methods mainly face two limitations. First, they treat emojis as binary indicator features and rely on handcrafted features for emoji-based sentiment analysis. Second, they consider the sentiment of emojis and texts separately, not fully exploring

Cross-lingual dependency parsing approaches have been employed to develop dependency parsers for the languages for which little or no treebanks are available using the treebanks of other languages. A language for which the cross-lingual parser is developed is usually referred to as the target language and the language whose treebank is used to train the cross-lingual parser model is referred to as

Recent work achieved remarkable results in training neural machine translation (NMT) systems in a fully unsupervised way, with new and dedicated architectures that only rely on monolingual corpora. However, previous work also showed that unsupervised statistical machine translation (USMT) performs better than unsupervised NMT (UNMT), especially for distant language pairs. To take advantage of the superiority

In recent years, the joint model of entity recognition (ER) and relation extraction (RE) has attracted more and more attention in the healthcare and medical domains. However, there are some problems with the prior work. The joint model cannot extract all the relations for a specific entity, and the majority of joint models heavily rely on complex artificial features or professional natural language

Sequential tagging tasks, such as Part-Of-Speech (POS) tagging and Named-Entity Recognition, are the building blocks of many natural language processing applications. Although prior works have reported promising results in standard settings, they often underperform on non-standard text, such as microblogs and social media. In this article, we introduce an adversarial evaluation scheme for the Thai

Dependency-based graph convolutional networks (DepGCNs) are proven helpful for text representation to handle many natural language tasks. Almost all previous models are trained with cross-entropy (CE) loss, which maximizes the posterior likelihood directly. However, the contribution of dependency structures is not well considered by CE loss. As a result, the performance improvement gained by using

A Kannada OCR, called Lipi Gnani, has been designed and developed from scratch, with the motivation of it being able to convert printed text or poetry in Kannada script, without any restriction on vocabulary. The training and test sets have been collected from more than 35 books published from 1970 to 2002, and this includes books written in Halegannada and pages containing Sanskrit slokas written

With the ever-increasing population using online social networks (OSN) in their daily lives, cyberbullying behaviors have also been attracting more attention. Studies show that the cyberbullying adversely affects the mental health. This is especially more pronounced for teenagers. In order to reduce or even stop the cyberbullying, it is of significant importance in the natural language processing and

The core of micro-business and consumer transactions is trust. Based on the Theory of Reasoned Action and Technology Acceptance Model, this paper discusses the factors of the establishment and promotion of micro-business trust from the trust orientation of consumer, the trust of WeChat businesses, and the trust of WeChat platform. Data were obtained by questionnaire, and SPSS software was used for

Utility Management in library is the programmatic tool with the synthetic mental program ability along with Artificial intelligence capacities headed to manage high volume of books, articles and assignments which help to ease the manual significance of librarians. This computerized machine code helps librarians to deal with various databases of the library management system. This framework keeps the

Sign Language (SL), also known as gesture-based language, is used by people with hearing loss to convey their messages. SL interpreters are required for people who do not have the knowledge of SL, but interpreters are not readily available. Thus, a machine-based translation system is required to translate the text into SL. In this article, a system is implemented for translating English text into Indian

Script Recognition is the mechanism of automatic script analysis and recognition whereby intensive study has been carried out and a significant amount of papers on this problem have been released over the past. But there are still a few issues to be solved, particularly in Indian historical manuscripts. This literature examines the Script recognition with reference to multi-script document and different

Named entity recognition (NER) refers to the identification of proper nouns from natural language text and classifying them into named entity types, such as person, location, and organization. Due to the widespread applications of NER, numerous NER techniques and benchmark datasets have been developed for both Western and Asian languages. Even though Shahmukhi script of the Punjabi language has been

In this article, we make use of sequence-to-sequence (seq2seq) models for spelling correction in the agglutinative Turkish language. In the baseline system, misspelled and target words are split into their letters and the letter sequences are fed into the seq2seq model. We prefer letters as the unit of the model due to the agglutinative nature of Turkish, which results in an impractical dictionary

User-generated text in social media communication (SMC) is mainly characterized by non-standard form. It may contain code switching (CS) text, a widespread phenomenon in SMC, in addition to noisy elements used, especially in written conversations (use of abbreviations, symbols, emoticons) or misspelled words. All of these factors constitute a wall in front of text mining applications. Common text mining

Native Language Identification (NLI) aims at identifying the native languages of authors by analyzing their text samples written in a non-native language. Most existing studies investigate this task for educational applications such as second language acquisition and require the learner corpora. This article performs NLI in a challenging context of the user-generated-content (UGC) where authors are

Libraries are vaults of learning and the enormous development in computerized assets has constrained library experts to utilize different data innovation tools to oversee and render management to the clients in Chinese education and research sector. To accomplish more noteworthy proficiency in the quickly evolving economic condition, libraries are progressively searching for new standards to convey

In the present scenario sustainable management and protection of digital cultural data sets are considered as a significant area of research. In the recent past the protection and management of cultural data is facing several new challenged and opportunities. Though several researchers explored their work on managing and protecting cultural data, efficiently and reliability of the present data management

On account of the exponential augmentation of documents on the internet, users need all the pertinent data at ?1? place with no hassle. Therefore, automatic text summarization (ATS) is needed to automate the procedure of summarizing text via extorting the salient details as of the documents. The goal is to propose an automatic, generic, in addition to extractive text summarization for a single document

Over the last decade, through a mixture of optical character recognition and manual input, there is now a growing corpus of Tibetan literature available as e-texts in Unicode format. With the creation of such a corpus, the techniques of text analytics that have been applied in the analysis of English and other modern languages may now be applied to Tibetan. In this work we narrow our focus to examine

Reading & Writing are the original speech-to-text and text-to-speech technologies. Stated simply, graphemes represent phonemes; and, during reading, readers must decode symbols into sounds. This is especially important for beginning readers, who are just learning. That's why it's important for early reading material to make connections between speech forms children know and use and the words on the

Outline extraction has been widely applied in online consultation to help experts quickly understand individual cases. Given a specific case described as unstructured plain text, outline extraction aims to make a summary for this case by answering a set of questions, which in fact is a new type of machine reading comprehension task. Inspired by a recently popular memory network, we propose a novel

Social media data has become invaluable component of business analytics. A multitude of nuances of social media text make the job of conventional text analytical tools difficult. Code-mixing of text is a phenomenon prevalent among social media users, wherein words used are borrowed from multiple languages, though written in the commonly understood roman script. All the existing supervised learning

A sentence is typically treated as the minimal syntactic unit used for extracting valuable information from a longer piece of text. However, in written Thai, there are no explicit sentence markers. We proposed a deep learning model for the task of sentence segmentation that includes three main contributions. First, we integrate n-gram embedding as a local representation to capture word groups near

Efforts on language documentation have been increasing in the past. While the amount of digital data of the world's languages is increasing, only a small amount of the data is sustainable, since data reuse is often exacerbated by idiosyncratic formats and a negligence of standards that could help to increase the comparability of linguistic data. The sustainability problem is nicely reflected in the