Search

Zero-Shot Learning (ZSL) aims to classify images of new categories in the testing phase without labeled images during training, using examples from categories with labeled images and some auxiliary information. The auxiliary information includes semantic attributes, textual descriptions, word embeddings, etc., for both labeled and unlabeled classes, utilizing Natural Language Processing (NLP) approaches. The word embeddings created are limited by the semantic attributes and textual descriptions where the semantics of categories are insufficient. In this paper, introduces a study for Generalized Zero-Shot Learning (GZSL), a type of ZSL, by integrating the rich semantics offered by ontology. Semantic attributes used for semantic representation are supported by ontology. Variational Autoencoder (VAE) and Generative Adversarial Network (GAN) network architectures are used together to synthesize visual features. Our work was evaluated on the AWA2 dataset, and improvement in GZSL performance was achieved. [ABSTRACT FROM AUTHOR]

In the era of rapid paper publications in various venues, automatic citation recommendations would be highly useful to researchers when they write papers. Local citation recommendation aims to recommend possible papers to cite given local citation contexts. Previous work mainly computes the similarity score between citation contexts and cited papers on a one-to-one basis, which is quite time-consuming. We train a pair of neural network encoders that map citation contexts and all possible cited papers to the same vector space, respectively. After that, we index the positions of all cited papers in the vector space. This makes our process for searching recommended papers considerably faster. On the other hand, existing methods tend to recommend papers that are highly similar to each other, which makes recommendations lack diversity. Therefore, we extend our algorithm to perform multi-topic recommendations. We generate multi-topic training examples based on the index we mentioned earlier. Furthermore, we specially design a multi-group contrastive learning method to train our model so that it can distinguish different topics. Empirical experiments show that our model outperforms previous methods by a wide margin. Our model is also light weighted and has been deployed online so that researchers can use it to obtain recommended citations for their own paper in real-time. • Proposed FLCR algorithm with sentence-transformer & k-d tree. • Introduced multi-topic citation recommendation for diverse contexts. • Developed large-scale dataset with 1.7 million citation contexts for evaluation. • Demonstrated significant performance improvement over previous methods. • Deployed demo for real-time citation recommendations. [ABSTRACT FROM AUTHOR]

Automatic themes-based classification of Quran verses is the process of classifying verses to predefined categorizes or themes. It is an essential task for all Muslims and people interested in studying the Quran. Quran themes-based classification could be used in many natural language processing (NLP) fields such as search engines, data mining, question–answering systems, and information retrieval applications. This paper presents an ensemble multi-label classification model that automatically identifies and classifies the Quran verses based on themes/topics. The model is composed of four phases: pre-processing, data vectorization, binary relevance classifier, and voting module. Firstly, the verses of the second chapter of the Quran (Al-Baqarah) are tokenized and normalized. Then, the topics of these verses are manually labeled based on "Mushaf Al-Tajweed" classification. Secondly, verses are converted into features' vectors using term frequency-inverse document frequency (TF-IDF) and word2vec techniques. Word2vec is used to consider the semantic meaning of Quranic words and to improve performance. Also, they are trained on a collected classic Arabic corpus of 200 million words. Then, the binary relevance multi-label classification technique is applied using three different classifiers: logistic regression, support vector machine, and random forest, which categorize verses into 393 topics/tags. Finally, the voting module is applied by picking the tags with the maximum prediction probability among the three classifiers. The results of the three classifiers and the ensemble model are compared against "Mushaf Al-Tajweed." The ensemble model outperforms the three classifiers. Its average hamming loss, recall, precision, and F1-Score are 0.224, 81%, 75%, and 77%, respectively. [ABSTRACT FROM AUTHOR]

• Our approach outperforms previous ones in identifying different query types. • Our approach has practical advantages related to the reduced number of features. • RandomForest outperformed other algorithms with 99.6% accuracy. In real-life classification problems, prior information about the problem and expert knowledge about the domain are often used to obtain reliable and consistent solutions. This is especially true in fields where the data is ambiguous, such as text, in which the same words can be used in seemingly similar texts, but have a different meaning. A promising avenue for text classification is machine learning, which has been shown to perform well in a variety of applications including query classification and sentiment analysis. Many of the proposed approaches rely on the bag-of-words representation, which loses the information about the structure of the text. In this paper, we propose a Customised Grammar Framework for text classification, which exploits domain-related information and a new way to represent text as a series of syntactic categories forming syntactic patterns. The framework employs a formal grammar approach for transforming the text into the syntactic patterns representation. We applied the framework for the query classification problem and our results show that our approach outperforms previous ones in terms of classification performance. [ABSTRACT FROM AUTHOR]

We study the problem of entity salience by proposing the design and implementation of Swat, a system that identifies the salient Wikipedia entities occurring in an input document. Swat consists of several modules that are able to detect and classify on‐the‐fly Wikipedia entities as salient or not, based on a large number of syntactic, semantic, and latent features properly extracted via a supervised process, which has been trained over millions of examples drawn from the New York Times corpus. The validation process is performed through a large experimental assessment, eventually showing that Swat improves known solutions over all publicly available datasets. We release Swat via an API that we describe and comment in the paper to ease its use in other software. [ABSTRACT FROM AUTHOR]

Stemming is the basic operation in Natural language processing (NLP) to remove derivational and inflectional affixes without performing a morphological analysis. This practice is essential to extract the root or stem. In NLP domains, the stemmer is used to improve the process of information retrieval (IR), text classifications (TC), text mining (TM) and related applications. In particular, Urdu stemmers utilize only uni-gram words from the input text by ignoring bigrams, trigrams, and n-gram words. To improve the process and efficiency of stemming, bigrams and trigram words must be included. Despite this fact, there are a few developed methods for Urdu stemmers in the past studies. Therefore, in this paper, we proposed an improved Urdu stemmer, using hybrid approach divided into multi-step operation, to deal with unigram, bigram, and trigram features as well. To evaluate the proposed Urdu stemming method, we have used two corpora; word corpus and text corpus. Moreover, two different evaluation metrics have been applied to measure the performance of the proposed algorithm. The proposed algorithm achieved an accuracy of 92.97% and compression rate of 55%. These experimental results indicate that the proposed system can be used to increase the effectiveness and efficiency of the Urdu stemmer for better information retrieval and text mining applications. [ABSTRACT FROM AUTHOR]

This paper describes our approach to developing the Turkish PropBank by adopting the semantic role-labeling guidelines of the original PropBank and using the translation of the English Penn-TreeBank as a resource. We discuss the semantic annotation process of the PropBank and language-specific cases for Turkish, the tools we have developed for annotation, and quality control for multiuser annotation. In the current phase of the project, more than 9500 sentences are semantically analyzed and predicate-argument information is extracted for 1330 verbs and 1914 verb senses. Our plan is to annotate 17,000 sentences by the end of 2017. [ABSTRACT FROM AUTHOR]

The epidemic spread of fake news is a side effect of the expansion of social networks to circulate news, in contrast to traditional mass media such as newspapers, magazines, radio, and television. Human inefficiency to distinguish between true and false facts exposes fake news as a threat to logical truth, democracy, journalism, and credibility in government institutions. In this paper, we survey methods for preprocessing data in natural language, vectorization, dimensionality reduction, machine learning, and quality assessment of information retrieval. We also contextualize the identification of fake news, and we discuss research initiatives and opportunities. [ABSTRACT FROM AUTHOR]

Background and Objective: Question answering (QA), the identification of short accurate answers to users questions written in natural language expressions, is a longstanding issue widely studied over the last decades in the open-domain. However, it still remains a real challenge in the biomedical domain as the most of the existing systems support a limited amount of question and answer types as well as still require further efforts in order to improve their performance in terms of precision for the supported questions. Here, we present a semantic biomedical QA system named SemBioNLQA which has the ability to handle the kinds of yes/no, factoid, list, and summary natural language questions.Methods: This paper describes the system architecture and an evaluation of the developed end-to-end biomedical QA system named SemBioNLQA, which consists of question classification, document retrieval, passage retrieval and answer extraction modules. It takes natural language questions as input, and outputs both short precise answers and summaries as results. The SemBioNLQA system, dealing with four types of questions, is based on (1) handcrafted lexico-syntactic patterns and a machine learning algorithm for question classification, (2) PubMed search engine and UMLS similarity for document retrieval, (3) the BM25 model, stemmed words and UMLS concepts for passage retrieval, and (4) UMLS metathesaurus, BioPortal synonyms, sentiment analysis and term frequency metric for answer extraction.Results and Conclusion: Compared with the current state-of-the-art biomedical QA systems, SemBioNLQA, a fully automated system, has the potential to deal with a large amount of question and answer types. SemBioNLQA retrieves quickly users' information needs by returning exact answers (e.g., "yes", "no", a biomedical entity name, etc.) and ideal answers (i.e., paragraph-sized summaries of relevant information) for yes/no, factoid and list questions, whereas it provides only the ideal answers for summary questions. Moreover, experimental evaluations performed on biomedical questions and answers provided by the BioASQ challenge especially in 2015, 2016 and 2017 (as part of our participation), show that SemBioNLQA achieves good performances compared with the most current state-of-the-art systems and allows a practical and competitive alternative to help information seekers find exact and ideal answers to their biomedical questions. The SemBioNLQA source code is publicly available at https://github.com/sarrouti/sembionlqa. [ABSTRACT FROM AUTHOR]