Yazar "Yildirim, S." seçeneğine göre listele
Listeleniyor 1 - 9 / 9
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Anaphoric Ambiguity Resolution in Software Requirement Texts(Institute of Electrical and Electronics Engineers Inc., 2023) Jafari, S.M.; Yildirim, S.; Cevik, M.; Basar, A.In requirements engineering (RE), anaphoric ambiguity is a frequent cause of misunderstandings. It can have a detrimental effect on the quality of requirements and jeopardize the success of a project. If stakeholders of the system, such as testers, developers, or customers, have different understandings or interpretations of software requirements, the system may not be accepted during customer validation. Despite its significance, there has been limited investigation into anaphoric ambiguity in RE. However, focusing on both recognizing and solving uncertainty can be more advantageous than just identifying it. Therefore we investigated the effectiveness of various QA learning techniques including encoder-based and text generation-based NLP models for two goals. We conduct detailed numerical experiments using various transformer models on two public requirements datasets and one generic dataset. Our results indicated that our QA architecture exhibits superior performance compared to baseline models in detecting ambiguity as well as resolving anaphora in contrast to other baseline approaches. We showed that our developed architecture can automatically support requirement development to minimize interpretation risk between stakeholders. © 2023 IEEE.Öğe Association rule based acquisition of hyponym and hypernym relation from a Turkish corpus(2012) Yildiz, T.; Yildirim, S.In this paper, we propose a method for the automatic acquisition of hypernym/hyponymy relations from a Turkish raw text. Once the model has extracted prospective hyponyms by using lexico-syntactic patterns, an Apriori algorithm is applied to eliminate faulty hyponyms and increase precision. We show that a model based on a particular lexico-syntactic pattern and association rules for Turkish language can successfully retrieve many is-a relation with high precision. © 2012 IEEE.Öğe Building Domain-Specific Lexicons: An Application to Financial News(Institute of Electrical and Electronics Engineers Inc., 2019) Yildirim, S.; Jothimani, D.; Kavaklio?lu, C.; Bener, A.Natural Language Processing (NLP) has gained attention in the recent years. Previous research (such as WordNet and Cyc) has focused on developing an all purpose (generalised) polarised lexicons. However, these lexicons do not provide much information in different domains such as Finance and Medical Sciences. Using these lexicons for text classification could affect the prediction accuracy. Therefore, there is a need for building domain- and context-specific lexicons. To achieve this, in this work, a label based propagation based word embedding algorithm has been proposed to obtain positive and negative lexicons. The proposed algorithm works on the principle of graph theory and word embedding. The proposed algorithm is tested on Dow Jones news wires text feed to classify the Financial news as hot and non-hot. Three classifiers, namely, Logistic Regression, Random Forest and XGBoost, employing polarised lexicons, seed words and random words were used. The performance of classifiers in all cases was evaluated using accuracy. Lexicons generated using the proposed approach were effective in classifying the Financial news articles as hot and non-hot compared to classifiers using seed words and random words. Proposed label propagation with word embedding algorithm generates context-specific lexicons, which aids in helps in better representation of text in natural processing tasks and avoids the problem of dimensionality. © 2019 IEEE.Öğe Classification of »hot News» for Financial Forecast Using NLP Techniques(Institute of Electrical and Electronics Engineers Inc., 2018) Yildirim, S.; Jothimani, D.; Kavaklioglu, C.; Başar, A.Complex dynamics of stock market could be attributed to various factors ranging from company's financial ratios to investors' sentiment and reaction to Financial news. The paper aims to classify Financial news articles as »hot» (significant) and »non-hot» (non-significant). The study is carried out using Dow Jones newswires text feed for a period of four years spanning from 2013 till 2017. Bag-of-ngrams appraoch and Term Frequency-Inverse Document Frequency (TF-IDF) were used for text representation and text weighting, respectively. Four linear classifiers, namely, Logistic Regression (LR), Support Vector Machine (SVM), k Nearest Neighbours (kNN) and multinomial Naïve Bayes (mNB) were used. Grid search was used for hyperparameter optimisation. Performance of the classifiers was evaluated using five measures, namely, success rate, precision, recall, F1 measure and area under receiver operating characteristics curve. LR and SVM outperformed other models in terms of all five performance measures for both Bag-of-ngrams model and Bag-of-ngrams model with TF-IDF approach. Use of TF-IDF improved performance of the classifiers, especially, in case of mNB. This study serves as a stepping stone in identification of important/relevant news, which could used as predictors for stock price forecasting. © 2018 IEEE.Öğe Corpus-driven hyponym acquisition for Turkish language(2012) Yildirim, S.; Yildiz, T.In this study, we propose a method for acquisition of hyponymy relations for the Turkish Language. This integrated method relies on both lexico-syntactic pattern and semantic similarity. Once the model has extracted the items using patterns it applies similarity based elimination of the incorrect ones in order to increase precision. We show that the algorithm based on a particular lexico-syntactic pattern for Turkish language can retrieve many hyponymy relations and also demonstrate that elimination based on semantic similarity gives promising results. We discuss how we measure the similarity between the concepts. The objective is to get better relevance and more precise results. The experiments show that this approach gives successful results with high precision. © 2012 Springer-Verlag.Öğe Extraction of part-whole relations from Turkish corpora(2013) Yildiz, T.; Yildirim, S.; Diri, B.In this work, we present a model for semi-automatically extracting part-whole relations from a Turkish raw text. The model takes a list of manually prepared seeds to induce syntactic patterns and estimates their reliabilities. It then captures the variations of part-whole candidates from the corpus. To get precise meronymic relationships, the candidates are ranked and selected according to their reliability scores. We use and compare some metrics to evaluate the strength of association between a pattern and matched pairs. We conclude with a discussion of the result and show that the model presented here gives promising results for Turkish text. © 2013 Springer-Verlag.Öğe Leveraging the power of Natural Language Processing for Financial Intelligence System(Institute of Electrical and Electronics Engineers Inc., 2022) Ugur, O.; Kalay, T.; Demirel, O.; Yildirim, S.In this study, we aim to exploit natural language processing (NLP) techniques to develop a financial intelligence system that understands and analyzes online news channels on the basis of companies filtered by specific keywords. The system enables us to immediately notify potential opportunities and threats that may arise for the relevant company portfolio and to take the necessary actions. The architecture can enrich portfolio management, increase a company's credit profitability, offer finance-specific functions and use time and resources effectively in collecting and evaluating information through various metrics. In this direction, we designated an infrastructure and addressed a wide variety of NLP issues to execute the system modules. Various NLP tasks such as text classification, text regression, impact measurement, and Named-Entity Recognition have been successfully solved with the latest techniques. Not only traditional machine learning techniques but also modern deep learning architectures such as RNN and Transformers have been utilized to solve financial tasks. © 2022 IEEE.Öğe A machine learning approach to personal pronoun resolution in Turkish(2007) Yildirim, S.; Kiliçaslan, Y.In this paper, we present a machine learning based approach for estimating antecedents of anaphorically used personal pronouns in Turkish sentences using a decision tree classification technique coupled with the ensemble learning method. The technique learns from an annotated corpus, which has been compiled mostly from various popular child stories. Copyright © 2007, American Association for Artificial Intelligence (www.aaai.org). All rights reserved.Öğe The Refugee Crisis in the Croatian Digital News: Towards a Computational Political Economy of Communication(International Association of Media Communication Research, 2018) Bili?, P.; Furman, I.; Yildirim, S.This article tests how media ownership and political leanings influenced textual and linguistic output in the production of narratives during the 2015 refugee crisis in Europe. We focused on digital news reports in Croatia, a country that experienced the highest influx of refugees among the Western Balkan countries in late 2015. Ten news organisations were selected to capture various ownership structures and ideological positions. We collected all articles published by these organisations (N = 352) during the two weeks before and two weeks after the sexual attacks that occurred in the German city of Cologne on New Year’s Eve 2015. The dataset was analysed with Natural Language Processing (NLP) and Correspondence Analysis. Our computational political economy of communication (CPEC) approach reveals a relative diversity of concepts used in the sample before the event, and an evident clustering of most viewpoints from media actors in the period after the event. There is a noticeable change from a humanitarian rhetoric to a security-oriented rhetoric that mobilises fear to legitimize stronger control of national borders. Based on the analysis, we argue that the majority of digital news media changed reporting style due to widespread moral panic and the economic incentive to commodify audience interest in the topic of the refugee crisis. In contrast, publicly funded news organizations showed that they provide the necessary counter-balance for informing citizens, producing quality content, and ensuring pluralism in the digital news environment. © The Author 2018
