Loading...
Search for:
word-embedding
0.006 seconds
Deep Compositional Captioner
, M.Sc. Thesis Sharif University of Technology ; Esfahani Zadeh, Mostafa (Supervisor) ; Kamali Tabrizi, Mostafa (Co-Supervisor) ; Moghadasi, Jamshid (Co-Supervisor)
Abstract
One of the most important applications of artificial intelligence, and especially deep learning is image captioning. Given an image, the task is to automatically produce a sentence, describing the image. Image captioning has several real world applications like helping the blind understanding the images, generating automatic captions for the social media, etc. In the past, several different methods for image captioning have been used, but after the emergence of deep learning, like many other areas, image captioning algorithms have been improved significantly. In this thesis, I talk about a specific method for image captioning, called ”Deep Compositional Captioning. In this method, at first...
Improving Persian Word Embeddings Using Neural Networks
, M.Sc. Thesis Sharif University of Technology ; Sameti, Hossein (Supervisor) ; Bokaei, Mohammad Hadi (Co-Supervisor)
Abstract
In recent years, word embeddings as the word representation have captured the attention of natural language processing (NLP) researches. One of the great advantages of word embeddings is their capability in representing the relationships of the words. Therefore, using word embeddings in NLP applications results in better performance.Despite widespread attention towards word embedding in late years, Persian word embeddings have not achieved sensible progress. One of the Persian word embeddings difficulties is related to that, Persian is a low-resource language in comparison with worldwide languages. Therefore, Persian word embedding quality is lower than English. Consequently, the accuracy of...
Persian word embedding evaluation benchmarks
, Article 26th Iranian Conference on Electrical Engineering, ICEE 2018, 8 May 2018 through 10 May 2018 ; 2018 , Pages 1583-1588 ; 9781538649169 (ISBN) ; Bokaei, M. H ; Shoeleh, F ; Yadollahi, M. M ; Doostmohammadi, E ; Farhoodi, M ; Sharif University of Technology
Institute of Electrical and Electronics Engineers Inc
2018
Abstract
Recently, there has been renewed interest in semantic word representation also called word embedding, in a wide variety of natural language processing tasks requiring sophisticated semantic and syntactic information. The quality of word embedding methods is usually evaluated based on English language benchmarks. Nevertheless, only a few studies analyze word embedding for low resource languages such as Persian. In this paper, we perform such an extensive word embedding evaluation in Persian language based on a set of lexical semantics tasks named analogy, concept categorization, and word semantic relatedness. For these evaluation tasks, we provide three benchmark data sets to show the...
Performance Evaluation and Improvement of Duplicate Question Detection in Developers’ Online Q&A Community
, M.Sc. Thesis Sharif University of Technology ; Habibi, Jafar (Supervisor)
Abstract
In this research, we study one of the challenges in the field of software engineering, namely the detection of diplicate questions in Stackoverflow, the Q&A community of programmers. The works done in this area has problems such as complexity and reduced performance over time. The proposed solution is based on machine learning and modern representation learning methods. Representation is done with two approaches, domain specific learning and transfer learning. Fasttext and GloVe, the two word embeddings used in domain specific learning, and in transfer learning, the embedding of the universal sentence encoder has been used. Support vector machine and multilayer perceptron used as...
Test Reuse in GUI-Based Applications Using Word Embedding
,
M.Sc. Thesis
Sharif University of Technology
;
Heydarnoori, Abbas
(Supervisor)
Abstract
Testing is one of the most important and time-consuming steps in the Software Development Life Cycle. Especially, in recent methodologies like agile in which change is an important feature and they take place in iterations with each iteration taking place in a limited time. Recent studies suggest approaches to automatically generate test cases for the applications. For GUI-based applications, test cases are composed of a chain of events that are activated by the user. For these applications, we can generate test cases by simulating the chain of events that get activated by the user. Semantic-based approaches use the semantic matching of the events and their related widgets, to generate test...
Persian language modeling using recurrent neural networks
, Article 9th International Symposium on Telecommunication, IST 2018, 17 December 2018 through 19 December 2018 ; 2019 , Pages 207-210 ; 9781538682746 (ISBN) ; Bahrani, M ; Veisi, H ; Besharati, S ; Sharif University of Technology
Institute of Electrical and Electronics Engineers Inc
2019
Abstract
In this paper, recurrent neural networks are applied to language modeling of Persian, using word embedding as word representation. To this aim, unidirectional and bidirectional Long Short-Term Memory (LSTM) networks are used, and the perplexity of Persian language models on a 100-million-word data set is evaluated. The effect of various parameters, including number of hidden layers and size of LSTM units, on the performance of the networks in reducing the perplexity of the models are investigated. Among different LSTM language models, the best perplexity, which is equal to 59.05, is achieved from a 2-layer bidirectional LSTM model. Comparing this value with the perplexity of the classical...
Discovering associations among technologies using neural networks for tech-mining
, Article IEEE Transactions on Engineering Management ; 2020 ; Veisi, H ; Fateh rad, M ; Rahmani, R ; Sharif University of Technology
Institute of Electrical and Electronics Engineers Inc
2020
Abstract
In both public and private sectors, critical technology-based tasks, such as innovation, forecasting, and road-mapping, are faced with unmanageable complexity due to the ever-expanding web of technologies which can range into thousands. This context cannot be easily handled manually or with efficient speed. However, more precise and insightful answers are expected. These answers are the fundamental challenge addressed by tech-mining. For tech-mining, discovering the associations among them is a critical task. These associations are used to form a weighted directed graph of technologies called “association tech-graph” which is used for technology development, trend analysis, policymaking,...