Sharif Digital Repository

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... 

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... 

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... 

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...