Sharif Digital Repository

One of the new paradigms in information retrieval is to develop textual Question-Answering systems. Question-Answering (QA) is an advanced IR process at which for a natural language question, the answer is extracted and issued in natural language. The QA systems are divided into two general groups: Open-Domain QA and Restricted-Domain QA.
In this research field, a number of different models and methods are developed in which a document collection is used to retrieve candidate answers and then different methods are deployed to detect and eliminate irrelevant ones from answer set. Most of these methods decide based on expected semantic answer type, which is determined using pre-defined... 

Web service technology is becoming increasingly popular since it is very bene?cial in di?erent types of applications. Due to a dramatical increase in the number of developed web services, the service discovery process has become crucial for using web services e?ciently. Service is an adaptive, self-describing, modular application, which may be used in either web or an internal network. Service providers should o?er the services along with a description ?le called advertisement explaining the speci?cations and functionalities of the service. Traditional service discovery methods are based on syntax and keyword matching, which may not satisfy the requester’s desired requirements and will... 

Temporal relation classification is one of the contemporary demanding tasks in natural language processing. This task can be used in various applications such as question answering, summarization, and language specific information retrieval. Temporal relation classification methods can be categorized into three main groups of supervised, semi-supervised, and unsupervised (based on the type of the training data that they need). In this thesis, we have two main goals: first, improving accuracy of temporal relation learning, and second, decreasing supervision of algorithm as much as possible. For achieving these goals, three main steps are proposed. In the first step, we propose an improved... 

Expert retrieval when the number of experts are limited is an open problem. Undoubtedly, becoming an expert in a field is a time consuming and expensive task; thus finding the best candidates is a crucial task. In addition, passage of time and growth of knowledge could change the view of a person towards life and his work, which may lead to the change of his or her field of work. When considering the changes each person makes in his or her life, it becomes obvious that they are not far from the original status. Therefore, recommending all possible options around a person could really help the task of decision making. This research is addressing two similar issues of finding experts, in a... 

Music information reterival systems have a lot of applications in music filtering and broadcast monitoring due to the huge amount of multimedia data these days. In these systems the feature extraction method is called audio fingerprinting. Small size of fingerprints allows the systems to search efficiently in thousands or millions numbers of audio songs. The input signal is usually just a couple of seconds long and degraded in several ways. The goal is to design a system which is robust to signal degradations and efficient to search. In this thesis one of the basic systems is reviewed and improved in several ways. This system uses spectrogram of signals to extract features and build an... 

Temporal relation extraction is one of the challenging research topics in natural language processing semantic level. The purpose of this kind of extraction is to find the temporal ordering between text events so that they can be used in various applications such as question answering and summarization systems.Most of early researches in temporal relation extractionaimed at finding a number of rules and templates for every single temporal relation in English texts. However, with the availability of temporal corpora in English and some other natural languages like Chinese, Korean, Italian, etc., the research trend in this field turned towards the use of machine learning methods. Accordingly,... 

Measuring emotions of music is one of the methods to determine music content. Music emotion detection is applicable in music retrieval, recognition of music genre and also music data management softwares. Music emotion is considered in different sciences such as physiology, psychology, musicology and engineering. First, we collected a database of different types of music with various emotions. These data have been labeled according to their emotions. In this project, four emotions (Angry, happy, relax and sad) have been used as labels based on Thayer’s two dimension emotion model. There are two basic steps for music emotion recognition similar to other recognition systems: Feature extraction... 

An object-oriented application framework, like Eclipse, not only provides a framework for designing and implementing new applications, but also decreases the time and the cost of developing new software applications. Moreover, theseframeworks increase the maintainability of software systems. Therefore, their popularity is on the rise. The main problem of using object-oriented application frameworks is the lack of proper documentations and guides. Thus, developers often try to learn how to implement their desired concepts (e.g., Context Menu) from available sample applications. This leads the programmers to another problem which is finding the sample applications. Finding a proper sample... 

To fully understanding a text written in a natural language, we need to comprehend the events within that text. Temporal relation extraction always have been one of the main challenges in natural language processing in semantic level. Temporal relation extraction makes the understanding and interpretation of text easier and the extracted information can be used in many natural language systems like question answering, summarization, and information retrieval systems. Early researches on temporal relation extraction was mainly on English and limited to rule based systems. However, with extending the English corpora and availability of temporal corpora in other languages, more attention has... 

There are several applications of wireless sensor networks wherein the data collected by the sensors in the network are critical and hence have to be reliably transported to the sink, example of such applications are fire detection in a forest or controlling vibration on body of dam. Reliable communication in wireless sensor networks is hard to achieve efficiently using methods in conventional systems like Internet. End-to-end retransmission is inefficient, or in some cases impossible. It is well-known that Reed-Solomon codes may be used to provide error correction for multiple failures in RAID-like systems. To the coding theorists, this technique is a straight forward extension to a basic... 

The long-term Attacks are some special multi-level attacks which remain inside of systems for a long time to finally perform the damage. One of the most famous kinds of these attacks is Advanced Persistent Threats. These kinds of attack are low-level, distributed inside of the network and their goal is stealing information or corrupting a process in the organization. Banks are one of the most vulnerable organizations which have suffered from these attacks, so the main purpose of this research is detecting them and give warning to the security admin. The goal of financial APTs is stealing money and to achieve that, they have to create some transactions and send them to the core banking. We... 

Lightweight clients are a type of blockchain users who do not store all the blocks in the blockchain due to limited resources. These users store only a small part of each block and when needed, request transactions from full nodes that store the entire blockchain. These users have no role in block validation and only want to receive transactions related to their addresses with proof of the inclusion in the block from full nodes.Since light clients rely on full nodes for receiving transactions, their privacy against full nodes is important. The current implementation of Bitcoin uses Bloom filters for privacy, but this offers very little privacy to the users.In this thesis, we study the... 

Automatic recognition of musical Maqams has been one of the challenging problems in Music Information Retrieval. Despite the increasing amount of related research in recent years, we are still far away from building related real-life applications. Nevertheless, a very small portion of these research is dedicated to automatic recognition of Maqams in recitation of the Holy Quran. In this thesis, as a first attempt, we have used machine learning methods to classify six Maqam families which are commonly used in Quran recitation. Also, due to the lack of pre-exisiting datasets, we have annotated approximately 1325 minutes of Tadwir recitation from two prominent Egyptian reciters, i.e., Muhammad... 

Prioritizing bug issue report is a critical task in the software maintenance cycle of repositories that have a large number of users and contributors. In such software, late fixing of bugs can cause the loss of users’ trust and market loss. At present, a majority of bug report prioritization is manual, in that the bug issue reports are triaged by human experts. However, new automated technologies are becoming feasible. These automated techniques have been shown to be effective in general situations, though a key weakness is that they do not use the criteria for prioritizing. Most of the state-of-the-art approaches are using machine learning algorithms to learn the different features of... 

A random vector with binary components that are independent of each other is referred to as a Bernoulli random vector. A Bernoulli Mixture Model (BMM) is a combination of a finite number of Bernoulli models, where each sample is generated randomly according to one of these models. The important challenge is to estimate the parameters of a Bernoulli Mixture Model or to cluster samples based on their source models. This problem has applications in bioinformatics, image recognition, text classification, social networks, and more. For example, in bioinformatics, it pertains to clustering ethnic groups based on genetic data. Many studies have introduced algorithms for solving this problem without... 

Nowadays Artificial Intelligence systems are ubiquitous. One of the important applications is textual question-answering systems, which provide a means of information retrieval in a user-friendly manner. Reasoning is an inseparable part of human daily life, and people use reasoning to judge and find rational and correct answers to questions. To get the desired output from question-answering systems, these systems must be equipped with reasoning. This research focuses on improving question answering by considering Commonsense Reasoning. The two most important weaknesses of the existing question-answering systems are the questions being in the form of multiple-choice, which is far from a... 

Rapid growth in science and technology has created vast diversity in products, services and needs of people and groups. As the Internet and web technologies have progressed, a web-based solution to explore products of either a specific domain or multiple domains is mandatory. One of the main challenges in these systems is learning users’ preferences to recommend items possibly interesting to the user. Social network of the users is one of the sources that can inject additional information about them which can be exploited to improve accuracy of the system. Depending on the method, the performance, accuracy and personalization may differ .One of the most popular methods to extract this...