Daniela Gifu | Romanian Academy, Iasi Branch (original) (raw)
Papers by Daniela Gifu
IEEE Conference Proceedings, 2016
This tutorial provides writing about research in data science. The focus will be on writing confe... more This tutorial provides writing about research in data science. The focus will be on writing conference papers and journal articles. The target audience is graduate students, post-doctoral fellows, and early-career faculties. The teaching methodology will include lectures and a heavy hands-on component.
Lecture Notes in Computer Science, 2023
ISD, 2021
In the context of products employing speech recognition, where the speech signal is sent from the... more In the context of products employing speech recognition, where the speech signal is sent from the device to centralized servers that process data, or simply products that involve data storage on servers, privacy for audio data is an important issue, just as it is for other types of data. Ignoring privacy has consequences for both, speakers (information leaks) and server administrators (legal issues). In this paper, we propose a speaker de-identification solution based on sound processing, altering voice characteristics, along with an API. Our solution consisting of pitch shift and noise mix (the latter is an optional augmentation method) has a great speaker de-identification performance, without an important loss in terms of word intelligibility. It is worth mentioning that sometimes the recordings may not be easy to understand in the initial (i.e., not de-identified) form, due to the speaker's pronunciation, talking speed, and other related factors.
International Letters of Social and Humanistic Sciences, Jul 1, 2014
The organizational communication represents an arbitrated process in which the message is sent to... more The organizational communication represents an arbitrated process in which the message is sent to the organization through a planning process and development strategy. The concept of communication has the role to make the connection between people. Human relations are in fact organizational communication interaction; they represent a universal concept because everything in the world is communicated. In a global setting, the information can be common, but also they can adapt in function of the immediate reality. One of the effects of the mass media is to develop the human relations and cultural relations by creating a connection between the members of different community. Communication is an essential condition in human evolution. A communication interaction generates significances, but any human behavior can be seen as an intentional act. A man's experience of many types of interactions represents his personal system (with subjective preferences and objective preferences). The interaction is a complex system and is represented by the state of homeostasis. Social interaction assumes a communication interaction with social-organizational facts: any actions is based on an idea and express the communication idea.
Procedia Computer Science, 2022
Procedia Computer Science, 2022
Communications in computer and information science, 2016
We are interested to develop a technology able to discover entities and relations connecting them... more We are interested to develop a technology able to discover entities and relations connecting them, as expressed in fiction texts. Deciphering these links is a major step in understanding the content of books. In this study we consider the case of imbricated entities, therefore entities realized at the surface text level by imbricated spans. For this research we use the QuoVadis corpus, whose conventions of annotations we describe briefly, same as some statistics on the types of relations, features regarding the relations' arguments and words or expressions functioning as triggers. The approach to recognize the semantic relations is based on patterns extracted from the corpus. The evaluation shows very promising results.
DOAJ (DOAJ: Directory of Open Access Journals), Dec 1, 2017
This paper presents the almost final results of a priority project of the Romanian Academy – the ... more This paper presents the almost final results of a priority project of the Romanian Academy – the Corpus of Contemporary Romanian Language (CoRoLa). The Corpus includes data in both written and spoken forms of the language. The textual collection is made up of publications covering the period from the 2nd World War to our days, while the spoken collection includes only recent recordings.
Music learning (here, thinking of playing piano) without professor can be a real challenge. This ... more Music learning (here, thinking of playing piano) without professor can be a real challenge. This can be difficult to achieve, given some traditional approaches to manage this process are still insufficiently satisfactory. Beyond the wellknown computer-assisted music learning tools (1) screenbased and (2) hardware-based, a promising solution for piano learning is based on augmented reality (AR). This technology provides an ideal environment for the student, but of course, it is not enough to become a career musician. In this paper, we propose an application that helps all those who want to learn to play the piano in a friendly way, starting with understanding sheet music. By projecting information onto the instrument, our AR system can create more direct interactions for the user.
The "Sentiment Analysis for Code-Mixed Social Media Text" task at the SemEval 2020 competition fo... more The "Sentiment Analysis for Code-Mixed Social Media Text" task at the SemEval 2020 competition focuses on sentiment analysis in code-mixed social media text 1 , specifically, on the combination of English with Spanish (Spanglish) and Hindi (Hinglish). In this paper, we present a system able to classify tweets, from Spanish and English languages, into positive, negative and neutral. Firstly, we built a classifier able to provide corresponding sentiment labels. Besides the sentiment labels, we provide the language labels at the word level. Secondly, we generate a word-level representation, using Convolutional Neural Network (CNN) architecture. Our solution indicates promising results for the Sentimix Spanglish-English task (0.744), the team, Lavinia_Ap, occupied the 9th place. However, for the Sentimix Hindi-English task (0.324) the results have to be improved.
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), 2022
Lecture Notes in Computer Science, 2023
The present study describes a method of exploring the Romanian old words collected in the written... more The present study describes a method of exploring the Romanian old words collected in the written press, from 1829 till 2015, and contains three independent collections of newspapers, developed and structured corresponding to Moldavia, Wallachia, and Transylvania. The purpose of this research is to record the chronology of the Romanian old words identified in the diachronic corpus that we have built in the last three years, called RODICA (ROmanian DIachonic Corpus with Annotations), in order to develop a learning technology based on the language evolution. We have used the citations extracted from the eDTLR (Dictionary Thesaurus of the Romanian Language in electronic form), with an important role for eLearning applications. To recover lemmata of old, obsolete, word forms using eDTLR quotations is a target on which NLP group from Iasi has started to work a few years ago and this work contributes significantly in developing a diachronic POS-tagger. A diachronic POS-tagger is very important in different comparative language analyzes of eLearning. However, there is an important problem, which arises, the fact that the corpus contains only quotations and not a complete sentence. One quotation may be attached both to a title-word different than the word searched for or belonging to the searched for title-word. We consider that the model of language that we used could be useful both for applicative objectives (for enabling effective language similarity analysis using statistical methods) and for scientific objectives (for exploring the nature of related languages).
Procedia Computer Science, 2020
I. Any manifestation of life is a component of communication, it is crossed by a communication pa... more I. Any manifestation of life is a component of communication, it is crossed by a communication passage. People irrepressibly generate meanings. As structuring domain of meanings, communication is a place where meanings burst out volcanically. Manifestations of life are surrounded by a halo of communicational meanings. Human material and ideatic existence includes a great potential of communication in continuous extension. The human being crosses the path of or is at the intersection of different communicational thoroughfares. The life of human beings is a place of communication. Consequently, any cognitive or cogitative manifestation presents a route of communication. People consume their lives relating by communicationally. Some communicational relationships are contradictory, others are neutral, since within the manifestations of life there are found conflicting meanings and/or neutral meanings. Communicational relations always comprise a set of neutral, neutrosophic meanings. Communication in general is a human manifestation of life with recognizable profile. Particularly, we talk about scientific communication, literary communication, pictorial communication, sculptural communication, esthetic communication and so on, as specific manifestations of life. All these include coherent, cohesive and structurable series of existential meanings which are contradictory and/or neutral, neutrosophic. It can be asserted that in any communication there are routes of access and neutrosophic routes. Any communication is traversed by neutrosophic routes of communication.
Taking into account the increase in the number of cars and, implicitly, the traffic problems, an ... more Taking into account the increase in the number of cars and, implicitly, the traffic problems, an automatic license plate recognition (ALPR) system becomes a significant task in smart surveillance and transportation. The interest for the implementation and integration of ALPR technology into the daily security operations is visible, although there are still insufficiently resolved issues. They are based on either the help of image processing techniques or deep learning techniques. More precisely, they are using object detection algorithms such as You Only Look Once (YOLO). In order to obtain a system capable of detecting the license plates, we propose a method using YOLOv4. This system achieved impressive frames per second, the results show that we are talking about a method that is relatively insensitive to background variations.
IEEE Conference Proceedings, 2016
This tutorial provides writing about research in data science. The focus will be on writing confe... more This tutorial provides writing about research in data science. The focus will be on writing conference papers and journal articles. The target audience is graduate students, post-doctoral fellows, and early-career faculties. The teaching methodology will include lectures and a heavy hands-on component.
Lecture Notes in Computer Science, 2023
ISD, 2021
In the context of products employing speech recognition, where the speech signal is sent from the... more In the context of products employing speech recognition, where the speech signal is sent from the device to centralized servers that process data, or simply products that involve data storage on servers, privacy for audio data is an important issue, just as it is for other types of data. Ignoring privacy has consequences for both, speakers (information leaks) and server administrators (legal issues). In this paper, we propose a speaker de-identification solution based on sound processing, altering voice characteristics, along with an API. Our solution consisting of pitch shift and noise mix (the latter is an optional augmentation method) has a great speaker de-identification performance, without an important loss in terms of word intelligibility. It is worth mentioning that sometimes the recordings may not be easy to understand in the initial (i.e., not de-identified) form, due to the speaker's pronunciation, talking speed, and other related factors.
International Letters of Social and Humanistic Sciences, Jul 1, 2014
The organizational communication represents an arbitrated process in which the message is sent to... more The organizational communication represents an arbitrated process in which the message is sent to the organization through a planning process and development strategy. The concept of communication has the role to make the connection between people. Human relations are in fact organizational communication interaction; they represent a universal concept because everything in the world is communicated. In a global setting, the information can be common, but also they can adapt in function of the immediate reality. One of the effects of the mass media is to develop the human relations and cultural relations by creating a connection between the members of different community. Communication is an essential condition in human evolution. A communication interaction generates significances, but any human behavior can be seen as an intentional act. A man's experience of many types of interactions represents his personal system (with subjective preferences and objective preferences). The interaction is a complex system and is represented by the state of homeostasis. Social interaction assumes a communication interaction with social-organizational facts: any actions is based on an idea and express the communication idea.
Procedia Computer Science, 2022
Procedia Computer Science, 2022
Communications in computer and information science, 2016
We are interested to develop a technology able to discover entities and relations connecting them... more We are interested to develop a technology able to discover entities and relations connecting them, as expressed in fiction texts. Deciphering these links is a major step in understanding the content of books. In this study we consider the case of imbricated entities, therefore entities realized at the surface text level by imbricated spans. For this research we use the QuoVadis corpus, whose conventions of annotations we describe briefly, same as some statistics on the types of relations, features regarding the relations' arguments and words or expressions functioning as triggers. The approach to recognize the semantic relations is based on patterns extracted from the corpus. The evaluation shows very promising results.
DOAJ (DOAJ: Directory of Open Access Journals), Dec 1, 2017
This paper presents the almost final results of a priority project of the Romanian Academy – the ... more This paper presents the almost final results of a priority project of the Romanian Academy – the Corpus of Contemporary Romanian Language (CoRoLa). The Corpus includes data in both written and spoken forms of the language. The textual collection is made up of publications covering the period from the 2nd World War to our days, while the spoken collection includes only recent recordings.
Music learning (here, thinking of playing piano) without professor can be a real challenge. This ... more Music learning (here, thinking of playing piano) without professor can be a real challenge. This can be difficult to achieve, given some traditional approaches to manage this process are still insufficiently satisfactory. Beyond the wellknown computer-assisted music learning tools (1) screenbased and (2) hardware-based, a promising solution for piano learning is based on augmented reality (AR). This technology provides an ideal environment for the student, but of course, it is not enough to become a career musician. In this paper, we propose an application that helps all those who want to learn to play the piano in a friendly way, starting with understanding sheet music. By projecting information onto the instrument, our AR system can create more direct interactions for the user.
The "Sentiment Analysis for Code-Mixed Social Media Text" task at the SemEval 2020 competition fo... more The "Sentiment Analysis for Code-Mixed Social Media Text" task at the SemEval 2020 competition focuses on sentiment analysis in code-mixed social media text 1 , specifically, on the combination of English with Spanish (Spanglish) and Hindi (Hinglish). In this paper, we present a system able to classify tweets, from Spanish and English languages, into positive, negative and neutral. Firstly, we built a classifier able to provide corresponding sentiment labels. Besides the sentiment labels, we provide the language labels at the word level. Secondly, we generate a word-level representation, using Convolutional Neural Network (CNN) architecture. Our solution indicates promising results for the Sentimix Spanglish-English task (0.744), the team, Lavinia_Ap, occupied the 9th place. However, for the Sentimix Hindi-English task (0.324) the results have to be improved.
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), 2022
Lecture Notes in Computer Science, 2023
The present study describes a method of exploring the Romanian old words collected in the written... more The present study describes a method of exploring the Romanian old words collected in the written press, from 1829 till 2015, and contains three independent collections of newspapers, developed and structured corresponding to Moldavia, Wallachia, and Transylvania. The purpose of this research is to record the chronology of the Romanian old words identified in the diachronic corpus that we have built in the last three years, called RODICA (ROmanian DIachonic Corpus with Annotations), in order to develop a learning technology based on the language evolution. We have used the citations extracted from the eDTLR (Dictionary Thesaurus of the Romanian Language in electronic form), with an important role for eLearning applications. To recover lemmata of old, obsolete, word forms using eDTLR quotations is a target on which NLP group from Iasi has started to work a few years ago and this work contributes significantly in developing a diachronic POS-tagger. A diachronic POS-tagger is very important in different comparative language analyzes of eLearning. However, there is an important problem, which arises, the fact that the corpus contains only quotations and not a complete sentence. One quotation may be attached both to a title-word different than the word searched for or belonging to the searched for title-word. We consider that the model of language that we used could be useful both for applicative objectives (for enabling effective language similarity analysis using statistical methods) and for scientific objectives (for exploring the nature of related languages).
Procedia Computer Science, 2020
I. Any manifestation of life is a component of communication, it is crossed by a communication pa... more I. Any manifestation of life is a component of communication, it is crossed by a communication passage. People irrepressibly generate meanings. As structuring domain of meanings, communication is a place where meanings burst out volcanically. Manifestations of life are surrounded by a halo of communicational meanings. Human material and ideatic existence includes a great potential of communication in continuous extension. The human being crosses the path of or is at the intersection of different communicational thoroughfares. The life of human beings is a place of communication. Consequently, any cognitive or cogitative manifestation presents a route of communication. People consume their lives relating by communicationally. Some communicational relationships are contradictory, others are neutral, since within the manifestations of life there are found conflicting meanings and/or neutral meanings. Communicational relations always comprise a set of neutral, neutrosophic meanings. Communication in general is a human manifestation of life with recognizable profile. Particularly, we talk about scientific communication, literary communication, pictorial communication, sculptural communication, esthetic communication and so on, as specific manifestations of life. All these include coherent, cohesive and structurable series of existential meanings which are contradictory and/or neutral, neutrosophic. It can be asserted that in any communication there are routes of access and neutrosophic routes. Any communication is traversed by neutrosophic routes of communication.
Taking into account the increase in the number of cars and, implicitly, the traffic problems, an ... more Taking into account the increase in the number of cars and, implicitly, the traffic problems, an automatic license plate recognition (ALPR) system becomes a significant task in smart surveillance and transportation. The interest for the implementation and integration of ALPR technology into the daily security operations is visible, although there are still insufficiently resolved issues. They are based on either the help of image processing techniques or deep learning techniques. More precisely, they are using object detection algorithms such as You Only Look Once (YOLO). In order to obtain a system capable of detecting the license plates, we propose a method using YOLOv4. This system achieved impressive frames per second, the results show that we are talking about a method that is relatively insensitive to background variations.