News

June, 2024
A UniDive Summer School took place at our faculty, 70 participants from more than 29 countries came to Moldova, to learn about the UniDive project, corpus annotation, multi-word expressions, Technical University of Moldova, our country and its capital, Chisinau.

February, 2024
Our colleague Daniela Istrati Defended her thesis "Optimization methods and interfaces in the organization of production systems".
CONGRATULATIONS!

October, 2023
A visit to the Friedrich Schiller University in Jena, Germany for the exchange of experience in corpus annotation.

April, 2023
We presented our work at the "Smart Diaspora - diaspora in higher education, science, innovation and entrepreneurship" conference that took place in Timișoara.

March, 2023
First UNIDIVE general meeting took place at Paris-Saclay University, France. We participated in the work of Working Groups WG1: Corpus annotation and WG2: Lexicon-corpus interface. Also, we presented our work on the Romaninan Non-standard corpus pdf.

November 2022
We were co-organizers of the conference ConsiLR 2022 dedicated to Linguistic resources and tools for natural language processing. The materials can be found on the program page.

July, 2022
COST action Universality, diversity and idiosyncrasy in language technology (UniDive) in which we participate has been approved! The project is for four years: 2023-2026. The first project meeting has been held in Brussels October, 23. The next one is expected in Paris in March 2023.

June 2022
Our students created several interesting theses. One of the theses written by Burlea Tatiana is an application that estimates phonosemantics of Russian words. So far, we had such application for Romanian.

2020-2021
The years have been difficult; we concentrated on the transformation of our teaching at the university into online format. Unfortunately, our research suffered.

December 2019
We were invited to the International Conference Language Technologies for All (LT4All) organized in UNESCO Headquarters, Paris, France. We presented our work on the old and regional Romanian texts.

2018
This year our research has been dedicated to the morphological and syntactic annotation of old Romanian texts and foklore from Moldova. We entered the UD family with Romanian Non-Standard corpus joining our efforts with Catalina Maranduc, PhD student at Alexandru Ioan Cuza University, Iaşi, Romania.

2017
This year our research has been dedicated to the annotation of sentuments in user generated texts. We annotated English texts from a forum via the special interface and Russian and Ukrainian news texts via the other interface. The texts have been provided by Olga Kanishcheva from Kharkov Polytechnic Institute. The resulting annotated corpora can be obtained by addressing victoria.bobicev@ia.utm.md

March, 2016
Through the joint efforts of students and teachers, an online version of the associative dictionary of the Romanian language was created. There are two interfaces: to consult the dictionary and to add new associations. If you know Romanian you can try it.

august, 2015
Anatol Popescu, the ideological inspirer and organizer of our research group, has passed away. His energy, scientific horizons and leadership abilities were our driving force, which we will sorely miss.

march, 2015
The rezults of Victoria Bobicev research was mentioned in Canadian TV program "The AGENDA" with Steve Paikin.

These results have been published in
Victoria Bobicev, Marina Sokolova, Khaled El Emam, Yasser Jafer, Brian Dewar, Elizabeth Jonker, Stan Matwin. Can Anonymous Posters on Medical Forums be Reidentified? Journal of Medical Internet Research 2013 (Oct 03); 15(10):e215.

October, 2014
An online concordancer has been created in the framework of the international project financed by AUF "Pour le renforcement de la recherche en vue du développement des formations francophones niveau master - La Plateforme du français technique et des technologies de la langue" dedicated to computer assisted French language learning.

The description is here.
Try it, it works with English texts too!

autumn, 2013
Two question-answering systems has been created in the framework of the institutional project "Research in the domain of Information Retrieval with the aim of Question-Answering system creation".

Based on the legislative documents dedicated to the development of science in Moldova provided by IDSI

Based on the laws of Moldova found on official website Registru
Try them!

September, 2012
The scientific-didactic title of Associate Professor has been conferred to Victoria Maxim.
Congratulations!

Summer, 2012
Victoria Boicev had a sabbatical in Ottawa, Canada from mid-June till late August.

Well done, Victoria!

November, 2011
On 5th October 2011 the scientific-didactic title of Associate Professor has been conferred to Victoria Bobicev.
Congratulations!

June, 2011
Our students (Applied Informatics) put online some of our applications:
Ion Badan, gr. IA-081 – the Romanian associative dictionary;
Dan Negară, gr. IA-081 – phonosemantics analysis of Romanian words;
Master students created following applications:
Alexandr Negară, gr. IA-091M, the application Job.Card;
Irina Pushcash, gr. IA-091M, blog with the sentiment analysis system in text;

details...

Aplil, 2011
Our PhD student Tatiana Zidrashco returned home after two year of research in Japan!

Welcome, Tatiana!

January, 2011
Our project "Research in the domain of Information Retrieval with the aim of Question-Answering system creation" has been approved by the government The project is planned for years 2011-2014.

October, 2010
Natalia Burciu, PhD student, left for Germany. She is going to study informatics in Berlin.
We wish you every success in your studies, Natalia!

May, 2010
A second version of Romanian and Russian WordNet-Affect was released and can be downloaded from resources page.
We are working on the third version.

January, 2010
Victoria Anghelush, PhD student, joined our group.

Welcome Victoria!

October, 2009
A first version of Romanian and Russian WordNet-Affect was created and can be downloaded from resources page.
The second one is in process of creation.

April, 2009
Our PhD student Tatiana Zidrashco left for Japan. She is going to carry out her research there for two years.
We wish you every success, Tatiana!

May, 2008
At the Institute of Mathematics and Computer Science of Moldavian Academy of Science
Mrs.Victoria Maxim
defended her PhD thesis
"Computational Analysis of Business Correspondence".
The thesis was confirmed by CNAA on June, 19,
the diploma was released on july 2008

June, 2007
At the Technical University of Moldova
Mrs.Victoria Bobicev
defended her PhD thesis
"Statistical Methods and Algorithms of Text Processing (based on Romanian texts)".
The thesis was confirmed by CNAA on September, 20, 2007.

PostHeaderIcon Resources

The first lexical resource ready for download is Romanian and Russian WordNet-Affect. We presented it in Sokolova M., Bobicev V. "Classification of Emotion Words in Russian and Romanian Languages". Proceedings of RANLP-2009 conference, Borovets, Bulgaria, pp. 415-419, 2009. pdf
We plan to continue our work. An updated version of our resource will be posted as soon as it is ready.

  WordNet-Affect translated in Romanian and Russian.

  WordNet-Affect is a lexical resource that contains information about emotions the words convey. It has been developed from the lexical knowledge base WordNet, through a selection and labelling of the affective concepts represented by sets of synonyms. Affective labels (a-labels) were manually assigned to Word Net synsets of nouns, adjectives, verbs and adverbs which convey affective meaning. Words labelled with the Emotion tag were further reannotated into six emotional categories: joy, fear, anger, sadness, disgust, surprise. Word Net-Affect is freely available for research purposes at http://wndomains.itc.it. The collection of WORDNET-AFFECT synsets used in our work was provided as a resource in SemEval-2007 Affective Text task focused on text annotation with affective tags. Word Net-Affect is organised in six files: anger.txt, disgust.txt, fear.txt, joy.txt, sadness.txt, surprise.txt. We keep the same data organisation. Data files are arranged as follows:
- each row contains one synset;
- the first letter in the row indicates part of speech: n-noun; a-adjective; v-verb; r-adverb;
- the letter is followed by the synset number;
- English synset definition follows the number and is separated by a tab;
- English synset words are listed separated by spaces;
- Romanian synset words are listed separated by spaces;
- Russian synset words are listed separated by spaces;
- English, Romanian and Russian sets of words are separated by tabs.

  Please cite the following reference in the publications or presentations containing research results obtained through the use of this resource:
Sokolova M., Bobicev V. "Classification of Emotion Words in Russian and Romanian Languages". Proceedings of RANLP-2009 conference, Borovets, Bulgaria, pp. 415-419, 2009.

Download version 1

The second version of Romanian and Russian WordNet-Affect

The next version is aligned with Romanian WordNet accessed at MultiWordNet site. The aligning process was not trivial because WordNet-Affect was created on the base of WordNet 1.6 and MultiWordNet is based on WordNet 2.0. Some synsets were not exactly the same and we could not establish the correspondence. However, most of synsets found in Romanian WordNet were attached to Romanian part of WordNet-Affect. Data files are arranged slightly in another order:
- English synset definition follows the number and is separated by a tab;
- English synset words are listed separated by spaces;
- Russian synset words are listed separated by spaces;
- Romanian synset words are listed separated by spaces;
- For Romanian synsets found in MultiWordNet definition in Romanian follows Romanian synset separated by tab.
The process of multilingual WordNet-Affect creation is described in the paper: "Emotions in words: developing a multilingual WordNet-Affect". CICLING 2010, Iasi, Romania, 2010. pdf

Download version 2

Other resources will appear soon.
Contact Info
Technical University of Moldova
Human Language Engineering Laboratory,
Department of Computer Science and Systems Engineering,
Faculty of Computers, Informatics and Microelectronics,
Technical University of Moldova,
Address: Studentilor str., 9/7, building nr. 3, Chişinău,
Republic of Moldova
Phone: 373 (22) 50-99-01
Fax: 373 (22) 50-99-05