Staff
Albina Sarymsakova

Computational linguist, graduated in Hispanic Philology from Kazan Federal University and PhD in Linguistic Studies (Cum Laude and International Mention) from Universidade da Coruña, with an award-winning thesis (Extraordinary Doctoral Awards, UDC) in linguistic technologies and multimodal discourse analysis of native and non-native speakers of Spanish. She is co-developer of Plugin para el análisis fonético-fonológico en español, a proprietary software tool for instant comparative pronunciation analysis of native and non-native speakers of Spanish. Member of the Sociedad Española del Procesamiento de Lenguaje Natural.
Research topics.
His main interests are in interdisciplinary areas including oral and written discourse analysis and processing, development of linguistic technologies and digital humanities. This includes multimodal studies of orality, speech synthesis, artificial intelligence technologies for language processing and their application in different domains (historical and socio-cultural). His main research line at IEGPS focuses on emotion recognition and annotation in historical corpora, using artificial intelligence tools.
Other activities.
Currently, she is an external researcher in the “Proxecto Nós” whose main objective is the development of artificial intelligence technologies for Galician. She has actively collaborated with several international research groups, including the Grupo Red Complejidad y Lenguaje of La Habana (Cuba), the CODISCO project ("La construcción discursiva del conflicto: territorialidad, imagen de la enfermedad e identidades de género en la literatura y la comunicación social), funded by the Ministerio de Industria y Competitividad and Feder funds (Code: FFI2017-85227-R, Period: 2018-21), and the R&D&I Project ”DeepR3. gal: Reducing, Reusing and Recycling large models for developing Responsible and Green Language Technologies” (TED2021-130295BC33) of CiTIUS-USC.
He has participated in conferences such as the VI Congress of the International Society for Hispanic Digital Humanities and the International Congress on Computational Processing of Portuguese (PROPOR-2024) and has also been part of the local organizing committee of the European Conference on Artificial Intelligence (ECAI-2024).
Recent publications
Albina Sarymsakova, Xulia Sánchez-Rodríguez and Marcos Garcia
“Towards accurate dependency parsing for Galician with limited resources”, Procesamiento del lenguaje natural, 73 (2024), pp. 247-257. doi 10.26342/2024-73-18. Available at: http://journal.sepln.org/sepln/ojs/ojs/index.php/pln/article/download/6614/4006
Albina Sarymsakova and Patricia Martin Rodilla
"Análisis acústico-digital de la entonación del español hablado por anglófonos", Revista de Humanidades Digitales 9 (2024), pp. 167-86. https://doi.org/10.5944/rhd.vol.9.2024.40146
Xulia Sánchez Rodríguez, Albina Sarymsakova, Laura Castro, and Marcos Garcia
“Increasing manually annotated resources for Galician: the Parallel Universal Dependencies Treebank”, in Proceedings of the 16th International Conference on Computational Processing of Portuguese, vol. 1 (2024), Santiago de Compostela, Galicia/Spain, Association for Computational Lingustics, pp. 587–592. Available at: https://aclanthology.org/2024.propor-1.65/
Albina Sarymsakova and Patricia Martín Rodilla
“Software-Assisted Identification of Non-Native Pitch Elements for Russian-Speaking Learners of Spanish”, Loquens 10 (1-2),e104 (2023). https://doi.org/10.3989/loquens.2023.e104
Tamara Couto Fernández, Albina Sarymsakova, Nelly Condori Fernández and Patricia Martín Rodilla
“Plugin for Automatisation of Phonetic-Phonological Analysis and Obtaining Analytical Feedback for Spanish Learners”, Annual Conference of the Spanish Association for Natural Language Processing (2022), A Coruña, Spain, pp. 83-87. available at: https://ceur-ws.org/Vol-3224/paper20.pdf
“Actos de habla indirectos y su interpretación en el marco prosódico y gestual en interacciones en español de aprendices rusos”, Phonica, 18 (2022), págs 24-45. https://doi.org/10.1344/phonica.2022.18.24-45