A Dialog Manager for Micro-Worlds

Ion, Radu; Badea, Valentin Gabriel; Cioroiu, George; Mititelu, Verginica Barbu; Irimia, Elena; Mitrofan, Maria; Tufiș, Dan

doi:10.24846/v29i4y202003

Cited by 5 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ROBIN, another complex project in which ICIA coordinated one of the component projects (ROBIN-Dialog) provided the community with important linguistic resources for dialogues in Romanian with the robot PEPPER in specified discourse universes (a complex dictionary, a corpus of dialogues) and a general module for managing communication with the robot , (Ion et al, 2020). The ROBIN Technical Acquisition Speech Corpus (RTASC) (Păis , et al, 2021) was created as a read speech corpus in Romanian language to be used for the development of a speechmediated dialog system with a personal robot.…”

Section: Speech Resources and Datasets For Romanian Languagementioning

confidence: 99%

Romanian Language Technology – a view from an academic perspective

Tufiș

2022

INT J COMPUT COMMUN, Int. J. Comput. Commun. Control

View full text Add to dashboard Cite

The article reports on research and developments pursued by the Research Institute for Artificial Intelligence "Mihai Draganescu" of the Romanian Academy in order to narrow the gaps identified by the deep analysis on the European languages made by Meta-Net white papers and published by Springer in 2012. Except English, all the European languages needed significant research and development in order to reach an adequate technological level, in line with the expectations and requirements of the knowledge society.

show abstract

Section: Speech Resources and Datasets For Romanian Languagementioning

confidence: 99%

Romanian Language Technology – a view from an academic perspective

Tufiș

2022

INT J COMPUT COMMUN, Int. J. Comput. Commun. Control

View full text Add to dashboard Cite

show abstract

“…The transition from ruled-based and statistical/fuzzy approaches on language processing [45] to the current neural networks-driven language modelling came with the need for larger and cleaner data, which is required for robust training and evaluation of language-centric AI applications. The field of natural language processing (NLP) has made significant progress in the area of question answering (QA), with a range of datasets available for various types of QA, including extractive, clozecompletion, and open or specialized domain QA [8,15,21,33,34]. In recent years, the performance of QA systems has even surpassed that of humans in some settings [12].…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Language Models on Romanian XQuAD and RoITD datasets

Nicolae

Yadav²,

Tufiș

2023

INT J COMPUT COMMUN, Int. J. Comput. Commun. Control

View full text Add to dashboard Cite

Natural language processing (NLP) has become a vital requirement in a wide range of applications, including machine translation, information retrieval, and text classification. The development and evaluation of NLP models for various languages have received significant attention in recent years, but there has been relatively little work done on comparing the performance of different language models on Romanian data. In particular, the introduction and evaluation of various Romanian language models with multilingual models have barely been comparatively studied. In this paper, we address this gap by evaluating eight NLP models on two Romanian datasets, XQuAD and RoITD. Our experiments and results show that bert-base-multilingual-cased and bertbase- multilingual-uncased, perform best on both XQuAD and RoITD tasks, while RoBERT-small model and DistilBERT models perform the worst. We also discuss the implications of our findings and outline directions for future work in this area.

show abstract