A Novel Question Answering System for Albanian Language

Trandafili, Evis; Meçe, Elinda Kajo; Kica, Kristjan; Paci, Hakik

doi:10.1007/978-3-319-75928-9_46

Cited by 4 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The system was built based on the idea of extracting answers to factoid questions for a given text. Experimental results obtained from the proposed approach were promising and showed that this was an effective solution for single domain documents [26].…”

Section: Question Answering Systemmentioning

confidence: 87%

“…However, to the best of our knowledge, there is only one research work that addressed this problem for the Albanian language. Trandafili et al [26] work is the first study published around question answering system for the Albanian language. The system was built based on the idea of extracting answers to factoid questions for a given text.…”

Section: Question Answering Systemmentioning

confidence: 99%

“…Studies conducted concerning tools include Int J Elec & Comp Eng ISSN: 2088-8708  Natural language processing for Albanian: A state-of-the-art survey (Muhamet Kastrati) 6433 part-of-speech and morphological tagging [3]- [5], stemming [6], the lexicon of Albanian for NLP [7], and syntactic parsing [8]. Also, there are several studies related to the application of the NLP for the Albanian language such as named-entity recognition [9]- [12], sentiment analysis [13]- [16], emotion detection [17], [18], hate speech detection [19], [20], summarization techniques [21], [22], text classification [23]- [25] and question answering system [26].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Natural language processing for Albanian: a state-of-the-art survey

Kastrati¹,

Biba²

2022

IJECE

View full text Add to dashboard Cite

<span lang="EN-US">Due to its wide applicability, natural language processing (NLP) has attracted significant research efforts to the machine learning and deep learning research community. Despite this, research works investigating NLP for the Albanian language are still limited. However, to the best of our knowledge, there is no literature review available, which presents a clear picture of what has been studied, argued, and established in the area. The main objective of this survey is to comprehensively review, analyze and discuss the state-of-the-art in NLP for the Albanian language. Here, we present an extensive study concerning the contribution of several authors that have contributed to the application of NLP to the Albanian language. Also, we present an overview of research carried out in the typical applications of NLP for the Albanian language. Finally, some future challenges and limitations of the area are discussed.</span>

show abstract

Section: Question Answering Systemmentioning

confidence: 87%

Section: Question Answering Systemmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Natural language processing for Albanian: a state-of-the-art survey

Kastrati¹,

Biba²

2022

IJECE

View full text Add to dashboard Cite

show abstract

“…The SVM model achieved the highest accuracy of 75.7% using FastText, while the use of RoBERTa resulted in a slightly lower accuracy of 0.6% [5]. The question-answering system proposed for the Albanian language in [6] does not implement the question classification component. The system has three modules: the first module preprocesses and indexes the documents, the second module analyzes the question, and the third module retrieves passages and extracts answers.…”

Section: Related Workmentioning

confidence: 99%

Question Classification in Albanian Through Deep Learning Approaches

Trandafili¹,

Kote²,

Plepi³

2023

IJACSA

View full text Add to dashboard Cite

In recent years, there is growing interest in intelligent conversation systems. In this context, Question Classification is an essential subtask in Question Answering systems that determines the question type, therefore, also the type of the answer. However, while there is abundant research for English, little research work has been carried out for other languages. In this paper we deal with classification of questions in the Albanian language which is considered a complex Indo-European language. We employ both machine learning and deep learning approaches on a large corpus in Albanian based on the six-class TREC dataset with approximately 5000 questions. Experiments with and without stop-words show that the impact of stop-words is significant in the accuracy of the classifier. Extensive comparison of algorithms for the task of question classification in Albanian show that deep learning algorithms outperform conventional machine learning approaches. To the best of our knowledge this is the first approach in literature for classifying questions in Albanian and the results are highly comparable to English.

show abstract