Proceedings ArticleDOI
NLP for the Greek Language: A Brief Survey
Katerina Papantoniou,Yannis Tzitzikas +1 more
- pp 101-109
Reads0
Chats0
TLDR
This paper surveys the work related to the processing of Greek language, and lists and briefly discusses related works, resources and tools, categorized according to various processing layers and contexts.Abstract:
There is a plethora of methods, tools and resources for processing text in the English language, however this is not the case for other languages, like Greek. Due to the increasing interest in NLP, and since there is a noteworthy number of works related to the processing of the Greek language, in this paper we survey the work related to the processing of Greek language. In particular, we list and briefly discuss related works, resources and tools, categorized according to various processing layers and contexts. This survey can be useful for researchers and students interested in NLP tasks, Information Retrieval and Knowledge Management for the Greek language.read more
Citations
More filters
Journal ArticleDOI
BengaliNet: A Low-Cost Novel Convolutional Neural Network for Bengali Handwritten Characters Recognition
TL;DR: This research proposed a low-cost novel convolutional neural network architecture for the recognition of Bengali characters with only 2.24 to 2.43 million parameters based on the number of output classes to help develop an automated high-performance recognition tool for Bengali handwritten characters.
Journal ArticleDOI
A Survey on Sentiment Analysis and Opinion Mining in Greek Social Media
Georgios Alexandridis,Iraklis Varlamis,Konstantinos Korovesis,George Caridakis,Panagiotis Tsantilas +4 more
TL;DR: This paper employed various language models for representing social media texts and text classifiers in the Greek language, for detecting the polarity of opinions expressed on social media, and the experimental results on a related dataset collected by the authors of the current work are promising, since various classifiers based on the language models (naive bayesian, random forests, support vector machines, logistic regression, deep feed forward neural networks) outperform those of word or sentence-based embeddings (word2vec, GloVe), achieving a classification accuracy of more than 80%.
Posted Content
Multi-granular Legal Topic Classification on Greek Legislation
Christos Papaloukas,Ilias Chalkidis,Konstantinos Athinaios,Despina-Athanasia Pantazi,Manolis Koubarakis +4 more
TL;DR: In this paper, the task of classifying legal texts written in the Greek language was studied and a novel dataset based on Greek legislation was introduced, consisting of more than 47 thousand official, categorized Greek legislation resources.
Book ChapterDOI
Efficient approach of using CNN based pretrained model in Bangla handwritten digit recognition
Shabbir Ahmed Shuvo,Musarrat Saberin Nipun,Rejwan Bin Sulaiman,Jannatul Nayeem,Zubaer Haque,Md Mostak Shaikh,Md Sakib Ullah Sourav +6 more
TL;DR: In this paper , a novel convolutional neural network (CNN)-based pre-trained handwritten digit recognition model has been proposed, which outperformed the performance of other models to date with 97% accuracy in the 10-digit classes.
Journal ArticleDOI
SoundexGR: An algorithm for phonetic matching for the Greek language
Antrei Kavros,Yannis Tzitzikas +1 more
TL;DR: This paper introduces an algorithm for phonetic matching designed for the Greek language, and provides comparative results for various parameters of the algorithm for revealing the trade-off between precision and recall in datasets with different kinds of errors.
References
More filters
Journal Article
Placing search in context: the concept revisited.
Lev Finkelstein,Evgeniy Gabrilovich,Yossi Matias,Ehud Rivlin,Zach Solan,Gadi Wolfman,Eytan Ruppin +6 more
TL;DR: A new conceptual paradigm for performing search in context is presented, that largely automates the search process, providing even non-professional users with highly relevant results.
Proceedings Article
Two-level model for morphological analysis
TL;DR: This paper presents a new linguistic, computationally implemented model for morphological analysis and synthesis that is unrestricted in scope and it is capable of handling the whole language system as well as ordinary running text.
Journal ArticleDOI
Handwritten character recognition through two-stage foreground sub-sampling
TL;DR: The proposed methodology relies on a new feature extraction technique based on recursive subdivisions of the character image so that the resulting sub-images at each iteration have balanced (approximately equal) numbers of foreground pixels, as far as this is possible.
Journal ArticleDOI
Generating natural language descriptions from OWL ontologies: the natural OWL system
TL;DR: This work presents Naturalowl, a natural language generation system that produces texts describing individuals or classes of owl ontologies, and presents trials showing that when the domain-dependent linguistic resources are available, Naturalowl produces significantly better texts compared to a simpler verbalizer, and that the resources can be created with relatively light effort.
Journal ArticleDOI
Acoustic characteristics of Greek vowels.
TL;DR: Vowels in focus position, when plotted by their F1 and F2 frequencies, defined a vowel space larger than that defined by vowels in any other condition.