Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

NLP for The Greek Language: A Longer Survey

Katerina Papantoniou, Yannis Tzitzikas

TL;DR

This survey comprehensively maps three decades of Greek NLP research across Ancient, Modern, and dialectal varieties by organizing works along processing layers such as OCR, morphology, POS/parsing, embeddings, semantics, pragmatics, and MT. It highlights a notable rise in neural approaches, abundant sentiment analysis work, and growing dialogue-system interest, while noting relatively fewer efforts in QA, summarization, and coreference. The authors compile extensive resources, corpora, datasets, tools, and web interfaces, underscoring the increasing availability of Greek NLP resources (with Ancient Greek research often led by institutions outside Greece). Overall, the paper provides a practical framework and reference catalog for researchers and educators to advance Greek language processing and related knowledge-management tasks.

Abstract

English language is in the spotlight of the Natural Language Processing (NLP) community with other languages, like Greek, lagging behind in terms of offered methods, tools and resources. Due to the increasing interest in NLP, in this paper we try to condense research efforts for the automatic processing of Greek language covering the last three decades. In particular, we list and briefly discuss related works, resources and tools, categorized according to various processing layers and contexts. We are not restricted to the modern form of Greek language but also cover Ancient Greek and various Greek dialects. This survey can be useful for researchers and students interested in NLP tasks, Information Retrieval and Knowledge Management for the Greek language.

NLP for The Greek Language: A Longer Survey

TL;DR

This survey comprehensively maps three decades of Greek NLP research across Ancient, Modern, and dialectal varieties by organizing works along processing layers such as OCR, morphology, POS/parsing, embeddings, semantics, pragmatics, and MT. It highlights a notable rise in neural approaches, abundant sentiment analysis work, and growing dialogue-system interest, while noting relatively fewer efforts in QA, summarization, and coreference. The authors compile extensive resources, corpora, datasets, tools, and web interfaces, underscoring the increasing availability of Greek NLP resources (with Ancient Greek research often led by institutions outside Greece). Overall, the paper provides a practical framework and reference catalog for researchers and educators to advance Greek language processing and related knowledge-management tasks.

Abstract

English language is in the spotlight of the Natural Language Processing (NLP) community with other languages, like Greek, lagging behind in terms of offered methods, tools and resources. Due to the increasing interest in NLP, in this paper we try to condense research efforts for the automatic processing of Greek language covering the last three decades. In particular, we list and briefly discuss related works, resources and tools, categorized according to various processing layers and contexts. We are not restricted to the modern form of Greek language but also cover Ancient Greek and various Greek dialects. This survey can be useful for researchers and students interested in NLP tasks, Information Retrieval and Knowledge Management for the Greek language.
Paper Structure (53 sections, 5 figures, 8 tables)

This paper contains 53 sections, 5 figures, 8 tables.

Table of Contents

  1. Introduction
  2. Other surveys and methodology
  3. Methodology for the current survey
  4. Survey of works on Greek NLP
  5. Categorization
  6. Quantitative Overview
  7. Optical Character Recognition (OCR)
  8. Ancient Greek
  9. Modern Greek
  10. Endangered dialects
  11. Phonetics/ Phonology
  12. Morphology
  13. Ancient Greek
  14. Modern Greek
  15. Endangered dialects
  16. ...and 38 more sections

Figures (5)

  • Figure 1: Categorization of works in the survey enriched with the publication year of the oldest work per category that we have included in this survey.
  • Figure 2: Example of some basic NLP tasks over a Greek phrase
  • Figure 3: Number of papers per topic (sorted)
  • Figure 4: Number of papers per topic as a tree map
  • Figure 5: Number of papers about Ancient Greek per topic (sorted)