---
title: "Greece — research institutions, scientists and papers"
description: "Greece: 4 institutions with papers in our library in 1 agglomerations, 14 people with a page, 20 works, 19,846 citations."
canonical: "https://research.elamur.ai/free/en/countries/greece/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/countries/greece/)

[home](https://md.research.elamur.ai/free/en/) / [countries](https://md.research.elamur.ai/free/en/countries/) / Greece

# Greece

Country 4 institutions in 1 agglomeration · [all countries](https://md.research.elamur.ai/free/en/countries/)

[**4** institutions with a page](https://md.research.elamur.ai/free/en/countries/greece/#institutions) · [**1** agglomeration](https://md.research.elamur.ai/free/en/countries/greece/#agglomerations) · [**14** people with a page](https://md.research.elamur.ai/free/en/countries/greece/#authors) · [**20** works in our library](https://md.research.elamur.ai/free/en/countries/greece/#works) · [**19,846** citations of their works](https://md.research.elamur.ai/free/en/countries/greece/#works)

## About

### Profile

Greece appears in this library through a small group of research bodies, all in the [Athens](https://md.research.elamur.ai/free/en/agglomerations/athens/) area. One is a university, [Athens University of Economics and Business](https://md.research.elamur.ai/free/en/universities/athens-university-of-economics-and-business/). The other three are research institutes. Two of them, the [Institute for Language and Speech Processing](https://md.research.elamur.ai/free/en/labs/institute-for-language-and-speech-processing/) and the [Athena Research and Innovation Center In Information Communication & Knowledge Technologies](https://md.research.elamur.ai/free/en/labs/athena-research-and-innovation-center-in-information-communication-knowledge/), are in Marousi. The third, the [National Centre of Scientific Research "Demokritos"](https://md.research.elamur.ai/free/en/labs/national-centre-of-scientific-research-demokritos/), is in Athens.

These institutions share one subject. Nearly every Greek work in our library belongs to [natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/), the computational study of human language. Several of them reach into [linguistics and languages](https://md.research.elamur.ai/free/en/shelves/linguistics/), and a distinct group reaches into [law](https://md.research.elamur.ai/free/en/shelves/law/). The university supplies the largest share of these works and the most cited body of them. The two Marousi institutes follow, and the "Demokritos" centre comes last.

This is a narrow view of Greek science. The library holds only part of the published literature. An institution appears here only when its researchers wrote at least two of the papers held on this site. What follows describes Greek research as it shows up among the works here, not the research of the country as a whole. Research in other fields and other Greek cities is missing because the library does not yet hold enough of it.

### History

On this site, Greek research begins in 2009 with [A Survey of Paraphrasing and Textual Entailment Methods](https://md.research.elamur.ai/free/en/papers/androutsopoulos-2009-survey-paraphrasing-textual-entailment-methods/), written by Ion Androutsopoulos and Prodromos Malakasiotis at the Athens University of Economics and Business. The survey treats paraphrase as entailment that holds in both directions. That framing lets the authors describe the two research areas together, and the survey draws on a very wide bibliography.

The next work dates from 2013. It is a report on preparing a multi-document, multilingual summarization corpus, linked to the "Demokritos" centre. From 2014 to 2016 came the run of papers that defines the Greek presence here more than any other: three annual SemEval shared tasks on aspect-based sentiment analysis. Researchers from the university and both Marousi institutes organised them together.

From 2017 the work spreads out. The Athena centre took part in two PARSEME shared tasks, in 2017 and 2018, on verbal multiword expressions. From 2019 a second large line appears at the university and the "Demokritos" centre: language processing for legal text. It produced a dense cluster of datasets, models and benchmarks through 2019, 2020 and 2021. A third line at the university, on toxic and offensive language, also falls in 2020 and 2021.

After 2021 the works here become fewer and change direction. They turn towards low-resource and historical languages and towards Greek itself. A corpus of Pomak appeared in 2022 and a survey of machine learning for ancient languages in 2023. Two works from 2026 address offensive lexicons across languages and a commonsense generation benchmark in Greek.

### Research profile

The most frequent topic among the Greek works in our library is [legal AI](https://md.research.elamur.ai/free/en/topics/legal-ai/). This line is centred on the Athens University of Economics and Business. It began in 2019 with two datasets. [Neural Legal Judgment Prediction in English](https://md.research.elamur.ai/free/en/papers/chalkidis-2019-neural-legal-judgment-prediction-english/) released a far bigger openly available collection of European Court of Human Rights cases and used it to predict case outcomes. [Large-Scale Multi-Label Text Classification on EU Legislation](https://md.research.elamur.ai/free/en/papers/chalkidis-2019-large-scale-multi-label-text/) released EURLEX57K, a corpus of English EU legislative acts drawn from EUR-LEX, for multi-label classification.

A year later, LEGAL-BERT compared ways of adapting the BERT language model to legal text, beginning with the original model left unchanged. The 2021 works took the line further. LexGLUE modelled itself on GLUE and SuperGLUE and built a single English benchmark for legal language understanding. [Paragraph-level Rationale Extraction through Regularization](https://md.research.elamur.ai/free/en/papers/chalkidis-2021-paragraph-level-rationale-extraction-through/) introduced a fresh problem, predicting which rights a European Court of Human Rights applicant claims were violated, and studied which paragraphs justify a model's decision. [MultiEURLEX](https://md.research.elamur.ai/free/en/papers/chalkidis-2021-multieurlex-multi-lingual-multi-label/) started from the point that nobody had yet examined transfer between languages for legal texts. It offered a multilingual, multi-label legal classification dataset for zero-shot transfer, and so it also sits under [multilingual and cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/).

The second large topic is [sentiment and emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/). It rests on the three SemEval tasks on aspect-based sentiment analysis held from 2014 to 2016. Most earlier sentiment work gave an entire text one overall polarity. These tasks instead asked systems to find the specific aspects of an entity that a review discusses, such as features of a product or service, and to judge the sentiment towards each one. Each edition set out shared data, an annotation scheme and an evaluation, so that many teams could compare systems on equal terms. The 2015 and 2016 editions continued and extended the 2014 design.

A third strand concerns toxic and offensive language, filed here under [bias, fairness and safety](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/). [Toxicity Detection: Does Context Really Matter?](https://md.research.elamur.ai/free/en/papers/pavlopoulos-2020-toxicity-detection-does-context-really/) asked whether the surrounding conversation changes how a post should be judged. Its authors urged the building of bigger collections labelled with context in view, and they made their own data and code public. [SemEval-2021 Task 5: Toxic Spans Detection](https://md.research.elamur.ai/free/en/papers/pavlopoulos-2021-semeval-2021-task-5-toxic/) moved from labelling a whole post as toxic to finding the particular words that make it so. The 2026 paper [From Form to Meaning](https://md.research.elamur.ai/free/en/papers/roussopoulou-2026-form-meaning-interlingua-sense-alignment/), linked to both Marousi institutes, carries this interest across languages. It uses large language models to match the individual senses of entries in offensive vocabularies from different languages, pairing them directly instead of passing through an intermediate representation.

A fourth strand deals with the structure of words and phrases. The [multiword expressions](https://md.research.elamur.ai/free/en/topics/multiword-expressions/) work comes from the PARSEME shared tasks of 2017 and 2018. These asked systems to find verbal multiword expressions in running text across many languages, covering idioms, combinations of a verb with a particle, and constructions in which a light verb carries a noun. The [morphology](https://md.research.elamur.ai/free/en/topics/morphology/) work is represented by [Morphologically annotated corpora of Pomak](https://md.research.elamur.ai/free/en/papers/karahoa-2022-morphologically-annotated-corpora-pomak/). Built within the Philotis platform, it aimed to demonstrate that people working on languages with few resources can create annotated corpora on their own.

Several smaller lines complete the picture. [Evaluation and benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) and [reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) meet in [GreekCommonGen](https://md.research.elamur.ai/free/en/papers/stamopoulos-2026-greekcommongen-benchmark-evaluating-generative-commonsense/), which adapts the English CommonGen benchmark to Greek in two stages and uses it to test generative commonsense reasoning. [Summarization](https://md.research.elamur.ai/free/en/topics/summarization/) appears through the 2013 MultiLing corpus report, whose second part covers Czech, Hebrew and Spanish. That report also places Greek research under the topics of Hebrew and Aramaic and of Semitic languages. [Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) and speech act theory appear through [Speaker-change Aware CRF for Dialogue Act Classification](https://md.research.elamur.ai/free/en/papers/shang-2020-speaker-change-aware-crf-dialogue/) from 2020. The 2023 [Machine Learning for Ancient Languages](https://md.research.elamur.ai/free/en/papers/sommerschield-2023-machine-learning-ancient-languages-survey/) survey ranges over all kinds of scripts and media, reaching back to the earliest writing in Mesopotamia. It opens a historical direction that none of the earlier Greek works here had taken.

### Leading scientists

[Ion Androutsopoulos](https://md.research.elamur.ai/free/en/authors/ion-androutsopoulos/), of the Athens University of Economics and Business, heads the list of Greek scientists on this site. Androutsopoulos is also connected to all three research institutes. The work here runs from the 2009 survey of paraphrasing and entailment through the legal line, including the 2019 judgment-prediction study, LexGLUE and MultiEURLEX. Androutsopoulos is the clearest link between the earliest Greek works here and the later ones.

[Dimitris Galanis](https://md.research.elamur.ai/free/en/authors/dimitris-galanis/), of the Institute for Language and Speech Processing, is a co-author of all three SemEval tasks on aspect-based sentiment analysis. A Dimitrios Galanis also wrote GreekCommonGen in 2026. [Maria Pontiki](https://md.research.elamur.ai/free/en/authors/maria-pontiki/), of the same institute, is first author of all three sentiment tasks. Pontiki's work here is the backbone of the Greek sentiment-analysis line.

[Lucas Dixon](https://md.research.elamur.ai/free/en/authors/lucas-dixon/) is connected to the university here. Dixon is a co-author of the 2020 study of context in toxicity detection, part of the work on harmful online language. [Ilias Chalkidis](https://md.research.elamur.ai/free/en/authors/ilias-chalkidis/), also at the university, is first author of most of the legal works: the 2019 judgment-prediction and EU legislation papers, LEGAL-BERT, LexGLUE, the rationale-extraction study and MultiEURLEX. Chalkidis's papers make up the core of the legal topic among the Greek works in our library.

[John Pavlopoulos](https://md.research.elamur.ai/free/en/authors/john-pavlopoulos/), connected to the university and to the Athena centre, has a broad range of work here. Pavlopoulos co-authored the 2014 sentiment task, led the toxicity-in-context study and the SemEval task on toxic spans, and took part in the 2023 survey of machine learning for ancient languages. [Haris Papageorgiou](https://md.research.elamur.ai/free/en/authors/haris-papageorgiou/), of the Institute for Language and Speech Processing, co-authored the 2015 and 2016 sentiment tasks.

[Prodromos Malakasiotis](https://md.research.elamur.ai/free/en/authors/prodromos-malakasiotis/), of the university, wrote the 2009 survey with Androutsopoulos and later took part in the legal line, co-authoring the EU legislation classification paper and LEGAL-BERT. [Jeffrey Sorensen](https://md.research.elamur.ai/free/en/authors/jeffrey-sorensen/), connected to the university here, co-authored both the 2020 toxicity study and the 2021 toxic spans task. [Manos Fergadiotis](https://md.research.elamur.ai/free/en/authors/manos-fergadiotis/), of the university, co-authored LEGAL-BERT, the rationale-extraction study and MultiEURLEX.

[Christos Baziotis](https://md.research.elamur.ai/free/en/authors/christos-baziotis/) and [Nithum Thain](https://md.research.elamur.ai/free/en/authors/nithum-thain/) complete the list of people connected to the university. Their works in our library fall within the same circle of language processing research.

Other researchers appear among the people of the Greek institutions on their own pages. They include [Voula Giouli](https://md.research.elamur.ai/free/en/authors/voula-giouli/), connected to both Marousi institutes, and [Stergos Afantenos](https://md.research.elamur.ai/free/en/authors/stergos-afantenos/), connected to the "Demokritos" centre.

### Landmark works

The most cited Greek work in our library is [SemEval-2014 Task 4: Aspect Based Sentiment Analysis](https://md.research.elamur.ai/free/en/papers/pontiki-2014-semeval-2014-task-4-aspect/). It set up the first of the three aspect-level sentiment challenges, giving the field shared data and a common evaluation for judging sentiment towards individual aspects rather than whole texts. Its successor, [SemEval-2016 Task 5](https://md.research.elamur.ai/free/en/papers/pontiki-2016-semeval-2016-task-5-aspect/), described the third round of the challenge. It is the second most cited Greek work here.

Third is [LEGAL-BERT: The Muppets straight out of Law School](https://md.research.elamur.ai/free/en/papers/chalkidis-2020-legal-bert-muppets-straight-out/). It weighed the options for bringing a general pre-trained language model into the legal domain. Among them were using the model as released, further pre-training it on legal text, and pre-training it on legal text from the start. It is the most cited work of the Greek legal line. [SemEval-2015 Task 12](https://md.research.elamur.ai/free/en/papers/pontiki-2015-semeval-2015-task-12-aspect/), the second sentiment edition, comes next. Together the three sentiment tasks account for a large part of the attention that Greek work in our library has received.

Below these four come works with a more specialised reach. The 2019 judgment-prediction paper and the EURLEX57K classification paper set up resources for legal text. The 2009 survey remains the oldest widely cited Greek work here. [LexGLUE](https://md.research.elamur.ai/free/en/papers/chalkidis-2021-lexglue-benchmark-dataset-legal-language/) gathered legal tasks into a single benchmark. [The PARSEME Shared Task on Automatic Identification of Verbal Multiword Expressions](https://md.research.elamur.ai/free/en/papers/savary-2017-parseme-shared-task-automatic-identification/) is the most cited work of the multiword-expression strand. It was followed by [Edition 1.1 of the PARSEME Shared Task](https://md.research.elamur.ai/free/en/papers/ramisch-2018-edition-1-1-parseme-shared/) in 2018, which asked systems to locate such expressions across an extended set of languages.

### Labs and units

Athens University of Economics and Business is the main source of Greek work in our library. It covers all three main lines: sentiment analysis through its part in the SemEval tasks, legal language processing through Chalkidis and colleagues, and toxicity detection through Pavlopoulos, Sorensen and Dixon. Most of the people on this site connected with Greece are attached to it.

The Institute for Language and Speech Processing, in Marousi, has the sentiment tasks as its most cited works here. Its later works turn to languages with fewer resources and to Greek: the Pomak corpora, the offensive-lexicon alignment of 2026 and GreekCommonGen. Galanis, Pontiki and Papageorgiou are the people most closely tied to it. Researchers such as [Maria Liakata](https://md.research.elamur.ai/free/en/authors/maria-liakata/) and [Krister Lindén](https://md.research.elamur.ai/free/en/authors/krister-linden/) also appear among its people.

The Athena Research and Innovation Center shares much of its work with the Institute for Language and Speech Processing. This includes the 2015 and 2016 sentiment tasks, the Pomak corpora and the 2026 lexicon work. It is also the Greek institution behind the two PARSEME shared tasks on multiword expressions. Among its people are [Sophia Ananiadou](https://md.research.elamur.ai/free/en/authors/sophia-ananiadou/) and [Antonios Anastasopoulos](https://md.research.elamur.ai/free/en/authors/antonios-anastasopoulos/).

The National Centre of Scientific Research "Demokritos" has the fewest works here. It shares LEGAL-BERT and the rationale-extraction study with the university's legal line, and it contributed to the 2013 MultiLing summarization corpus. Malakasiotis and Fergadiotis head its people on this site.

### Collaborations

The Greek institutions on this site work closely with one another. The sentiment tasks link the university with both Marousi institutes. The legal line links the university with the "Demokritos" centre. The two Marousi institutes share several works, from the sentiment tasks to the 2022 and 2026 papers. Androutsopoulos and Pavlopoulos appear across more than one institution, which suggests that the same research circles are active in several places in the Athens area.

Work with researchers abroad runs through the shared tasks and the larger projects. The legal papers bring in Nikolaos Aletras, and LexGLUE adds Daniel Martin Katz, Michael Bommarito, Dirk Hartung and Abhik Jana. The PARSEME tasks were led by Agata Savary, Carlos Ramisch and Silvio Cordeiro. The 2013 summarization report involved Michael Elhadad, Sabino Miranda-Jiménez and Josef Steinberger. The toxic spans task included Léo Laugier, and the ancient-languages survey was led by Thea Sommerschield with Yannis Assael. The dialogue-act paper came from Guokan Shang, Antoine Tixier and Michalis Vazirgiannis. Within Greece, the 2026 lexicon work pairs Maria Alexandra Roussopoulou with Stella Markantonatou, and the Pomak corpora involve Panagiotis G. Krimpas and Vivian Stamou.

### Timeline

The years 2009 to 2013 hold the earliest Greek works in our library. The 2009 survey framed paraphrase and textual entailment together, and the 2013 MultiLing report prepared summarization data in several languages.

From 2014 to 2016 the aspect-based sentiment tasks dominate, one edition each year. The university and the two Marousi institutes ran them together, and they remain the most cited Greek works here.

In 2017 and 2018 the PARSEME tasks on verbal multiword expressions brought the Athena centre into multilingual shared tasks on phrase structure.

From 2019 to 2021 Greek work here grows fastest. The legal line produced its datasets, LEGAL-BERT, LexGLUE, the rationale-extraction study and MultiEURLEX. The toxicity work produced its study of context and the toxic spans task. The dialogue-act paper also appeared in 2020.

From 2022 onwards the works turn to low-resource, historical and Greek-language problems: the Pomak corpora in 2022, the ancient-languages survey in 2023, and in 2026 the cross-lingual alignment of offensive lexicons and GreekCommonGen.

## Where

## Agglomerations (1)

1. [**Athens**4 institutions*19,846 citations*](https://md.research.elamur.ai/free/en/agglomerations/athens/)

## Institutions (4)

### 🎓 Universities (1)

1. **[Athens University of Economics and Business](https://md.research.elamur.ai/free/en/universities/athens-university-of-economics-and-business/)**University · [Athens](https://md.research.elamur.ai/free/en/agglomerations/athens/), Greece*14 works · 9,217 citations*

### 🔬 Labs and research institutes (3)

1. **[Institute for Language and Speech Processing](https://md.research.elamur.ai/free/en/labs/institute-for-language-and-speech-processing/)**Research institute · [Marousi](https://md.research.elamur.ai/free/en/agglomerations/athens/), Greece*6 works · 5,514 citations*
2. **[Athena Research and Innovation Center In Information Communication & Knowledge Technologies](https://md.research.elamur.ai/free/en/labs/athena-research-and-innovation-center-in-information-communication-knowledge/)**Research institute · [Marousi](https://md.research.elamur.ai/free/en/agglomerations/athens/), Greece*6 works · 3,438 citations*
3. **[National Centre of Scientific Research "Demokritos"](https://md.research.elamur.ai/free/en/labs/national-centre-of-scientific-research-demokritos/)**Research institute · [Athens](https://md.research.elamur.ai/free/en/agglomerations/athens/), Greece*3 works · 1,677 citations*

## People (14)

Authors with a page confirmed at its institutions, the most cited first.

1. [**Ion Androutsopoulos**Athens University of Economics and Business*12 papers here · 9,606 citations*](https://md.research.elamur.ai/free/en/authors/ion-androutsopoulos/)
2. [**Dimitris Galanis**Institute for Language and Speech Processing*3 papers here · 5,507 citations*](https://md.research.elamur.ai/free/en/authors/dimitris-galanis/)
3. [**Maria Pontiki**Institute for Language and Speech Processing*3 papers here · 5,507 citations*](https://md.research.elamur.ai/free/en/authors/maria-pontiki/)
4. [**Lucas Dixon**Athens University of Economics and Business*2 papers here · 5,502 citations*](https://md.research.elamur.ai/free/en/authors/lucas-dixon/)
5. [**Ilias Chalkidis**Athens University of Economics and Business*8 papers here · 4,076 citations*](https://md.research.elamur.ai/free/en/authors/ilias-chalkidis/)
6. [**John Pavlopoulos**Athens University of Economics and Business*4 papers here · 3,188 citations*](https://md.research.elamur.ai/free/en/authors/john-pavlopoulos/)
7. [**Haris Papageorgiou**Institute for Language and Speech Processing*2 papers here · 3,102 citations*](https://md.research.elamur.ai/free/en/authors/haris-papageorgiou/)
8. [**Prodromos Malakasiotis**Athens University of Economics and Business*4 papers here · 2,436 citations*](https://md.research.elamur.ai/free/en/authors/prodromos-malakasiotis/)
9. [**Jeffrey Sorensen**Athens University of Economics and Business*5 papers here · 2,140 citations*](https://md.research.elamur.ai/free/en/authors/jeffrey-sorensen/)
10. [**Manos Fergadiotis**Athens University of Economics and Business*3 papers here · 1,863 citations*](https://md.research.elamur.ai/free/en/authors/manos-fergadiotis/)
11. [**Christos Baziotis**Athens University of Economics and Business*2 papers here · 701 citations*](https://md.research.elamur.ai/free/en/authors/christos-baziotis/)
12. [**Nithum Thain**Athens University of Economics and Business*2 papers here · 448 citations*](https://md.research.elamur.ai/free/en/authors/nithum-thain/)
13. [**Michalis Vazirgiannis**Athens University of Economics and Business*2 papers here · 403 citations*](https://md.research.elamur.ai/free/en/authors/michalis-vazirgiannis/)
14. [**Voula Giouli**Athena Research and Innovation Center In Information Communication & Knowledge Technologies*4 papers here · 383 citations*](https://md.research.elamur.ai/free/en/authors/voula-giouli/)

## Works in our library (20)

Works of its institutions, the most cited first.

1. [**SemEval-2014 Task 4: Aspect Based Sentiment Analysis**Maria Pontiki, Dimitris Galanis, John Pavlopoulos, et al.*2014 · 2,405 citations*](https://md.research.elamur.ai/free/en/papers/pontiki-2014-semeval-2014-task-4-aspect/)
2. [**SemEval-2016 Task 5: Aspect Based Sentiment Analysis**Maria Pontiki, Dimitris Galanis, Haris Papageorgiou, et al.*2016 · 1,656 citations*](https://md.research.elamur.ai/free/en/papers/pontiki-2016-semeval-2016-task-5-aspect/)
3. [**LEGAL-BERT: The Muppets straight out of Law School**Ilias Chalkidis, Manos Fergadiotis, Prodromos Malakasiotis, et al.*2020 · 1,490 citations*](https://md.research.elamur.ai/free/en/papers/chalkidis-2020-legal-bert-muppets-straight-out/)
4. [**SemEval-2015 Task 12: Aspect Based Sentiment Analysis**Maria Pontiki, Dimitris Galanis, Haris Papageorgiou, et al.*2015 · 1,446 citations*](https://md.research.elamur.ai/free/en/papers/pontiki-2015-semeval-2015-task-12-aspect/)
5. [**Neural Legal Judgment Prediction in English**Ilias Chalkidis, Ion Androutsopoulos, Nikolaos Aletras*2019 · 558 citations*](https://md.research.elamur.ai/free/en/papers/chalkidis-2019-neural-legal-judgment-prediction-english/)
6. [**Large-Scale Multi-Label Text Classification on EU Legislation**Ilias Chalkidis, Emmanouil Fergadiotis, Prodromos Malakasiotis, et al.*2019 · 283 citations*](https://md.research.elamur.ai/free/en/papers/chalkidis-2019-large-scale-multi-label-text/)
7. [**A Survey of Paraphrasing and Textual Entailment Methods**Ion Androutsopoulos, Prodromos Malakasiotis*2009 · 280 citations*](https://md.research.elamur.ai/free/en/papers/androutsopoulos-2009-survey-paraphrasing-textual-entailment-methods/)
8. [**LexGLUE: A Benchmark Dataset for Legal Language Understanding in English**Ilias Chalkidis; Abhik Jana; Dirk Hartung; Michael Bommarito; Ion Androutsopoulos; Daniel Martin Katz;, Nikolaos Aletras*2021 · 256 citations*](https://md.research.elamur.ai/free/en/papers/chalkidis-2021-lexglue-benchmark-dataset-legal-language/)
9. [**The PARSEME Shared Task on Automatic Identification of Verbal Multiword Expressions**Agata Savary, Carlos Ramisch, Silvio Cordeiro, et al.*2017 · 205 citations*](https://md.research.elamur.ai/free/en/papers/savary-2017-parseme-shared-task-automatic-identification/)
10. [**Toxicity Detection: Does Context Really Matter?**John Pavlopoulos, Jeffrey Sorensen, Lucas Dixon, et al.*2020 · 198 citations*](https://md.research.elamur.ai/free/en/papers/pavlopoulos-2020-toxicity-detection-does-context-really/)
11. [**SemEval-2021 Task 5: Toxic Spans Detection**John Pavlopoulos, Jeffrey Sorensen, Léo Laugier, et al.*2021 · 172 citations*](https://md.research.elamur.ai/free/en/papers/pavlopoulos-2021-semeval-2021-task-5-toxic/)
12. [**Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Cases**Ilias Chalkidis, Manos Fergadiotis, Dimitrios Tsarapatsanis, et al.*2021 · 167 citations*](https://md.research.elamur.ai/free/en/papers/chalkidis-2021-paragraph-level-rationale-extraction-through/)
13. [**MultiEURLEX - A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer**Ilias Chalkidis, Manos Fergadiotis, Ion Androutsopoulos*2021 · 160 citations*](https://md.research.elamur.ai/free/en/papers/chalkidis-2021-multieurlex-multi-lingual-multi-label/)
14. [**Edition 1.1 of the PARSEME Shared Task on Automatic Identification of Verbal Multiword Expressions**Carlos Ramisch, Silvio Ricardo Cordeiro, Agata Savary, et al.*2018 · 124 citations*](https://md.research.elamur.ai/free/en/papers/ramisch-2018-edition-1-1-parseme-shared/)
15. [**Machine Learning for Ancient Languages: A Survey**Thea Sommerschield, Yannis Assael, John Pavlopoulos, et al.*2023 · 123 citations*](https://md.research.elamur.ai/free/en/papers/sommerschield-2023-machine-learning-ancient-languages-survey/)
16. [**Speaker-change Aware CRF for Dialogue Act Classification**Guokan Shang, Antoine Tixier, Michalis Vazirgiannis, et al.*2020 · 23 citations*](https://md.research.elamur.ai/free/en/papers/shang-2020-speaker-change-aware-crf-dialogue/)
17. [**Multi-document multilingual summarization corpus preparation, Part 2: Czech, Hebrew and Spanish**Michael Elhadad, Sabino Miranda-Jiménez, Josef Steinberger, et al.*2013 · 20 citations*](https://md.research.elamur.ai/free/en/papers/elhadad-2013-multi-document-multilingual-summarization-corpus/)
18. [**Morphologically annotated corpora of Pomak**Ritván Jusúf Karahóǧa, Panagiotis G. Krimpas, Vivian Stamou, et al.*2022 · 7 citations*](https://md.research.elamur.ai/free/en/papers/karahoa-2022-morphologically-annotated-corpora-pomak/)
19. [**From Form to Meaning: Interlingua Sense-Alignment of Offensive Language with LLMs**Maria Alexandra Roussopoulou, Stella Markantonatou*2026*](https://md.research.elamur.ai/free/en/papers/roussopoulou-2026-form-meaning-interlingua-sense-alignment/)
20. [**GreekCommonGen: A Benchmark for Evaluating Generative Commonsense Reasoning in Greek**Aristotelis Stamopoulos, Dimitrios Galanis*2026*](https://md.research.elamur.ai/free/en/papers/stamopoulos-2026-greekcommongen-benchmark-evaluating-generative-commonsense/)

## Concepts, shelves and topics

Of its works in our library: the number of works on each and its rating among them.

📚 Shelves 6[Natural language processing · 12 works](https://md.research.elamur.ai/free/en/shelves/nlp/) · [Law · 6 works](https://md.research.elamur.ai/free/en/shelves/law/) · [Linguistics & languages · 8 works](https://md.research.elamur.ai/free/en/shelves/linguistics/) · [Machine translation · 2 works](https://md.research.elamur.ai/free/en/shelves/machine-translation/) · [Modern Hebrew · 1 work](https://md.research.elamur.ai/free/en/shelves/he/) · [Society & ethics · 1 work](https://md.research.elamur.ai/free/en/shelves/society/)

🧭 Topics 14[Sentiment & emotion · 4 works](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · [Legal AI · 6 works](https://md.research.elamur.ai/free/en/topics/legal-ai/) · [Bias, fairness & safety · 2 works](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) · [Idioms & multiword expressions · 2 works](https://md.research.elamur.ai/free/en/topics/multiword-expressions/) · [Reasoning · 2 works](https://md.research.elamur.ai/free/en/topics/reasoning/) · [Evaluation & benchmarks · 2 works](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · [Multilingual & cross-lingual NLP · 2 works](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · [Morphology · 1 work](https://md.research.elamur.ai/free/en/topics/morphology/) · [Dialogue systems · 1 work](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · [Speech act theory · 1 work](https://md.research.elamur.ai/free/en/topics/speech-act-theory/) · [Hebrew & Aramaic · 1 work](https://md.research.elamur.ai/free/en/topics/hebrew-aramaic/) · [Semitic languages · 1 work](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · [Summarization · 1 work](https://md.research.elamur.ai/free/en/topics/summarization/) · [Machine translation · 1 work](https://md.research.elamur.ai/free/en/topics/machine-translation/)

## Works by year

### 2020s

[**2026** 2 works](https://md.research.elamur.ai/free/en/countries/greece/year/2026/) · [**2023** 1 work](https://md.research.elamur.ai/free/en/papers/sommerschield-2023-machine-learning-ancient-languages-survey/) · [**2022** 1 work](https://md.research.elamur.ai/free/en/papers/karahoa-2022-morphologically-annotated-corpora-pomak/) · [**2021** 4 works](https://md.research.elamur.ai/free/en/countries/greece/year/2021/) · [**2020** 3 works](https://md.research.elamur.ai/free/en/countries/greece/year/2020/)

### 2010s

[**2019** 2 works](https://md.research.elamur.ai/free/en/countries/greece/year/2019/) · [**2018** 1 work](https://md.research.elamur.ai/free/en/papers/ramisch-2018-edition-1-1-parseme-shared/) · [**2017** 1 work](https://md.research.elamur.ai/free/en/papers/savary-2017-parseme-shared-task-automatic-identification/) · [**2016** 1 work](https://md.research.elamur.ai/free/en/papers/pontiki-2016-semeval-2016-task-5-aspect/) · [**2015** 1 work](https://md.research.elamur.ai/free/en/papers/pontiki-2015-semeval-2015-task-12-aspect/) · [**2014** 1 work](https://md.research.elamur.ai/free/en/papers/pontiki-2014-semeval-2014-task-4-aspect/) · [**2013** 1 work](https://md.research.elamur.ai/free/en/papers/elhadad-2013-multi-document-multilingual-summarization-corpus/)

### 2000s

[**2009** 1 work](https://md.research.elamur.ai/free/en/papers/androutsopoulos-2009-survey-paraphrasing-textual-entailment-methods/)

- [← back to](https://md.research.elamur.ai/free/en/countries/) — countries

Updated 23 October 2026