Athanasia Kolovou


2022

pdf
Collaborative Metadata Aggregation and Curation in Support of Digital Language Equality Monitoring
Maria Giagkou | Stelios Piperidis | Penny Labropoulou | Miltos Deligiannis | Athanasia Kolovou | Leon Voukoutis
Proceedings of the Workshop Towards Digital Language Equality within the 13th Language Resources and Evaluation Conference

The European Language Equality (ELE) project develops a strategic research, innovation and implementation agenda (SRIA) and a roadmap for achieving full digital language equality in Europe by 2030. Key component of the SRIA development is an accurate estimation of the current standing of languages with respect to their technological readiness. In this paper we present the empirical basis on which such estimation is grounded, its starting point and in particular the automatic and collaborative methods used for extending it. We focus on the collaborative expert activities, the challenges posed, and the solutions adopted. We also briefly present the dashboard application developed for querying and visualising the empirical data as well as monitoring and comparing the evolution of technological support within and across languages.

2021

pdf
European Language Grid: A Joint Platform for the European Language Technology Community
Georg Rehm | Stelios Piperidis | Kalina Bontcheva | Jan Hajic | Victoria Arranz | Andrejs Vasiļjevs | Gerhard Backfried | Jose Manuel Gomez-Perez | Ulrich Germann | Rémi Calizzano | Nils Feldhus | Stefanie Hegele | Florian Kintzel | Katrin Marheinecke | Julian Moreno-Schneider | Dimitris Galanis | Penny Labropoulou | Miltos Deligiannis | Katerina Gkirtzou | Athanasia Kolovou | Dimitris Gkoumas | Leon Voukoutis | Ian Roberts | Jana Hamrlova | Dusan Varis | Lukas Kacena | Khalid Choukri | Valérie Mapelli | Mickaël Rigault | Julija Melnika | Miro Janosik | Katja Prinz | Andres Garcia-Silva | Cristian Berrio | Ondrej Klejch | Steve Renals
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations

Europe is a multilingual society, in which dozens of languages are spoken. The only option to enable and to benefit from multilingualism is through Language Technologies (LT), i.e., Natural Language Processing and Speech Technologies. We describe the European Language Grid (ELG), which is targeted to evolve into the primary platform and marketplace for LT in Europe by providing one umbrella platform for the European LT landscape, including research and industry, enabling all stakeholders to upload, share and distribute their services, products and resources. At the end of our EU project, which will establish a legal entity in 2022, the ELG will provide access to approx. 1300 services for all European languages as well as thousands of data sets.

2018

pdf
NTUA-SLP at SemEval-2018 Task 1: Predicting Affective Content in Tweets with Deep Attentive RNNs and Transfer Learning
Christos Baziotis | Athanasiou Nikolaos | Alexandra Chronopoulou | Athanasia Kolovou | Georgios Paraskevopoulos | Nikolaos Ellinas | Shrikanth Narayanan | Alexandros Potamianos
Proceedings of the 12th International Workshop on Semantic Evaluation

In this paper we present deep-learning models that submitted to the SemEval-2018 Task 1 competition: “Affect in Tweets”. We participated in all subtasks for English tweets. We propose a Bi-LSTM architecture equipped with a multi-layer self attention mechanism. The attention mechanism improves the model performance and allows us to identify salient words in tweets, as well as gain insight into the models making them more interpretable. Our model utilizes a set of word2vec word embeddings trained on a large collection of 550 million Twitter messages, augmented by a set of word affective features. Due to the limited amount of task-specific training data, we opted for a transfer learning approach by pretraining the Bi-LSTMs on the dataset of Semeval 2017, Task 4A. The proposed approach ranked 1st in Subtask E “Multi-Label Emotion Classification”, 2nd in Subtask A “Emotion Intensity Regression” and achieved competitive results in other subtasks.

pdf
NTUA-SLP at SemEval-2018 Task 2: Predicting Emojis using RNNs with Context-aware Attention
Christos Baziotis | Athanasiou Nikolaos | Athanasia Kolovou | Georgios Paraskevopoulos | Nikolaos Ellinas | Alexandros Potamianos
Proceedings of the 12th International Workshop on Semantic Evaluation

In this paper we present a deep-learning model that competed at SemEval-2018 Task 2 “Multilingual Emoji Prediction”. We participated in subtask A, in which we are called to predict the most likely associated emoji in English tweets. The proposed architecture relies on a Long Short-Term Memory network, augmented with an attention mechanism, that conditions the weight of each word, on a “context vector” which is taken as the aggregation of a tweet’s meaning. Moreover, we initialize the embedding layer of our model, with word2vec word embeddings, pretrained on a dataset of 550 million English tweets. Finally, our model does not rely on hand-crafted features or lexicons and is trained end-to-end with back-propagation. We ranked 2nd out of 48 teams.

pdf
NTUA-SLP at SemEval-2018 Task 3: Tracking Ironic Tweets using Ensembles of Word and Character Level Attentive RNNs
Christos Baziotis | Athanasiou Nikolaos | Pinelopi Papalampidi | Athanasia Kolovou | Georgios Paraskevopoulos | Nikolaos Ellinas | Alexandros Potamianos
Proceedings of the 12th International Workshop on Semantic Evaluation

In this paper we present two deep-learning systems that competed at SemEval-2018 Task 3 “Irony detection in English tweets”. We design and ensemble two independent models, based on recurrent neural networks (Bi-LSTM), which operate at the word and character level, in order to capture both the semantic and syntactic information in tweets. Our models are augmented with a self-attention mechanism, in order to identify the most informative words. The embedding layer of our word-level model is initialized with word2vec word embeddings, pretrained on a collection of 550 million English tweets. We did not utilize any handcrafted features, lexicons or external datasets as prior information and our models are trained end-to-end using back propagation on constrained data. Furthermore, we provide visualizations of tweets with annotations for the salient tokens of the attention layer that can help to interpret the inner workings of the proposed models. We ranked 2nd out of 42 teams in Subtask A and 2nd out of 31 teams in Subtask B. However, post-task-completion enhancements of our models achieve state-of-the-art results ranking 1st for both subtasks.

2017

pdf
Tweester at SemEval-2017 Task 4: Fusion of Semantic-Affective and pairwise classification models for sentiment analysis in Twitter
Athanasia Kolovou | Filippos Kokkinos | Aris Fergadis | Pinelopi Papalampidi | Elias Iosif | Nikolaos Malandrakis | Elisavet Palogiannidi | Haris Papageorgiou | Shrikanth Narayanan | Alexandros Potamianos
Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)

In this paper, we describe our submission to SemEval2017 Task 4: Sentiment Analysis in Twitter. Specifically the proposed system participated both to tweet polarity classification (two-, three- and five class) and tweet quantification (two and five-class) tasks.

2016

pdf
Tweester at SemEval-2016 Task 4: Sentiment Analysis in Twitter Using Semantic-Affective Model Adaptation
Elisavet Palogiannidi | Athanasia Kolovou | Fenia Christopoulou | Filippos Kokkinos | Elias Iosif | Nikolaos Malandrakis | Haris Papageorgiou | Shrikanth Narayanan | Alexandros Potamianos
Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)