1 code implementation • LATERAISSE (LREC) 2022 • Justus-Jonas Erker, Catalina Goanta, Gerasimos Spanakis
Cancel Culture as an Internet phenomenon has been previously explored from a social and legal science perspective.
Cultural Vocal Bursts Intensity Prediction
Sentiment Analysis
no code implementations • EMNLP (ACL) 2021 • Walter Simoncini, Gerasimos Spanakis
Named Entity Recognition is a fundamental task in information extraction and is an essential element for various Natural Language Processing pipelines.
1 code implementation • 18 Dec 2024 • Vageesh Saxena, Benjamin Bashpole, Gijs Van Dijck, Gerasimos Spanakis
Human trafficking (HT) remains a critical issue, with traffickers increasingly leveraging online escort advertisements (ads) to advertise victims anonymously.
1 code implementation • 15 Dec 2024 • Paweł Mąka, Yusuf Can Semerci, Jan Scholtes, Gerasimos Spanakis
In this paper, we investigate the role of attention heads in Context-aware Machine Translation models for pronoun disambiguation in the English-to-German and English-to-French language directions.
no code implementations • 15 Oct 2024 • Ben Hagag, Liav Harpaz, Gil Semo, Dor Bernsohn, Rohit Saha, Pashootan Vaezipoor, Kyryl Truskovskyi, Gerasimos Spanakis
This paper presents the results of the LegalLens Shared Task, focusing on detecting legal violations within text in the wild across two sub-tasks: LegalLens-NER for identifying legal violation entities and LegalLens-NLI for associating these violations with relevant legal contexts and affected individuals.
1 code implementation • 2 Sep 2024 • Antoine Louis, Gijs Van Dijck, Gerasimos Spanakis
Hybrid search has emerged as an effective strategy to offset the limitations of different matching paradigms, especially in out-of-domain contexts where notable improvements in retrieval quality have been observed.
1 code implementation • 18 Jul 2024 • Abderrahmane Issam, Yusuf Can Semerci, Jan Scholtes, Gerasimos Spanakis
The wait-$k$ policy offers a solution by starting to translate after consuming $k$ words, where the choice of the number $k$ directly affects the latency and quality.
no code implementations • 17 Jul 2024 • Haoyang Gui, Thales Bertaglia, Catalina Goanta, Sybe de Vries, Gerasimos Spanakis
We apply this methodology to an original dataset reflecting the content of 150 Dutch influencers publicly registered with the Dutch Media Authority based on recently introduced registration obligations.
no code implementations • 8 May 2024 • Mandani Ntekouli, Gerasimos Spanakis, Lourens Waldorp, Anne Roefs
More specifically, clustering individuals in EMA data facilitates uncovering and studying the commonalities as well as variations of groups in the population.
no code implementations • 1 May 2024 • Lucas-Andreï Thil, Mirela Popa, Gerasimos Spanakis
Supervised learning (SL) approaches have achieved impressive performance while utilizing significantly less training data compared to previous methods.
no code implementations • 28 Mar 2024 • Mandani Ntekouli, Gerasimos Spanakis, Lourens Waldorp, Anne Roefs
In the evolving field of psychopathology, the accurate assessment and forecasting of data derived from Ecological Momentary Assessment (EMA) is crucial.
1 code implementation • 23 Feb 2024 • Antoine Louis, Vageesh Saxena, Gijs Van Dijck, Gerasimos Spanakis
In this work, we present a novel modular dense retrieval model that learns from the rich data of a single high-resource language and effectively zero-shot transfers to a wide array of languages, thereby eliminating the need for language-specific labeled data.
1 code implementation • 19 Feb 2024 • Justus-Jonas Erker, Florian Mai, Nils Reimers, Gerasimos Spanakis, Iryna Gurevych
Search-based dialog models typically re-encode the dialog history at every turn, incurring high cost.
no code implementations • 2 Feb 2024 • Paweł Mąka, Yusuf Can Semerci, Jan Scholtes, Gerasimos Spanakis
In this study, we show that a special case of multi-encoder architecture, where the latent representation of the source sentence is cached and reused as the context in the next step, achieves higher accuracy on the contrastive datasets (where the models have to rank the correct translation among the provided sentences) and comparable BLEU and COMET scores as the single- and multi-encoder approaches.
no code implementations • 11 Oct 2023 • Mandani Ntekouli, Gerasimos Spanakis, Lourens Waldorp, Anne Roefs
However, it is believed that additional information of similar individuals is likely to enhance these models leading to better individuals' description.
no code implementations • 9 Oct 2023 • Catalina Goanta, Nikolaos Aletras, Ilias Chalkidis, Sofia Ranchordas, Gerasimos Spanakis
Regulation studies are a rich source of knowledge on how to systematically deal with risk and uncertainty, as well as with scientific evidence, to evaluate and compare regulatory options.
no code implementations • 9 Oct 2023 • Vageesh Saxena, Benjamin Bashpole, Gijs Van Dijck, Gerasimos Spanakis
Human trafficking (HT) is a pervasive global issue affecting vulnerable individuals, violating their fundamental human rights.
1 code implementation • 9 Oct 2023 • Gianluca Vico, Gerasimos Spanakis
Etruscan is an ancient language spoken in Italy from the 7th century BC to the 1st century AD.
1 code implementation • 29 Sep 2023 • Antoine Louis, Gijs Van Dijck, Gerasimos Spanakis
To support this approach, we introduce and release the Long-form Legal Question Answering (LLeQA) dataset, comprising 1, 868 expert-annotated legal questions in the French language, complete with detailed answers rooted in pertinent legal provisions.
1 code implementation • 8 Jun 2023 • Thales Bertaglia, Stefan Huber, Catalina Goanta, Gerasimos Spanakis, Adriana Iamnitchi
To improve annotation accuracy and, thus, the detection of sponsored content, we propose using chatGPT to augment the annotation process with phrases identified as relevant features and brief explanations.
1 code implementation • 4 May 2023 • Vageesh Saxena, Nils Rethmeier, Gijs Van Dijck, Gerasimos Spanakis
The anonymity on the Darknet allows vendors to stay undetected by using multiple vendor aliases or frequently migrating between markets.
1 code implementation • 30 Jan 2023 • Antoine Louis, Gijs Van Dijck, Gerasimos Spanakis
Statutory article retrieval (SAR), the task of retrieving statute law articles relevant to a legal question, is a promising application of legal text processing.
no code implementations • 2 Dec 2022 • Mandani Ntekouli, Gerasimos Spanakis, Lourens Waldorp, Anne Roefs
In the field of psychopathology, Ecological Momentary Assessment (EMA) methodological advancements have offered new opportunities to collect time-intensive, repeated and intra-individual measurements.
1 code implementation • 14 Nov 2022 • Justus-Jonas Erker, Stefan Schaffer, Gerasimos Spanakis
Inspired by the curvature of space-time (Einstein, 1921), we introduce Curved Contrastive Learning (CCL), a novel representation learning technique for learning the relative turn distance between utterance pairs in multi-turn dialogues.
no code implementations • 4 Apr 2022 • Mandani Ntekouli, Gerasimos Spanakis, Lourens Waldorp, Anne Roefs
Interestingly, it is observed that in one of the two real-world datasets, knowledge distillation method achieves improved AUC scores (mean relative change of +17\% compared to personalized) showing how it can benefit EMA data classification and performance.
1 code implementation • ACL 2022 • Antoine Louis, Gerasimos Spanakis
Statutory article retrieval is the task of automatically retrieving law articles relevant to a legal question.
Ranked #1 on
Information Retrieval
on BSARD
1 code implementation • 12 May 2021 • Błażej Dolicki, Gerasimos Spanakis
As a result, one should not expect that for a target language $L_1$ there is a single language $L_2$ that is the best choice for any NLP task (for instance, for Bulgarian, the best source language is French on POS tagging, Russian on NER and Thai on NLI).
no code implementations • 10 Dec 2020 • Adam Vandor, Marie van Vollenhoven, Gerhard Weiss, Gerasimos Spanakis
Harmony in visual compositions is a concept that cannot be defined or easily expressed mathematically, even by humans.
1 code implementation • GeBNLP (COLING) 2020 • Rodrigo Alejandro Chávez Mulsa, Gerasimos Spanakis
Recent research in Natural Language Processing has revealed that word embeddings can encode social biases present in the training data which can affect minorities in real world applications.
1 code implementation • 30 Oct 2020 • Thalea Schlender, Gerasimos Spanakis
Specifically, in the natural language processing domain, it has been shown that social biases persist in word embeddings and are thus in danger of amplifying these biases when used.
1 code implementation • WS 2020 • Danni Liu, Jan Niehues, Gerasimos Spanakis
The experiments show that with limited data far less than needed for training a model from scratch, we can adapt a Transformer-based ASR model to incorporate both transcription and compression capabilities.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
1 code implementation • 22 May 2020 • Danni Liu, Gerasimos Spanakis, Jan Niehues
On How2 English-Portuguese speech translation, we reduce latency to 0. 7 second (-84% rel.)
no code implementations • 31 Jan 2020 • Maria Mihaela Trusca, Gerasimos Spanakis
The tiled convolutional neural network (tiled CNN) has been applied only to computer vision for learning invariances.
1 code implementation • 22 Sep 2019 • Cedric Oeldorf, Gerasimos Spanakis
Domains such as logo synthesis, in which the data has a high degree of multi-modality, still pose a challenge for generative adversarial networks (GANs).
1 code implementation • 6 Sep 2019 • Tobias Bauer, Emre Devrim, Misha Glazunov, William Lopez Jaramillo, Balaganesh Mohan, Gerasimos Spanakis
Inspired by the recent social movement of #MeToo, we are building a chatbot to assist survivors of sexual harassment cases (designed for the city of Maastricht but can easily be extended).
2 code implementations • 6 Mar 2019 • Matteo Maggiolo, Gerasimos Spanakis
Time Series forecasting (univariate and multivariate) is a problem of high complexity due the different patterns that have to be detected in the input, ranging from high to low frequencies ones.
no code implementations • 31 Jan 2019 • Raffaele Piccini, Gerasimos Spanakis
Conversational agents have begun to rise both in the academic (in terms of research) and commercial (in terms of applications) world.
no code implementations • 31 Jan 2019 • Wouter Leeftink, Gerasimos Spanakis
The autoencoder is tested on how well it is able to change the sentiment of an encoded phrase and it was found that such a task is possible.
1 code implementation • 23 Oct 2018 • Ajkel Mino, Gerasimos Spanakis
Yet, conditional generative adversarial networks can be used to generate logos that could help designers in their creative process.
1 code implementation • 8 Dec 2017 • Florian Krebs, Bruno Lubascher, Tobias Moers, Pieter Schaap, Gerasimos Spanakis
In order to predict the distribution of reactions of a new post, neural network architectures (convolutional and recurrent neural networks) were tested using pretrained word embeddings.
no code implementations • 16 Oct 2017 • Alexander Bartl, Gerasimos Spanakis
Finding semantically rich and computer-understandable representations for textual dialogues, utterances and words is crucial for dialogue systems (or conversational agents), as their performance mostly depends on understanding the context of conversations.
no code implementations • 9 Oct 2017 • Tom Rolandus Hagedoorn, Gerasimos Spanakis
Massive Open Online Courses (MOOCs) are attracting the attention of people all over the world.
1 code implementation • 6 Oct 2017 • Joeri Hermans, Gerasimos Spanakis, Rico Möckel
This work addresses the instability in asynchronous data parallel optimization.
no code implementations • 6 Jul 2016 • Gerasimos Spanakis, Gerhard Weiss, Anne Roefs
Ecological Momentary Assessment (EMA) data is organized in multiple levels (per-subject, per-day, etc.)
no code implementations • 19 May 2016 • Gerasimos Spanakis, Gerhard Weiss
Self-Organizing Map (SOM) is a neural network model which is used to obtain a topology-preserving mapping from the (usually high dimensional) input/feature space to an output/map space of fewer dimensions (usually two or three in order to facilitate visualization).