Search Results for author: Gerasimos Spanakis

Found 27 papers, 14 papers with code

SeqAttack: On Adversarial Attacks for Named Entity Recognition

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.

named-entity-recognition Named Entity Recognition +5

Finding the Law: Enhancing Statutory Article Retrieval via Graph Neural Networks

1 code implementation30 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.

Ad-Hoc Information Retrieval Information Retrieval +1

Clustering individuals based on multivariate EMA time-series data

no code implementations2 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.

Clustering Multivariate Time Series Time Series Analysis

Imagination is All You Need! Curved Contrastive Learning for Abstract Sequence Modeling Utilized on Long Short-Term Dialogue Planning

no code implementations14 Nov 2022 Justus-Jonas Erker, Gerasimos Spanakis, Stefan Schaffer

Motivated by the entailment property of multi-turn dialogues through contrastive learning sentence embeddings, we introduce a novel technique, Curved Contrastive Learning (CCL), for generating semantically meaningful and conversational graph curved utterance embeddings that can be compared using cosine similarity.

Contrastive Learning Sentence Embeddings

Using Explainable Boosting Machine to Compare Idiographic and Nomothetic Approaches for Ecological Momentary Assessment Data

no code implementations4 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.

Interpretable Machine Learning Knowledge Distillation

A Statutory Article Retrieval Dataset in French

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.

Information Retrieval Retrieval +1

Analysing The Impact Of Linguistic Features On Cross-Lingual Transfer

1 code implementation12 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).

Cross-Lingual Transfer Multilingual NLP +2

Can we detect harmony in artistic compositions? A machine learning approach

no code implementations10 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.

BIG-bench Machine Learning

Evaluating Bias In Dutch Word Embeddings

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.

Association Sentence Embeddings +1

"Thy algorithm shalt not bear false witness": An Evaluation of Multiclass Debiasing Methods on Word Embeddings

1 code implementation30 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.

Association Fairness +1

Adapting End-to-End Speech Recognition for Readable Subtitles

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

Hybrid Tiled Convolutional Neural Networks for Text Sentiment Classification

no code implementations31 Jan 2020 Maria Mihaela Trusca, Gerasimos Spanakis

The tiled convolutional neural network (tiled CNN) has been applied only to computer vision for learning invariances.

Classification General Classification +2

LoGANv2: Conditional Style-Based Logo Generation with Generative Adversarial Networks

1 code implementation22 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).

#MeTooMaastricht: Building a chatbot to assist survivors of sexual harassment

1 code implementation6 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).

Chatbot named-entity-recognition +5

Autoregressive Convolutional Recurrent Neural Network for Univariate and Multivariate Time Series Prediction

2 code implementations6 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.

Time Series Forecasting Time Series Prediction

Exploring the context of recurrent neural network based conversational agents

no code implementations31 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.

Towards Controlled Transformation of Sentiment in Sentences

no code implementations31 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.

LoGAN: Generating Logos with a Generative Adversarial Neural Network Conditioned on color

1 code implementation23 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.

Social Emotion Mining Techniques for Facebook Posts Reaction Prediction

1 code implementation8 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.

Word Embeddings

A retrieval-based dialogue system utilizing utterance and context embeddings

no code implementations16 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.


Massive Open Online Courses Temporal Profiling for Dropout Prediction

no code implementations9 Oct 2017 Tom Rolandus Hagedoorn, Gerasimos Spanakis

Massive Open Online Courses (MOOCs) are attracting the attention of people all over the world.


Accumulated Gradient Normalization

1 code implementation6 Oct 2017 Joeri Hermans, Gerasimos Spanakis, Rico Möckel

This work addresses the instability in asynchronous data parallel optimization.

AMSOM: Adaptive Moving Self-organizing Map for Clustering and Visualization

no code implementations19 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).

Cannot find the paper you are looking for? You can Submit a new open access paper.