no code implementations • 17 Oct 2024 • Georgios Chochlakis, Alexandros Potamianos, Kristina Lerman, Shrikanth Narayanan
In-context Learning (ICL) has become the primary method for performing natural language tasks with Large Language Models (LLMs).
no code implementations • 5 Oct 2024 • Maria-Eleni Zoumpoulidi, Georgios Paraskevopoulos, Alexandros Potamianos
The decision regarding the need to employ more sophisticated cognitive skills is based on self-evaluation performed by the LLM.
1 code implementation • 17 Sep 2024 • Charilaos Papaioannou, Emmanouil Benetos, Alexandros Potamianos
We introduce Label-Combination Prototypical Networks (LC-Protonets) to address the problem of multi-label few-shot classification, where a model must generalize to new classes based on only a few available examples.
no code implementations • 11 Sep 2024 • Efthymios Georgiou, Georgios Paraskevopoulos, Alexandros Potamianos
In this work, we introduce Y-Drop, a regularization method that biases the dropout algorithm towards dropping more important neurons with higher probability.
1 code implementation • 27 May 2024 • Andreas Charalampopoulos, Nikolas Chatzis, Foivos Ntoulas-Panagiotopoulos, Charilaos Papaioannou, Alexandros Potamianos
Fast feedforward networks (FFFs) are a class of neural networks that exploit the observation that different regions of the input space activate distinct subsets of neurons in wide networks.
no code implementations • 25 Mar 2024 • Georgios Chochlakis, Alexandros Potamianos, Kristina Lerman, Shrikanth Narayanan
The promise of ICL is that the LLM can adapt to perform the present task at a competitive or state-of-the-art level at a fraction of the cost.
no code implementations • 19 Dec 2023 • Efthymios Georgiou, Yannis Avrithis, Alexandros Potamianos
Multimodal sentiment analysis (MSA) leverages heterogeneous data sources to interpret the complex nature of human sentiments.
1 code implementation • 31 Oct 2023 • Yohan Jo, Xinyan Zhao, Arijit Biswas, Nikoletta Basiou, Vincent Auvray, Nikolaos Malandrakis, Angeliki Metallinou, Alexandros Potamianos
While most task-oriented dialogues assume conversations between the agent and one user at a time, dialogue systems are increasingly expected to communicate with multiple users simultaneously who make decisions collaboratively.
1 code implementation • 19 Jul 2023 • Charilaos Papaioannou, Emmanouil Benetos, Alexandros Potamianos
This leads to research questions on whether these models can be used to learn representations for different music cultures and styles, or whether we can build similar music audio embedding models trained on data from different cultures or styles.
no code implementations • 16 Jul 2023 • Maria Nektaria Minaidi, Charilaos Papaioannou, Alexandros Potamianos
Experimental results indicate that using a self-attention mechanism as the frame selection mechanism outperforms the state-of-the-art on SumMe and leads to comparable to state-of-the-art performance on TVSum and COGNIMUSE.
Generative Adversarial Network
Unsupervised Video Summarization
no code implementations • 3 May 2023 • Efthymios Georgiou, Alexandros Potamianos
Data augmentation is a prevalent technique for improving performance in various machine learning applications.
no code implementations • 6 Apr 2023 • Thodoris Kouzelis, Grigoris Bastas, Athanasios Katsamanis, Alexandros Potamianos
The results show that the proposed techniques improve the performance of our system and while reducing the computational complexity.
no code implementations • 24 Mar 2023 • Ilias Triantafyllopoulos, Georgios Paraskevopoulos, Alexandros Potamianos
Motivated by psychological literature we propose to incorporate profanity and morality features of posts and words in our architecture using a late fusion scheme.
no code implementations • 31 Dec 2022 • Georgios Paraskevopoulos, Theodoros Kouzelis, Georgios Rouvalis, Athanasios Katsamanis, Vassilis Katsouros, Alexandros Potamianos
Modern speech recognition systems exhibits rapid performance degradation under domain shift.
no code implementations • 15 Dec 2022 • Nikolaos Antoniou, Efthymios Georgiou, Alexandros Potamianos
Designing powerful adversarial attacks is of paramount importance for the evaluation of $\ell_p$-bounded adversarial defenses.
no code implementations • 1 Dec 2022 • Odysseas S. Chlapanis, Georgios Paraskevopoulos, Alexandros Potamianos
Multimodal learning pipelines have benefited from the success of pretrained language models.
1 code implementation • 21 Nov 2022 • Charilaos Papaioannou, Ioannis Valiantzas, Theodoros Giannakopoulos, Maximos Kaliakatsos-Papakostas, Alexandros Potamianos
The content has been collected from a Greek documentary series that is available online, where academics present music traditions of Greece with live music and dance performance during the show, along with discussions about social, cultural and musicological aspects of the presented music.
1 code implementation • 3 Oct 2022 • Christina Sartzetaki, Georgios Paraskevopoulos, Alexandros Potamianos
We propose a novel deep architecture for the task of reasoning about social interactions in videos.
1 code implementation • 2 Jul 2022 • Eleftherios Kapelonis, Efthymios Georgiou, Alexandros Potamianos
Task-oriented dialogue systems often employ a Dialogue State Tracker (DST) to successfully complete conversations.
no code implementations • 28 Apr 2022 • Efthymios Georgiou, Kosmas Kritsis, Georgios Paraskevopoulos, Athanasios Katsamanis, Vassilis Katsouros, Alexandros Potamianos
Recent deep learning Text-to-Speech (TTS) systems have achieved impressive performance by generating speech close to human parity.
1 code implementation • 24 Jan 2022 • Georgios Paraskevopoulos, Efthymios Georgiou, Alexandros Potamianos
Current deep learning approaches for multimodal fusion rely on bottom-up fusion of high and mid-level latent modality representations (late/mid fusion) or low level sensory inputs (early fusion).
Ranked #7 on
Multimodal Sentiment Analysis
on CMU-MOSEI
(using extra training data)
no code implementations • 30 Oct 2021 • Emmanouil Zaranis, Georgios Paraskevopoulos, Athanasios Katsamanis, Alexandros Potamianos
Specifically, during finetuning we propose to use three objectives: response language modeling, sentiment understanding, and empathy forcing.
1 code implementation • NAACL 2021 • Constantinos Karouzos, Georgios Paraskevopoulos, Alexandros Potamianos
In this work we explore Unsupervised Domain Adaptation (UDA) of pretrained language models for downstream tasks.
Ranked #1 on
Sentiment Analysis
on Multi-Domain Sentiment Dataset
no code implementations • 14 Apr 2021 • Georgios Paraskevopoulos, Efthymios Tzinis, Nikolaos Ellinas, Theodoros Giannakopoulos, Alexandros Potamianos
We examine the use of linear and non-linear dimensionality reduction algorithms for extracting low-rank feature representations for speech emotion recognition.
1 code implementation • 8 Feb 2021 • Georgios Chochlakis, Efthymios Georgiou, Alexandros Potamianos
In this work, we introduce Z2FSL, an end-to-end generative ZSL framework that uses such an approach as a backbone and feeds its synthesized output to a Few-Shot Learning (FSL) algorithm.
1 code implementation • ACL 2019 • Katerina Margatina, Christos Baziotis, Alexandros Potamianos
This form of conditioning on the attention distribution, enforces the contribution of the most salient words for the task at hand.
no code implementations • NAACL 2019 • Eleftheria Briakou, Nikos Athanasiou, Alexandros Potamianos
In traditional Distributional Semantic Models (DSMs) the multiple senses of a polysemous word are conflated into a single vector space representation.
1 code implementation • 7 Apr 2019 • Christos Baziotis, Ion Androutsopoulos, Ioannis Konstas, Alexandros Potamianos
The proposed model does not require parallel text-summary pairs, achieving promising results in unsupervised sentence compression on benchmark datasets.
1 code implementation • NAACL 2019 • Alexandra Chronopoulou, Christos Baziotis, Alexandros Potamianos
A growing number of state-of-the-art transfer learning methods employ language models pretrained on large generic corpora.
1 code implementation • 9 Nov 2018 • Efthymios Tzinis, Georgios Paraskevopoulos, Christos Baziotis, Alexandros Potamianos
We investigate the performance of features that can capture nonlinear recurrence dynamics embedded in the speech signal for the task of Speech Emotion Recognition (SER).
Ranked #52 on
Emotion Recognition in Conversation
on IEMOCAP
Emotion Recognition in Conversation
Speech Emotion Recognition
1 code implementation • WS 2018 • Alexandra Chronopoulou, Aikaterini Margatina, Christos Baziotis, Alexandros Potamianos
In this paper we present our approach to tackle the Implicit Emotion Shared Task (IEST) organized as part of WASSA 2018 at EMNLP 2018.
1 code implementation • 1 Jun 2018 • Georgios Paraskevopoulos, Efthymios Tzinis, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Alexandros Potamianos
We present a novel view of nonlinear manifold learning using derivative-free optimization techniques.
3 code implementations • SEMEVAL 2018 • Christos Baziotis, Nikos Athanasiou, Pinelopi Papalampidi, Athanasia Kolovou, Georgios Paraskevopoulos, Nikolaos Ellinas, Alexandros Potamianos
In this paper we present two deep-learning systems that competed at SemEval-2018 Task 3 "Irony detection in English tweets".
3 code implementations • SEMEVAL 2018 • Christos Baziotis, Nikos Athanasiou, Georgios Paraskevopoulos, Nikolaos Ellinas, Athanasia Kolovou, Alexandros Potamianos
In this paper we present a deep-learning model that competed at SemEval-2018 Task 2 "Multilingual Emoji Prediction".
3 code implementations • SEMEVAL 2018 • Christos Baziotis, Nikos Athanasiou, Alexandra Chronopoulou, Athanasia Kolovou, Georgios Paraskevopoulos, Nikolaos Ellinas, Shrikanth Narayanan, Alexandros Potamianos
In this paper we present deep-learning models that submitted to the SemEval-2018 Task~1 competition: "Affect in Tweets".
no code implementations • EACL 2017 • Filippos Kokkinos, Alexandros Potamianos
We introduce a tree-structured attention neural network for sentences and small phrases and apply it to the problem of sentiment classification.