Search Results for author:
Found 38 papers, 21 papers with code
CHORDONOMICON: A Dataset of 666,000 Songs and their Chord Progressions
Chord progressions encapsulate important information about music, pertaining to its structure and conveyed emotions.
Graph Linearization Methods for Reasoning on Graphs with Large Language Models
Large language models have evolved to process multiple modalities beyond text, such as images and audio, which motivates us to explore how to effectively leverage them for graph machine learning tasks.
BERTtime Stories: Investigating the Role of Synthetic Story Data in Language pre-training
To measure the effect of synthetic story data, we train LTG-BERT encoder models on a combined dataset of: a subset of TinyStories, story completions generated by GPT-Neo, and a subset of the BabyLM dataset.
RISCORE: Enhancing In-Context Riddle Solving in Language Models through Context-Reconstructed Example Augmentation
Riddle-solving requires advanced reasoning skills, pushing LLMs to engage in abstract thinking and creative problem-solving, often revealing limitations in their cognitive abilities.
"I Never Said That": A dataset, taxonomy and baselines on response clarity classification
Equivocation and ambiguity in public speech are well-studied discourse phenomena, especially in political science and analysis of political interviews.
GOSt-MT: A Knowledge Graph for Occupation-related Gender Biases in Machine Translation
This paper introduces a novel approach to studying occupation-related gender bias through the creation of the GOSt-MT (Gender and Occupation Statistics for Machine Translation) Knowledge Graph.
MusicLIME: Explainable Multimodal Music Understanding
Multimodal models are critical for music understanding tasks, as they capture the complex interplay between audio and lyrics.
Enhancing adversarial robustness in Natural Language Inference using explanations
The surge of state-of-the-art Transformer-based models has undoubtedly pushed the limits of NLP model performance, excelling in a variety of tasks.
Prompt2Fashion: An automatically generated fashion dataset
Despite the provided fine-grained insights on the quality and relevance of generation, we extend the discussion on the importance of expert knowledge for the evaluation of artistic AI-generated datasets such as this one.
ARPA: A Novel Hybrid Model for Advancing Visual Word Disambiguation Using Large Language Models and Transformers
In the rapidly evolving fields of natural language processing and computer vision, Visual Word Sense Disambiguation (VWSD) stands as a critical, yet challenging task.
Optimal and efficient text counterfactuals using Graph Neural Networks
As NLP models become increasingly integral to decision-making processes, the need for explainability and interpretability has become paramount.
Automatic Generation of Fashion Images using Prompting in Generative Machine Learning Models
Emphasizing adaptability in AI-driven fashion creativity, we depart from traditional approaches and focus on prompting techniques, such as zero-shot and few-shot learning, as well as Chain-of-Thought (CoT), which results in a variety of colors and textures, enhancing the diversity of the outputs.
Semantic Prototypes: Enhancing Transparency Without Black Boxes
As machine learning (ML) models and datasets increase in complexity, the demand for methods that enhance explainability and interpretability becomes paramount.
Deep Ensemble Art Style Recognition
We also discuss the impact of the data and art styles themselves on the performance of our models forming a manifold perspective on the problem.
Beyond One-Size-Fits-All: Adapting Counterfactual Explanations to User Objectives
Explainable Artificial Intelligence (XAI) has emerged as a critical area of research aimed at enhancing the transparency and interpretability of AI systems.
AILS-NTUA at SemEval-2024 Task 6: Efficient model tuning for hallucination detection and analysis
In this paper, we present our team's submissions for SemEval-2024 Task-6 - SHROOM, a Shared-task on Hallucinations and Related Observable Overgeneration Mistakes.
AILS-NTUA at SemEval-2024 Task 9: Cracking Brain Teasers: Transformer Models for Lateral Thinking Puzzles
In this paper, we outline our submission for the SemEval-2024 Task 9 competition: 'BRAINTEASER: A Novel Task Defying Common Sense'.
Masked Generative Story Transformer with Character Guidance and Caption Augmentation
Story Visualization (SV) is a challenging generative vision task, that requires both visual quality and consistency between different frames in generated image sequences.
Structure Your Data: Towards Semantic Graph Counterfactuals
With a focus on the visual domain, we represent images as scene graphs and obtain their GNN embeddings to bypass solving the NP-hard graph similarity problem for all input pairs, an integral part of the CE computation process.
Puzzle Solving using Reasoning of Large Language Models: A Survey
Exploring the capabilities of Large Language Models (LLMs) in puzzle solving unveils critical insights into their potential and challenges in AI, marking a significant step towards understanding their applicability in complex reasoning tasks.
Graph Edits for Counterfactual Explanations: A comparative study
Counterfactuals have been established as a popular explainability technique which leverages a set of minimal edits to alter the prediction of a classifier.
Perceptual Musical Features for Interpretable Audio Tagging
In the age of music streaming platforms, the task of automatically tagging music audio has garnered significant attention, driving researchers to devise methods aimed at enhancing performance metrics on standard datasets.
Large Language Models and Multimodal Retrieval for Visual Word Sense Disambiguation
We also study VWSD as a unimodal problem by converting to text-to-text and image-to-image retrieval, as well as question-answering (QA), to fully explore the capabilities of relevant models.
Language Models as Knowledge Bases for Visual Word Sense Disambiguation
Visual Word Sense Disambiguation (VWSD) is a novel challenging task that lies between linguistic sense disambiguation and fine-grained multimodal retrieval.
Employing Crowdsourcing for Enriching a Music Knowledge Base in Higher Education
The campaign's results and the comments gathered through an online survey enable us to draw some useful insights about the benefits and challenges of integrating crowdsourcing into computer science curricula and how this can enhance students' engagement in the learning process.
Choose your Data Wisely: A Framework for Semantic Counterfactuals
In this work, we build on these ideas, and propose a framework that provides counterfactual explanations in terms of knowledge graphs.
Counterfactuals of Counterfactuals: a back-translation-inspired approach to analyse counterfactual editors
We propose a new back translation-inspired evaluation methodology that utilises earlier outputs of the explainer as ground truth proxies to investigate the consistency of explainers.
GreekBART: The First Pretrained Greek Sequence-to-Sequence Model
In addition, we examine its performance on two NLG tasks from GreekSUM, a newly introduced summarization dataset for the Greek language.
Knowledge-Based Counterfactual Queries for Visual Question Answering
Visual Question Answering (VQA) has been a popular task that combines vision and language, with numerous relevant implementations in literature.
Fine-Grained ImageNet Classification in the Wild
Image classification has been one of the most popular tasks in Deep Learning, seeing an abundance of impressive implementations each year.
The Contribution of Knowledge in Visiolinguistic Learning: A Survey on Tasks and Challenges
Recent advancements in visiolinguistic (VL) learning have allowed the development of multiple models and techniques that offer several impressive implementations, able to currently resolve a variety of tasks that require the collaboration of vision and language.
Counterfactual Edits for Generative Evaluation
Evaluation of generative models has been an underrepresented field despite the surge of generative architectures.
An Impartial Transformer for Story Visualization
Story Visualization is an advanced task of computed vision that targets sequential image synthesis, where the generated samples need to be realistic, faithful to their conditioning and sequentially consistent.
Ranked #1 on
Story Visualization
on CLEVR-SV
A survey on knowledge-enhanced multimodal learning
Multimodal learning has been a field of increasing interest, aiming to combine various modalities in a single joint representation.
Conditional Image Generation
Factual Visual Question Answering
+13
Towards explainable evaluation of language models on the semantic similarity of visual concepts
Recent breakthroughs in NLP research, such as the advent of Transformer models have indisputably contributed to major advancements in several tasks.
Computing Rule-Based Explanations of Machine Learning Classifiers using Knowledge Graphs
The use of symbolic knowledge representation and reasoning as a way to resolve the lack of transparency of machine learning classifiers is a research area that lately attracts many researchers.
Class-Wise Principal Component Analysis for hyperspectral image feature extraction
This paper introduces the Class-wise Principal Component Analysis, a supervised feature extraction method for hyperspectral data.
Semantic Enrichment of Pretrained Embedding Output for Unsupervised IR
The rapid growth of scientific literature in the biomedical and clinical domain has significantly com- plicated the identification of information of interest by researchers as well as other practitioners.
Ranked #1 on
Information Retrieval
on Ohsumed
