Search Results for author:
Found 57 papers, 34 papers with code
LARD: Large-scale Artificial Disfluency Generation
In addition, we release a new large-scale dataset with disfluencies that can be used on four different tasks: disfluency detection, classification, extraction, and correction.
Towards Human-Centered Summarization: A Case Study on Financial News
In order to overcome these issues, we reconsider the task of summarization from a human-centered perspective.
The concept of nation in nineteenth-century Greek fiction through computational literary analysis
How the construction of national consciousness may be captured in the literary production of a whole century?
Keyphrase Extraction from Scientific Articles via Extractive Summarization
Automatically extracting keyphrases from scholarly documents leads to a valuable concise representation that humans can understand and machines can process for tasks, such as information retrieval, article clustering and article classification.
Keyword Extraction Using Unsupervised Learning on the Document’s Adjacency Matrix
This work revisits the information given by the graph-of-words and its typical utilization through graph-based ranking approaches in the context of keyword extraction.
AUTH @ CLSciSumm 20, LaySumm 20, LongSumm 20
We present the systems we submitted for the shared tasks of the Workshop on Scholarly Document Processing at EMNLP 2020.
DUAL: Diversity and Uncertainty Active Learning for Text Summarization
Active learning methods typically prioritize either uncertainty or diversity but have shown limited effectiveness in summarization, often being outperformed by random sampling.
Batch Selection for Multi-Label Classification Guided by Uncertainty and Dynamic Label Correlations
The accuracy of deep neural networks is significantly influenced by the effectiveness of mini-batch construction during training.
AUTH at BioLaySumm 2024: Bringing Scientific Content to Kids
The BioLaySumm 2024 shared task at the ACL 2024 BioNLP workshop aims to transform biomedical research articles into lay summaries suitable for a broad audience, including children.
Multi-Label Adaptive Batch Selection by Highlighting Hard and Imbalanced Samples
However, the intrinsic class imbalance in multi-label data may bias the model towards majority labels, since samples relevant to minority labels may be underrepresented in each mini-batch.
From Lengthy to Lucid: A Systematic Literature Review on NLP Techniques for Taming Long Sentences
This survey, conducted using the PRISMA guidelines, systematically reviews two main strategies for addressing the issue of long sentences: a) sentence compression and b) sentence splitting.
Local Interpretability of Random Forests for Multi-Target Regression
Although model-agnostic techniques exist for multi-target regression, specific techniques tailored to random forest models are not available.
Does Noise Affect Housing Prices? A Case Study in the Urban Area of Thessaloniki
Real estate markets depend on various methods to predict housing prices, including models that have been trained on datasets of residential or commercial properties.
Large-scale investigation of weakly-supervised deep learning for the fine-grained semantic indexing of biomedical literature
Conclusion: The results suggest that concept occurrence is a strong heuristic for refining the coarse-grained labels at the level of MeSH concepts and the proposed method improves it further.
Truthful Meta-Explanations for Local Interpretability of Machine Learning Models
As a result, the demand for a selection tool, a meta-explanation technique based on a high-quality evaluation metric, is apparent.
Fine-Grained Selective Similarity Integration for Drug-Target Interaction Prediction
Recently, with the availability of abundant heterogeneous biological information from diverse data sources, computational methods have been able to leverage multiple drug and target similarities to boost the performance of DTI prediction.
An Attention Matrix for Every Decision: Faithfulness-based Arbitration Among Multiple Attention-Based Interpretations of Transformers in Text Classification
Transformers are widely used in natural language processing, where they consistently achieve state-of-the-art performance.
Local Multi-Label Explanations for Random Forest
Random Forest falls short on this property, especially when a large number of tree predictors are used.
Topic-Controllable Summarization: Topic-Aware Evaluation and Transformer Methods
Topic-controllable summarization is an emerging research area with a wide range of potential applications.
Local Explanation of Dimensionality Reduction
Dimensionality reduction (DR) is a popular method for preparing and analyzing high-dimensional data.
Multiple Similarity Drug-Target Interaction Prediction with Random Walks and Matrix Factorization
Moreover, the validation of highly ranked non-interacting pairs also demonstrates the potential of MDMF2A to discover novel DTIs.
Bayesian Active Summarization
Bayesian Active Learning has had significant impact to various NLP problems, but nevertheless it's application to text summarization has been explored very little.
Short-term Renewable Energy Forecasting in Greece using Prophet Decomposition and Tree-based Ensembles
Energy production using renewable sources exhibits inherent uncertainties due to their intermittent nature.
Harvesting the Public MeSH Note field
In this document, we report an analysis of the Public MeSH Note field of the new descriptors introduced in the MeSH thesaurus between 2006 and 2020.
Should We Trust This Summary? Bayesian Abstractive Summarization to The Rescue
We explore the notion of uncertainty in the context of modern abstractive summarization models, using the tools of Bayesian Deep Learning.
Optimizing Area Under the Curve Measures via Matrix Factorization for Predicting Drug-Target Interaction with Multiple Similarities
In drug discovery, identifying drug-target interactions (DTIs) via experimental approaches is a tedious and expensive procedure.
Conclusive Local Interpretation Rules for Random Forests
LionForests is a random forest-specific interpretation technique, which provides rules as explanations.
LioNets: A Neural-Specific Local Interpretation Technique Exploiting Penultimate Layer Information
Artificial Intelligence (AI) has a tremendous impact on the unexpected growth of technology in almost every aspect.
VisioRed: A Visualisation Tool for Interpretable Predictive Maintenance
The use of machine learning rapidly increases in high-risk scenarios where decisions are required, for example in healthcare or industrial monitoring equipment.
Improving Zero-Shot Entity Retrieval through Effective Dense Representations
We achieve a new state-of-the-art 84. 28% accuracy on top-50 candidates on the Zeshel dataset, compared to the previous 82. 06% on the top-64 of (Wu et al., 2020).
Improving Distantly-Supervised Relation Extraction through BERT-based Label & Instance Embeddings
We propose REDSandT (Relation Extraction with Distant Supervision and Transformers), a novel distantly-supervised transformer-based RE method, that manages to capture a wider set of relations through highly informative instance and label embeddings for RE, by exploiting BERT's pre-trained model, and the relationship between labels and entities, respectively.
Ranked #2 on
Relationship Extraction (Distant Supervised)
on New York Times Corpus
(AUC metric)
What is all this new MeSH about? Exploring the semantic provenance of new descriptors in the MeSH thesaurus
To this end, we propose a framework to categorize new descriptors based on their current relation to older descriptors.
Drug-Target Interaction Prediction via an Ensemble of Weighted Nearest Neighbors with Interaction Recovery
In addition, WkNNIR exploits local imbalance to promote the influence of more reliable similarities on the interaction recovery and prediction processes.
From Protocol to Screening: A Hybrid Learning Approach for Technology-Assisted Systematic Literature Reviews
We present a novel method for TAR that implements a full pipeline from the research protocol to the screening of the relevant papers.
Altruist: Argumentative Explanations through Local Interpretations of Predictive Models
Lack of evaluation and selection criteria also makes it difficult for the end user to choose the most suitable technique.
Keywords lie far from the mean of all words in local vector space
Keyword extraction is an important document process that aims at finding a small set of terms that concisely describe a document's topics.
ETHOS: an Online Hate Speech Detection Dataset
Online hate speech is a recent problem in our society that is rising at a steady pace by leveraging the vulnerabilities of the corresponding regimes that characterise most social media platforms.
Ranked #1 on
Hate Speech Detection
on Ethos MultiLabel
Beyond MeSH: Fine-Grained Semantic Indexing of Biomedical Literature based on Weak Supervision
To this end, we propose a new method that uses weak supervision to train a concept annotator on the literature available for a particular disease.
Multi-Label Sampling based on Local Label Imbalance
Experimental results on 13 multi-label datasets demonstrate the effectiveness of the proposed measure and sampling approaches for a variety of evaluation metrics, particularly in the case of an ensemble of classifiers trained on repeated samples of the original data.
A Divide-and-Conquer Approach to the Summarization of Long Documents
With this approach we can decompose the problem of long document summarization into smaller and simpler problems, reducing computational complexity and creating more training examples, which at the same time contain less noise in the target summaries compared to the standard approach.
Ranked #14 on
Text Summarization
on Pubmed
(using extra training data)
LionForests: Local Interpretation of Random Forests
Towards a future where machine learning systems will integrate into every aspect of people's lives, researching methods to interpret such systems is necessary, instead of focusing exclusively on enhancing their performance.
LioNets: Local Interpretation of Neural Networks through Penultimate Layer Decoding
Technological breakthroughs on smart homes, self-driving cars, health care and robotic assistants, in addition to reinforced law regulations, have critically influenced academic research on explainable machine learning.
Structured Summarization of Academic Publications
We propose SUSIE, a novel summarization method that can work with state-of-the-art summarization models in order to produce structured scientific summaries for academic articles.
A Review of Keyphrase Extraction
Keyphrase extraction is a textual information processing task concerned with the automatic extraction of representative and characteristic phrases from a document that express all the key aspects of its content.
Synthetic Oversampling of Multi-Label Data based on Local Label Distribution
Class-imbalance is an inherent characteristic of multi-label data which affects the prediction accuracy of most multi-label learning methods.
Unsupervised Keyphrase Extraction from Scientific Publications
It then uses the minimum covariance determinant estimator to model the distribution of non-keyphrase word vectors, under the assumption that these vectors come from the same distribution, indicative of their irrelevance to the semantics expressed by the dimensions of the learned vector representation.
Making Classifier Chains Resilient to Class Imbalance
Class imbalance is an intrinsic characteristic of multi-label data.
Web Robot Detection in Academic Publishing
In this paper, we present our approach on detecting web robots in academic publishing websites.
Local Word Vectors Guiding Keyphrase Extraction
Automated keyphrase extraction is a fundamental textual information processing task concerned with the selection of representative phrases from a document that summarize its content.
Subset Labeled LDA for Large-Scale Multi-Label Classification
We conduct extensive experiments on eight data sets, with label sets sizes ranging from hundreds to hundreds of thousands, comparing our proposed algorithm with the previously proposed LLDA algorithms (Prior--LDA, Dep--LDA), as well as the state of the art in extreme multi-label classification.
Large-Scale Online Semantic Indexing of Biomedical Articles via an Ensemble of Multi-Label Classification Models
Background: In this paper we present the approaches and methods employed in order to deal with a large scale multi-label semantic indexing task of biomedical papers.
Hierarchical Partitioning of the Output Space in Multi-label Data
Hierarchy Of Multi-label classifiers (HOMER) is a multi-label learning algorithm that breaks the initial learning task to several, easier sub-tasks by first constructing a hierarchy of labels from a given label set and secondly employing a given base multi-label classifier (MLC) to the resulting sub-problems.
Dense Distributions from Sparse Samples: Improved Gibbs Sampling Parameter Estimators for LDA
We introduce a novel approach for estimating Latent Dirichlet Allocation (LDA) parameters from collapsed Gibbs samples (CGS), by leveraging the full conditional distributions over the latent variable assignments to efficiently average over multiple samples, for little more computational cost than drawing a single additional collapsed Gibbs sample.
Multi-Target Regression via Random Linear Target Combinations
Multi-target regression is concerned with the simultaneous prediction of multiple continuous target variables based on the same set of input variables.
Discovering and Exploiting Entailment Relationships in Multi-Label Learning
Marginal probabilities are entered as soft evidence in the network and adjusted through probabilistic inference.
Multi-Target Regression via Input Space Expansion: Treating Targets as Inputs
When the prediction targets are binary the task is called multi-label classification, while when the targets are continuous the task is called multi-target regression.
