Search Results for author:
Found 35 papers, 20 papers with code
Electoral Agitation Dataset: The Use Case of the Polish Election
Therefore, social media is full of electoral agitation (electioneering), especially during the election campaigns.
FactSelfCheck: Fact-Level Black-Box Hallucination Detection for LLMs
While existing hallucination detection methods typically operate at the sentence level or passage level, we propose FactSelfCheck, a novel black-box sampling-based method that enables fine-grained fact-level detection.
Hallucination Detection in LLMs Using Spectral Features of Attention Maps
We propose the $\text{LapEigvals}$ method, which utilises the top-$k$ eigenvalues of the Laplacian matrix derived from the attention maps as an input to hallucination detection probes.
Developing PUGG for Polish: A Modern Approach to KBQA, MRC, and IR Dataset Construction
Advancements in AI and natural language processing have revolutionized machine-human language interactions, with question answering (QA) systems playing a pivotal role.
Empowering Small-Scale Knowledge Graphs: A Strategy of Leveraging General-Purpose Knowledge Graphs for Enriched Embeddings
Knowledge-intensive tasks pose a significant challenge for Machine Learning (ML) techniques.
Representation learning in multiplex graphs: Where and how to fuse information?
In recent years, unsupervised and self-supervised graph representation learning has gained popularity in the research community.
Unveiling the Potential of Probabilistic Embeddings in Self-Supervised Learning
In recent years, self-supervised learning has played a pivotal role in advancing machine learning by allowing models to acquire meaningful representations from unlabeled data.
Similarity-based Memory Enhanced Joint Entity and Relation Extraction
Document-level joint entity and relation extraction is a challenging information extraction problem that requires a unified approach where a single neural network performs four sub-tasks: mention detection, coreference resolution, entity classification, and relation extraction.
coreference-resolution
Joint Entity and Relation Extraction
+2
Electoral Agitation Data Set: The Use Case of the Polish Election
Therefore, social media is full of electoral agitation (electioneering), especially during the election campaigns.
Domain-Agnostic Neural Architecture for Class Incremental Continual Learning in Document Processing Platform
Production deployments in complex systems require ML architectures to be highly efficient and usable against multiple tasks.
RAFEN -- Regularized Alignment Framework for Embeddings of Nodes
A well-defined node embedding model should reflect both node features and the graph structure in the final embedding.
Graph-level representations using ensemble-based readout functions
Graph machine learning models have been successfully deployed in a variety of application areas.
Neural Architecture for Online Ensemble Continual Learning
Continual learning with an increasing number of classes is a challenging task.
This is the way: designing and compiling LEPISZCZE, a comprehensive NLP benchmark for Polish
In this paper, we introduce LEPISZCZE (the Polish word for glew, the Middle English predecessor of glue), a new, comprehensive benchmark for Polish NLP with a large variety of tasks and high-quality operationalization of the benchmark.
Assessment of Massively Multilingual Sentiment Classifiers
We use these to assess 11 models and 80 high-quality sentiment datasets (out of 342 raw datasets collected) in 27 languages and included results on the internally annotated datasets.
Spatial Data Mining of Public Transport Incidents reported in Social Media
We successfully build an information type classifier for social media posts, detect stop names in posts, and relate them to GPS coordinates, obtaining a spatial understanding of long-term aggregated phenomena.
Controversy and Conformity: from Generalized to Personalized Aggressiveness Detection
There is content such as hate speech, offensive, toxic or aggressive documents, which are perceived differently by their consumers.
Graph Barlow Twins: A self-supervised representation learning framework for graphs
The self-supervised learning (SSL) paradigm is an essential exploration area, which tries to eliminate the need for expensive data labeling.
AttrE2vec: Unsupervised Attributed Edge Representation Learning
Representation learning has overcome the often arduous and manual featurization of networks through (unsupervised) feature learning as it results in embeddings that can apply to a variety of downstream learning tasks.
UCSG-NET- Unsupervised Discovering of Constructive Solid Geometry Tree
On the contrary, we propose a model that extracts a CSG parse tree without any supervision - UCSG-Net.
Political Advertising Dataset: the use case of the Polish 2020 Presidential Elections
Political advertisements constitute a basic form of campaigning, subjected to various social requirements.
UCSG-Net -- Unsupervised Discovering of Constructive Solid Geometry Tree
On the contrary, we propose a model that extracts a CSG parse tree without any supervision - UCSG-Net.
Comprehensive Analysis of Aspect Term Extraction Methods using Various Text Embeddings
Recently, a variety of model designs and methods have blossomed in the context of the sentiment analysis domain.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
Extracting Aspects Hierarchies using Rhetorical Structure Theory
We propose a novel approach to generate aspect hierarchies that proved to be consistently correct compared with human-generated hierarchies.
Aspect Detection using Word and Char Embeddings with (Bi)LSTM and CRF
We proposed a~new accurate aspect extraction method that makes use of both word and character-based embeddings.
FILDNE: A Framework for Incremental Learning of Dynamic Networks Embeddings
Experimental results on several downstream tasks, over seven real-world data sets, show that FILDNE is able to reduce memory and computational time costs while providing competitive quality measure gains with respect to the contemporary methods for representation learning on dynamic graphs.
LNEMLC: Label Network Embeddings for Multi-Label Classification
Multi-label classification aims to classify instances with discrete non-exclusive labels.
Graph Energies of Egocentric Networks and Their Correlation with Vertex Centrality Measures
We show that when graph energies are applied to local egocentric networks, the values of these energies correlate strongly with vertex centrality measures.
Social and Information Networks Physics and Society
Method for Aspect-Based Sentiment Annotation Using Rhetorical Analysis
This paper fills a gap in aspect-based sentiment analysis and aims to present a new method for preparing and analysing texts concerning opinion and generating user-friendly descriptive reports in natural language.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+1
A Network Perspective on Stratification of Multi-Label Data
We present a new approach to stratifying multi-label data for classification purposes based on the iterative stratification approach proposed by Sechidis et.
Is a Data-Driven Approach still Better than Random Choice with Naive Bayes classifiers?
In case of F1 scores and Subset Accuracy - data driven approaches were more likely to perform better than random approaches than otherwise in the worst case.
A scikit-based Python environment for performing multi-label classification
It provides native Python implementations of popular multi-label classification methods alongside a novel framework for label space partitioning and division.
WordNet2Vec: Corpora Agnostic Word Vectorization Method
Since WordNet embeds natural language in the form of a complex network, a transformation mechanism WordNet2Vec is proposed in the paper.
How is a data-driven approach better than random choice in label space division for multi-label classification?
We show that fastgreedy and walktrap community detection methods on weighted label co-occurence graphs are 85-92% more likely to yield better F1 scores than random partitioning.
Learning in Unlabeled Networks - An Active Learning and Inference Approach
The question that arises is: "labels of which nodes should be collected and used for learning in order to provide the best classification accuracy for the whole network?".
