Search Results for author:
Found 55 papers, 17 papers with code
Exploring Neural Language Models via Analysis of Local and Global Self-Attention Spaces
Large pretrained language models using the transformer neural network architecture are becoming a dominant methodology for many natural language processing tasks, such as question answering, text classification, word sense disambiguation, text completion and machine translation.
Sentiment Classification by Incorporating Background Knowledge from Financial Ontologies
Ontologies are increasingly used for machine reasoning over the last few years.
Slav-NER: the 3rd Cross-lingual Challenge on Recognition, Normalization, Classification, and Linking of Named Entities across Slavic Languages
Seven teams covered all six languages, and five teams participated in the cross-lingual entity linking task.
Exploratory Analysis of News Sentiment Using Subgroup Discovery
In this study, we present an exploratory analysis of a Slovenian news corpus, in which we investigate the association between named entities and sentiment in the news.
EMBEDDIA hackathon report: Automatic sentiment and viewpoint analysis of Slovenian news corpus on the topic of LGBTIQ+
We conduct automatic sentiment and viewpoint analysis of the newly created Slovenian news corpus containing articles related to the topic of LGBTIQ+ by employing the state-of-the-art news sentiment classifier and a system for semantic change detection.
Interesting cross-border news discovery using cross-lingual article linking and document similarity
Team Name: team-8 Embeddia Tool: Cross-Lingual Document Retrieval Zosa et al. Dataset: Estonian and Latvian news datasets abstract: Contemporary news media face increasing amounts of available data that can be of use when prioritizing, selecting and discovering new news.
EMBEDDIA Tools, Datasets and Challenges: Resources and Hackathon Contributions
This paper presents tools and data sources collected and released by the EMBEDDIA project, supported by the European Union’s Horizon 2020 research and innovation program.
BERT meets Shapley: Extending SHAP Explanations to Transformer-based Classifiers
Transformer-based neural networks offer very good classification performance across a wide range of domains, but do not provide explanations of their predictions.
Zero-shot Cross-lingual Content Filtering: Offensive Language and Hate Speech Detection
We present a system for zero-shot cross-lingual offensive language and hate speech classification.
EMBEDDIA project: Cross-Lingual Embeddings for Less- Represented Languages in European News Media
EMBEDDIA project developed a range of resources and methods for less-resourced EU languages, focusing on applications for media industry, including keyword extraction, comment moderation and article generation.
IJS at TextGraphs-16 Natural Language Premise Selection Task: Will Contextual Information Improve Natural Language Premise Selection?
The results demonstrate that the contextual representation is better at capturing meaningful information despite not being pretrained in the mathematical background compared to the statistical approach (e. g., the TF-IDF) with a boost of around 3. 00% MAP@500.
Fusion of linguistic, neural and sentence-transformer features for improved term alignment
Crosslingual terminology alignment task has many practical applications.
Extracting and Analysing Metaphors in Migration Media Discourse: towards a Metaphor Annotation Scheme
The study of metaphors in media discourse is an increasingly researched topic as media are an important shaper of social reality and metaphors are an indicator of how we think about certain issues through references to other things.
E8-IJS@LT-EDI-ACL2022 - BERT, AutoML and Knowledge-graph backed Detection of Depression
Depression is a mental illness that negatively affects a person’s well-being and can, if left untreated, lead to serious consequences such as suicide.
JSI at SemEval-2022 Task 1: CODWOE - Reverse Dictionary: Monolingual and cross-lingual approaches
The reverse dictionary task is a sequence-to-vector task in which a gloss is provided as input, and the output must be a semantically matching word vector.
Tracking Changes in ESG Representation: Initial Investigations in UK Annual Reports
We describe initial work into analysing the language used around environmental, social and governance (ESG) issues in UK company annual reports.
Embeddings models for Buddhist Sanskrit
We release a novel corpus of Buddhist texts, a novel corpus of general Sanskrit and word similarity and word analogy datasets for intrinsic evaluation of Buddhist Sanskrit embeddings models.
A Computational Analysis of the Dehumanisation of Migrants from Syria and Ukraine in Slovene News Media
Dehumanisation involves the perception and or treatment of a social group's members as less than human.
Multi-Task Learning for Features Extraction in Financial Annual Reports
For assessing various performance indicators of companies, the focus is shifting from strictly financial (quantitative) publicly disclosed information to qualitative (textual) information.
Semantic change detection for Slovene language: a novel dataset and an approach based on optimal transport
In this paper, we focus on the detection of semantic changes in Slovene, a less resourced Slavic language with two million speakers.
AHAM: Adapt, Help, Ask, Model -- Harvesting LLMs for literature mining
Our system aims to reduce both the ratio of outlier topics to the total number of topics and the similarity between topic definitions.
Latent Graphs for Semi-Supervised Learning on Biomedical Tabular Data
In the domain of semi-supervised learning, the current approaches insufficiently exploit the potential of considering inter-instance relationships among (un)labeled data.
Measuring Catastrophic Forgetting in Cross-Lingual Transfer Paradigms: Exploring Tuning Strategies
As cross-lingual transfer strategies, we compare the intermediate-training (\textit{IT}) that uses each language sequentially and cross-lingual validation (\textit{CLV}) that uses a target language already in the validation phase of fine-tuning.
Detection of depression on social networks using transformers and ensembles
As the impact of technology on our lives is increasing, we witness increased use of social media that became an essential tool not only for communication but also for sharing information with community about our thoughts and feelings.
XAI in Computational Linguistics: Understanding Political Leanings in the Slovenian Parliament
We develop both classical machine learning and transformer language models to predict the left- or right-leaning of parliamentarians based on their given speeches on the topic of migrants.
The Recent Advances in Automatic Term Extraction: A survey
Automatic term extraction (ATE) is a Natural Language Processing (NLP) task that eases the effort of manually identifying terms from domain-specific corpora by providing a list of candidate terms.
Ensembling Transformers for Cross-domain Automatic Term Extraction
Automatic term extraction plays an essential role in domain language understanding and several natural language processing downstream tasks.
Retrieval-efficiency trade-off of Unsupervised Keyword Extraction
Efficiently identifying keyphrases that represent a given document is a challenging task.
Multi-label classification for biomedical literature: an overview of the BioCreative VII LitCovid Track for COVID-19 literature topic annotations
To close the gap, we organized the BioCreative LitCovid track to call for a community effort to tackle automated topic annotation for COVID-19 literature.
Out of Thin Air: Is Zero-Shot Cross-Lingual Keyword Detection Better Than Unsupervised?
We find that the pretrained models fine-tuned on a multilingual corpus covering languages that do not appear in the test set (i. e. in a zero-shot setting), consistently outscore unsupervised models in all six languages.
Named entity recognition architecture combining contextual and global features
Named entity recognition (NER) is an information extraction technique that aims to locate and classify named entities (e. g., organizations, locations,...) within a document into predefined categories.
Knowledge Graph informed Fake News Classification via Heterogeneous Representation Ensembles
Increasing amounts of freely available data both in textual and relational form offers exploration of richer document representations, potentially improving the model performance and robustness.
Prioritization of COVID-19-related literature via unsupervised keyphrase extraction and document representation learning
The COVID-19 pandemic triggered a wave of novel scientific literature that is impossible to inspect and study in a reasonable time frame manually.
Evaluation of contextual embeddings on less-resourced languages
The current dominance of deep neural networks in natural language processing is based on contextual embeddings such as ELMo, BERT, and BERT derivatives.
JSI at the FinSim-2 task: Ontology-Augmented Financial Concept Classification
The task is to design a system that can automatically classify concepts from the Financial domain into the most relevant hypernym concept in an external ontology - the Financial Industry Business Ontology.
Extending Neural Keyword Extraction with TF-IDF tagset matching
Keyword extraction is the task of identifying words (or multi-word expressions) that best describe a given document and serve in news portals to link articles of similar topics.
Identification of COVID-19 related Fake News via Neural Stacking
Identification of Fake News plays a prominent role in the ongoing pandemic, impacting multiple aspects of day-to-day life.
SemEval-2020 Task 3: Graded Word Similarity in Context
This paper presents the Graded Word Similarity in Context (GWSC) task which asked participants to predict the effects of context on human perception of similarity in English, Croatian, Slovene and Finnish.
COVID-19 therapy target discovery with context-aware literature mining
The abundance of literature related to the widespread COVID-19 pandemic is beyond manual inspection of a single expert.
AttViz: Online exploration of self-attention for transparent neural language modeling
Neural language models are becoming the prevailing methodology for the tasks of query answering, text classification, disambiguation, completion and translation.
The NetViz terminology visualization tool and the use cases in karstology domain modeling
We showcase the usefulness of the tool on examples from the karstology domain, where in the first use case we visualize the domain knowledge as represented in a manually annotated corpus of domain definitions, while in the second use case we show the power of visualization for domain understanding by visualizing automatically extracted knowledge in the form of triplets extracted from the karstology domain corpus.
Mining Semantic Relations from Comparable Corpora through Intersections of Word Embeddings
We report an experiment aimed at extracting words expressing a specific semantic relation using intersections of word embeddings.
TNT-KID: Transformer-based Neural Tagger for Keyword Identification
With growing amounts of available textual data, development of algorithms capable of automatic analysis, categorization and summarization of these data has become a necessity.
CoSimLex: A Resource for Evaluating Graded Word Similarity in Context
State of the art natural language processing tools are built on context-dependent word embeddings, but no direct method for evaluating these representations currently exists.
Leveraging Contextual Embeddings for Detecting Diachronic Semantic Shift
We propose a new method that leverages contextual embeddings for the task of diachronic semantic shift detection by generating time specific word representations from BERT embeddings.
Emotion Recognition in Low-Resource Settings: An Evaluation of Automatic Feature Selection Methods
A machine learning model trained on a smaller feature set will reduce the memory and computational resources of an emotion recognition system which can result in lowering the barriers for use of health monitoring technology.
Supervised and Unsupervised Neural Approaches to Text Readability
We present a set of novel neural supervised and unsupervised approaches for determining the readability of documents.
Language comparison via network topology
In our experiments, we employ eight different network topology metrics, and empirically showcase on a parallel corpus, how the methods can be used for modeling the relations between nine selected languages.
RaKUn: Rank-based Keyword extraction via Unsupervised learning and Meta vertex aggregation
Keyword extraction is used for summarizing the content of a document and supports efficient document retrieval, and is as such an indispensable part of modern text-based systems.
tax2vec: Constructing Interpretable Features from Taxonomies for Short Text Classification
The use of background knowledge is largely unexploited in text classification tasks.
Gender Profiling for Slovene Twitter communication: the Influence of Gender Marking, Content and Style
Inspired by the TwiSty corpus and experiments (Verhoeven et al., 2016), we employed the Janes corpus (Erjavec et al., 2016) and its gender annotations to perform gender classification experiments on Twitter text comparing a token-based and a lemma-based approach.
Irregularity Detection in Categorized Document Corpora
The paper presents an approach to extract irregularities in document corpora, where the documents originate from different sources and the analyst's interest is to find documents which are atypical for the given source.
