Search Results for author: Dimitar Trajanov

Found 6 papers, 1 papers with code

ISO-based Annotated Multilingual Parallel Corpus for Discourse Markers

no code implementations LREC 2022 Purificação Silvano, Mariana Damova, Giedrė Valūnaitė Oleškevičienė, Chaya Liebeskind, Christian Chiarcos, Dimitar Trajanov, Ciprian-Octavian Truică, Elena-Simona Apostol, Anna Baczkowska

In order to represent the meaning of the discourse markers, we propose an annotation scheme of discourse relations from ISO 24617-8 with a plug-in to ISO 24617-2 for communicative functions.

Sentiment Analysis in Finance: From Transformers Back to eXplainable Lexicons (XLex)

1 code implementation6 Jun 2023 Maryan Rizinski, Hristijan Peshov, Kostadin Mishev, Milos Jovanovik, Dimitar Trajanov

Lastly, the XLex approach is inherently more interpretable than transformer models as lexicon models rely on predefined rules, allowing for better insights into the results of SA and making the XLex approach a viable tool for financial decision-making.

Decision Making Sentiment Analysis

Enhancing Knowledge Graph Construction Using Large Language Models

no code implementations8 May 2023 Milena Trajanoska, Riste Stojanov, Dimitar Trajanov

The growing trend of Large Language Models (LLM) development has attracted significant attention, with models for various applications emerging consistently.

graph construction Joint Entity and Relation Extraction +1

Company classification using zero-shot learning

no code implementations1 May 2023 Maryan Rizinski, Andrej Jankov, Vignesh Sankaradas, Eugene Pinsky, Igor Miskovski, Dimitar Trajanov

In recent years, natural language processing (NLP) has become increasingly important in a variety of business applications, including sentiment analysis, text classification, and named entity recognition.

named-entity-recognition Named Entity Recognition +4

PharmKE: Knowledge Extraction Platform for Pharmaceutical Texts using Transfer Learning

no code implementations25 Feb 2021 Nasi Jofche, Kostadin Mishev, Riste Stojanov, Milos Jovanovik, Dimitar Trajanov

The methodology is used to create accurately labeled training and test datasets, which are then used to train models for custom entity labeling tasks, centered on the pharmaceutical domain.

named-entity-recognition Named Entity Recognition +6

Cannot find the paper you are looking for? You can Submit a new open access paper.