Search Results for author:
Found 16 papers, 2 papers with code
Propagation of emotions, arousal and polarity in WordNet using Heterogeneous Structured Synset Embeddings
In this paper we present a novel method for emotive propagation in a wordnet based on a large emotive seed.
Testing Zipf’s meaning-frequency law with wordnets as sense inventories
According to George K. Zipf, more frequent words have more senses.
A Comparison of Sense-level Sentiment Scores
In this paper, we compare a variety of sense-tagged sentiment resources, including SentiWordNet, ML-Senticon, plWordNet emo and the NTU Multilingual Corpus.
Discriminating Homonymy from Polysemy in Wordnets: English, Spanish and Polish Nouns
We propose a novel method of homonymy-polysemy discrimination for three Indo-European Languages (English, Spanish and Polish).
Neural Language Models vs Wordnet-based Semantically Enriched Representation in CST Relation Recognition
Neural language models, including transformer-based models, that are pre-trained on very large corpora became a common way to represent text in various tasks, including recognition of textual semantic relations, e. g. Cross-document Structure Theory.
Wordnet-based Evaluation of Large Distributional Models for Polish
The paper presents construction of large scale test datasets for word embeddings on the basis of a very large wordnet.
Recognition of Hyponymy and Meronymy Relations in Word Embeddings for Polish
Word embeddings were used for the extraction of hyponymy relation in several approaches, but also it was recently shown that they should not work, in fact.
Context-sensitive Sentiment Propagation in WordNet
In this paper we present a comprehensive overview of recent methods of the sentiment propagation in a wordnet.
Personalized Large Language Models
Large language models (LLMs) have significantly advanced Natural Language Processing (NLP) tasks in recent years.
BEIR-PL: Zero Shot Information Retrieval Benchmark for the Polish Language
In this work, inspired by mMARCO and Mr.~TyDi datasets, we translated all accessible open IR datasets into Polish, and we introduced the BEIR-PL benchmark -- a new benchmark which comprises 13 datasets, facilitating further development, training and evaluation of modern Polish language models for IR tasks.
ChatGPT: Jack of all trades, master of none
Our comparison of its results with available State-of-the-Art (SOTA) solutions showed that the average loss in quality of the ChatGPT model was about 25% for zero-shot and few-shot evaluation.
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.
Brand-Product Relation Extraction Using Heterogeneous Vector Space Representations
Relation Extraction is a fundamental NLP task.
Word Sense Disambiguation based on Constrained Random Walks in Linked Semantic Networks
Word Sense Disambiguation remains a challenging NLP task.
Graph-Based Approach to Recognizing CST Relations in Polish Texts
Similarity between sentences is calculated from graph, and the similarity values are input to classifiers trained by Logistic Model Tree.
