CLARIN-PL
Not a member yet
504 research outputs found
Sort by
Big Data language model - subword - BPE - ARPA
No full textBig data language model based on subword units, based on byte pair encoding in ARPA forma
Big Data language model - subword - SYLLABED - RAW
No full textBig data language model based on syllabes in RAW forma
Big Data language model in Word2Vec CBOW format.
No full textBig Data language model in Word2Vec CBOW format
Big Data language model - subword - SYLLABED - ARPA
No full textBig data language model based on syllabes in ARPA format
XLM-RoBERTa event relations recognition
No full textEvent relations recognition models for the Polish language, based on the XLM-RoBERTa language model
PolEmo 1.0 + MultiEmo-Test 1.0 Multilingual Sentiment Analysis Dataset for KES2020
No full textPolEmo 1.0 + MultiEmo-Test 1.0: Corpus of Multi-Domain Consumer Reviews. Test dataset from PolEmo 1.0 was translated to eight different languages: Dutch, English, French, German, Italian, Portuguese, Russian and Spanish.
Citation:
@article{KANCLERZ2020128,
title = {Cross-lingual deep neural transfer learning in sentiment analysis},
journal = {Procedia Computer Science},
volume = {176},
pages = {128-137},
year = {2020},
note = {Knowledge-Based and Intelligent Information & Engineering Systems: Proceedings of the 24th International Conference KES2020},
issn = {1877-0509},
doi = {https://doi.org/10.1016/j.procs.2020.08.014},
url = {https://www.sciencedirect.com/science/article/pii/S187705092031838X},
author = {Kamil Kanclerz and Piotr Miłkowski and Jan Kocoń},
keywords = {natural language processing, sentiment analysis, polarity recognition, transfer learning, deep learning, multilingual approach},
abstract = {In this article, we present a novel technique for the use of language-agnostic sentence representations to adapt the model trained on texts in Polish (as a low-resource language) to recognize polarity in texts in other (high-resource) languages. The first model focuses on the creation of a language-agnostic representation of each sentence. The second one aims to predict the sentiment of the text based on these sentence representations. Besides models evaluation on PolEmo 1.0 Sentiment Corpus, we also conduct a proof of concept for using a deep neural network model trained only on language-agnostic embeddings of texts in Polish to predict the sentiment of the texts in MultiEmo-Test 1.0 Sentiment Corpus, containing PolEmo 1.0 test datasets translated into eight different languages: Dutch, English, French, German, Italian, Portuguese, Russian and Spanish. Both corpora are publicly available under a Creative Commons copyright license.}
XLM-RoBERTa events recognition
No full textEvent recognition models for the Polish language, based on the XLM-RoBERTa language model
Big Data language model - second version - RAW
No full textBig Data language model - second version - RA
Expanding WordNet with Gloss and Polysemy Links for Evocation Strength Recognition
Get PDFEvocation — a phenomenon of sense associations going beyond standard (lexico)-semantic relations — is difficult to recognise for natural language processing systems. Machine learning models give predictions which are only moderately correlated with the evocation strength. It is believed that ordinary graph measures are not as good at this task as methods based on vector representations. The paper proposes a new method of enriching the WordNet structure with weighted polysemy and gloss links, and proves that Dijkstra’s algorithm performs equally as well as other more sophisticated measures when set together with such expanded structures