DiaBiz.Kom - towards a Polish Dialogue Act Corpus Based on ISO 24617-2 Standard

no code implementations • COLING 2022 • Marcin Oleksy, Jan Wieczorek, Dorota Drużyłowska, Julia Klyus, Aleksandra Domogała, Krzysztof Hwaszcz, Hanna Kędzierska, Daria Mikoś, Anita Wróż

This article presents the specification and evaluation of DiaBiz. Kom – the corpus of dialogue texts in Polish.

Developing PUGG for Polish: A Modern Approach to KBQA, MRC, and IR Dataset Construction

1 code implementation • 5 Aug 2024 • Albert Sawczyn, Katsiaryna Viarenich, Konrad Wojtasik, Aleksandra Domogała, Marcin Oleksy, Maciej Piasecki, Tomasz Kajdanowicz

Advancements in AI and natural language processing have revolutionized machine-human language interactions, with question answering (QA) systems playing a pivotal role.

Information Retrieval Knowledge Base Question Answering +2

ChatGPT: Jack of all trades, master of none

1 code implementation • 21 Feb 2023 • Jan Kocoń, Igor Cichecki, Oliwier Kaszyca, Mateusz Kochanek, Dominika Szydło, Joanna Baran, Julita Bielaniewicz, Marcin Gruza, Arkadiusz Janz, Kamil Kanclerz, Anna Kocoń, Bartłomiej Koptyra, Wiktoria Mieleszczenko-Kowszewicz, Piotr Miłkowski, Marcin Oleksy, Maciej Piasecki, Łukasz Radliński, Konrad Wojtasik, Stanisław Woźniak, Przemysław Kazienko

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.

All Chatbot +7

PST 2.0 -- Corpus of Polish Spatial Texts

no code implementations • LREC 2020 • Micha{\l} Marci{\'n}czuk, Marcin Oleksy, Jan Wieczorek

We have defined our guidelines based on three existing specifications for English (SpatialML, SpatialRole Labelling from SemEval-2013 Task 3 and ISO-Space1. 4 from SpaceEval 2014).

Inforex --- a Collaborative Systemfor Text Corpora Annotation and Analysis Goes Open

1 code implementation • RANLP 2019 • Micha{\l} Marci{\'n}czuk, Marcin Oleksy

In the paper we present the latest changes introduce to Inforex {---} a web-based system for qualitative and collaborative text corpora annotation and analysis.

Attribute Morphological Disambiguation +2

Tagger for Polish Computer Mediated Communication Texts

no code implementations • RANLP 2019 • Wiktor Walentynowicz, Maciej Piasecki, Marcin Oleksy

In this paper we present a morpho-syntactic tagger dedicated to Computer-mediated Communication texts in Polish.

Clustering Sentence

Inforex --- a collaborative system for text corpora annotation and analysis

no code implementations • RANLP 2017 • Micha{\l} Marci{\'n}czuk, Marcin Oleksy, Jan Koco{\'n}

We report a first major upgrade of Inforex {---} a web-based system for qualitative and collaborative text corpora annotation and analysis.

Named Entity Recognition (NER) Word Sense Disambiguation

Liner2 --- a Generic Framework for Named Entity Recognition

no code implementations • WS 2017 • Micha{\l} Marci{\'n}czuk, Jan Koco{\'n}, Marcin Oleksy

In the paper we present an adaptation of Liner2 framework to solve the BSNLP 2017 shared task on multilingual named entity recognition.

Morphological Analysis Multilingual Named Entity Recognition +2