The BEIR dataset is a large, heterogeneous benchmark for Information Retrieval (IR), garnering considerable attention within the research community. However, BEIR and analogous datasets are predominantly restricted to English language. Our objective is to establish extensive large-scale resources for IR in the Polish language, thereby advancing the research in this NLP area. 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. We executed an evaluation and comparison of numerous IR models on the newly introduced BEIR-PL benchmark. Furthermore, we publish pre-trained open IR models for Polish language, marking a pioneering development in this field. The BEIR-PL is included in MTEB Benchmark and also available with trained models at URL https://huggingface.co/clarin-knext.

Many knowledge-based solutions were proposed to solve Word Sense Disambiguation (WSD) problem with limited annotated resources.Such WSD algorithms are able to cover very large sense repositories, but still being outperformed by supervised ones on benchmark data.In this paper, we start with analysis identifying key properties and issues in application of spreading activation algorithms in knowledge-based WSD, e.g.influence of the network local structures, interaction with context information and sense frequency.Taking our observations as a point of departure, we introduce a novel solution with new contextto-sense matching using BERT embeddings, iterative parallel spreading activation function and selective sense alignment using contextual BERT embeddings.The proposed solution obtains performance beyond the state-of-the-art for the contemporary knowledge-based WSD approaches for both English and Polish data.

Focusing on recognition of multi-word expressions (MWEs), we address the problem of recording MWEs in WordNet.In fact, not all MWEs recorded in that lexical database could with no doubt be considered as lexicalised (e.g.elements of wordnet taxonomy, quantifier phrases, certain collocations).In this paper, we use a cross-encoder approach to improve our earlier method of distinguishing between lexicalised and non-lexicalised MWEs found in WordNet using custom-designed rulebased and statistical approaches.We achieve F1-measure for the class of lexicalised word combinations close to 80%, easily beating two baselines (random and a majority class one).Language model also proves to be better than a feature-based logistic regression model.

Derivational relations are an important element in defining meanings, as they help to explore word-formation schemes and predict senses of derivates (derived words).In this work, we analyse different methods of representing derivational forms obtained from WordNetfrom quantitative vectors to contextual learned embedding methods -and compare ways of classifying the derivational relations occurring between them.Our research focuses on the explainability of the obtained representations and results.The data source for our research is plWordNet, which is the wordnet of the Polish language and includes a rich set of derivation examples.

Data augmentation is a difficult task in Natural Language Processing.Simple methods that can be relatively easily applied in other domains like insertion, deletion or substitution, mostly result in changing the sentence meaning significantly and obtaining an incorrect example.Wordnets are potentially a perfect source of rich and high quality data that when integrated with the powerful capacity of generative models can help to solve this complex task.In this work, we use plWordNet, which is a wordnet of the Polish language, to explore the capability of encoder-decoder architectures in data augmentation of sense glosses.We discuss the limitations of generative methods and perform qualitative review of generated data samples.

The availability of compute and data to train larger and larger language models increases the demand for robust methods of benchmarking the true progress of LM training. Recent years witnessed significant progress in standardized benchmarking for English. Benchmarks such as GLUE, SuperGLUE, or KILT have become a de facto standard tools to compare large language models. Following the trend to replicate GLUE for other languages, the KLEJ benchmark\ (klej is the word for glue in Polish) has been released for Polish. In this paper, we evaluate the progress in benchmarking for low-resourced languages. We note that only a handful of languages have such comprehensive benchmarks. We also note the gap in the number of tasks being evaluated by benchmarks for resource-rich English/Chinese and the rest of the world.In this paper, we introduce LEPISZCZE (lepiszcze is 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.We design LEPISZCZE with flexibility in mind. Including new models, datasets, and tasks is as simple as possible while still offering data versioning and model tracking. In the first run of the benchmark, we test 13 experiments (task and dataset pairs) based on the five most recent LMs for Polish. We use five datasets from the Polish benchmark and add eight novel datasets. As the paper's main contribution, apart from LEPISZCZE, we provide insights and experiences learned while creating the benchmark for Polish as the blueprint to design similar benchmarks for other low-resourced languages.

Robust methods have been proposed for content and topic-based text classification, as well authorship attribution in stylometry. However, the problem of a fine-grained literary genre (style) recognition is much less studied. We present several approaches to the recognition of eight literary genres manually annotated in a large corpus of Polish blogs. Different text representations were combined with neural network classifiers, including deep, recursive neural networks. Very good results were achieved for the representation of blog posts with the help of pre-trained fastText word embeddings and the Bi-GRU recursive deep neural network as a classifier. As the observed good performance of this classifier could be a result of topical bias across genres, experiments on a selected sub-corpus with a reduced dominance of the most frequent topic were also conducted with no significant change observed.

Neural language models, including transformer-based models, that are pretrained 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.Pre-trained models are usually fine tuned to downstream tasks and the obtained vectors are used as an input for deep neural classifiers.No linguistic knowledge obtained from resources and tools is utilised.In this paper we compare such universal approaches with a combination of rich graph-based linguistically motivated sentence representation and a typical neural network classifier applied to a task of recognition of CST relation in Polish.The representation describes selected levels of the sentence structure including description of lexical meanings on the basis of the wordnet (plWordNet) synsets and connected SUMO concepts.The obtained results show that in the case of difficult relations and medium size training corpus semantically enriched text representation leads to significantly better results.

The paper reports on the methodology and final results of a large-scale synset mapping between plWordNet and Princeton WordNet.Dedicated manual and semi-automatic mapping procedures as well as interlingual relation types for nouns, verbs, adjectives and adverbs are described.The statistics of all types of interlingual relations are also provided.

Relation Extraction is a fundamental NLP task. In this paper we investigate the impact of underlying text representation on the performance of neural classification models in the task of Brand-Product relation extraction. We also present the methodology of preparing annotated textual corpora for this task and we provide valuable insight into the properties of Brand-Product relations existing in textual corpora. The problem is approached from a practical angle of applications Relation Extraction in facilitating commercial Internet monitoring.

In this paper, we compare a variety of sense-tagged sentiment resources, including SentiWordNet, ML-Senticon, plWord-Net emo and the NTU Multilingual Corpus.The goal is to investigate the quality of the resources and see how well the sentiment polarity annotation maps across languages.

The paper presents the latest release of the Polish WordNet, namely plWord-Net 4.1.The most significant developments since 3.0 version include new relations for nouns and verbs, mapping semantic role-relations from the valency lexicon Walenty onto the plWord-Net structure and sense-level interlingual mapping.Several statistics are presented in order to illustrate the development and contemporary state of the wordnet.

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.In our work we verified both claims using a very large wordnet of Polish as a gold standard for lexico-semantic relations and word embeddings extracted from a very large corpus of Polish.We showed that a hyponymy extraction method based on linear regression classifiers trained on clusters of vectors can be successfully applied on large scale.We presented also a possible explanation for contradictory findings in the literature.Moreover, in order to show the feasibility of the method we extended it to the recognition of meronymy.

The paper presents an expansion of the verb model for plWordNet -the wordnet of Polish.A modified system of constitutive features (register, aspect and verb classes), synset and lexical relations is presented.A special attention is given to the proposed new relations and changes in the verb classification.We discuss also the results of its verification by application to the description of a relatively large sample of Polish verbs.The model introduces a new class of relations, namely non-constitutive synset relations that are shared among lexical units, but describe, not define synsets.The proposed model is compared to the entailment relations in other wordnets, and the description of verbs based on valency frames.

In this paper we present a comprehensive overview of recent methods of the sentiment propagation in a wordnet.Next, we propose a fully automated method called Classifier-based Polarity Propagation, which utilises a very rich set of features, where most of them are based on wordnet relation types, multi-level bag-ofsynsets and bag-of-polarities.We have evaluated our solution using manually annotated part of plWordNet 3.1 emo, which contains more than 83k manual sentiment annotations, covering more than 41k synsets.We have demonstrated that in comparison to existing rule-based methods using a specific narrow set of semantic relations our method has achieved statistically significant and better results starting with the same seed synsets.

plWordNet, the wordnet of Polish, has become a very comprehensive description of the Polish lexical system.This paper presents a plan of its semi-automated integration with thesauri, terminological databases and ontologies, as a further necessary step in its development.This will improve linking of plWordNet into Linked Open Data, and facilitate applications in, e.g., WSD, keyword extraction or automated metadata generation.We present an overview of resources relevant to Polish and a plan for their linking to plWordNet.

The paper presents a new re-built and expanded, version 2.0 of WordnetLoom -an open wordnet editor.It facilitates work on a multilingual system of wordnets, is based on efficient software architecture of thin client, and offers more flexibility in enriching wordnet representation.This new version is built on the experience collected during the use of the previous one for more than 10 years of plWordNet development.We discuss its extensions motivated by the collected experience.A special focus is given to the development of a variant for the needs of MultiWordnet of Portuguese, which is based on a very different wordnet development model.

The paper presents construction of large scale test datasets for word embeddings on the basis of a very large wordnet.They were next applied for evaluation of word embedding models and used to assess and compare the usefulness of different word embeddings extracted from a very large corpus of Polish.We analysed also and compared several publicly available models described in literature.In addition, several large word embeddings models built on the basis of a very large Polish corpus are presented.

The paper presents a feature-based model of equivalence targeted at (manual) sense linking between Princeton WordNet and plWordNet.The model incorporates insights from lexicographic and translation theories on bilingual equivalence and draws on the results of earlier synsetlevel mapping of nouns between Princeton WordNet and plWordNet.It takes into account all basic aspects of language such as form, meaning and function and supplements them with (parallel) corpus frequency and translatability.Three types of equivalence are distinguished, namely strong, regular and weak depending on the conformity with the proposed features.The presented solutions are languageneutral and they can be easily applied to language pairs other than Polish and English.Sense-level mapping is a more finegrained mapping than the existing synset mappings and is thus of great potential to human and machine translation.

The paper presents an approach to building a very large emotive lexicon for Polish based on plWordNet.An expanded annotation model is discussed, in which lexical units (word senses) are annotated with basic emotions, fundamental human values and sentiment polarisation.The annotation process is performed manually in the 2+1 scheme by pairs of linguists and psychologies.Guidelines referring to the usage in corpora, substitution tests as well linguistic properties of lexical units (e.g.derivational associations) are discussed.Application of the model in a substantial extension of the emotive annotation of plWordNet is presented.The achieved high inter-annotator agreement shows that with relatively small workload a promising emotive resource can be created.

We have released plWordNet 3.0, a very large wordnet for Polish. In addition to what is expected in wordnets – richly interrelated synsets – it contains sentiment and emotion annotations, a large set of multi-word expressions, and a mapping onto WordNet 3.1. Part of the release is enWordNet 1.0, a substantially enlarged copy of WordNet 3.1, with material added to allow for a more complete mapping. The paper discusses the design principles of plWordNet, its content, its statistical portrait, a comparison with similar resources, and a partial list of applications.

The paper explores the application of plWordNet, a very large wordnet of Polish, in weakly supervised Word Sense Disambiguation (WSD).Because plWord-Net provides only partial descriptions by glosses and usage examples, and does not include sense-disambiguated glosses, PageRank-based WSD methods perform slightly worse than for English.However, we show that the use of weights for the relation types and the order in which lexical units have been added for sense re-ranking can significantly improve WSD precision.The evaluation was done on two Polish corpora (KPWr and Składnica) including manual WSD.We discuss the fundamental difference in the construction of both corpora and very different test results.

It took us nearly ten years to get from no wordnet for Polish to the largest wordnet ever built.We started small but quickly learned to dream big.Now we are about to release plWordNet 3.0-emo -complete with sentiment and emotions annotatedand a domestic version of Princeton Word-Net, larger than WordNet 3.1 by nearly ten thousand newly added words.The paper retraces the road we travelled and talks a little about the future.

A wordnet is many things to many people: a graph of inter-related lexicalised concepts, a taxonomy, a thesaurus, and so on.A wordnet makes good sense as the mainstay of any deep automated semantic analysis of text.We have begun the construction of a multi-component, multi-use toolkit of natural language processing tools with plWordNet, a very large Polish wordnet, at its centre.The components will include plWordNet and its mapping onto an ontology (the upper level and elements of the middle level), a lexicon of proper names and a semantic valency lexicon.Some of those elements will be aligned with plWordNet, and there will be a mapping onto Princeton WordNet.Several challenging applications will show the utility of the toolkit in practice.

Lexicalised concepts are represented in wordnets by word-sense pairs.The strength of markedness is one of the factors which influence word use.Stylistically unmarked words are largely contextneutral.Technical terms, obsolete words, "officialese", slangs, obscenities and so on are all marked, often strongly, and that limits their use considerably.We discuss the position of register and markedness in wordnets with respect to semantic relations, and we list typical values of register.We illustrate the discussion with the system of registers in plWordNet, the largest Polish wordnet.We present a decision tree for the assignment of marking labels, and examine the consistency of the editing decisions based on that tree.

In the paper, three-level hand-writing recognition using language syntactic properties on the upper level is presented. Isolated characters are recognized on the lowest level. The character classification from the lowest level is used in words recognition. Words are recognized using a combined classifier based on possibly incomplete unigram lexicon. Word classifier builds a rank of the most likely words. Ranks created for subsequent words are input to the syntactic classifier, which recognizes the whole sentences. Here the local syntactic constraints are used to build a syntactically consistent sentence. The method has been applied to recognition of hand-written medical texts describing fixed aspects of patient treatment. Due to narrow area of topics explained in the texts and peculiarity of style characteristic for physicians writing texts, the syntax of expected sentences is relatively simple, what makes the problem of checking the syntactic consistency simpler.

Our objective is to provide a flexible, scalable, distributed architecture that assures a high performance for information extraction (IE) systems working in Internet. The architecture is based on both the general paradigm of the service-oriented architecture, client-server approach and strong separation of concerns between storage and processing components. An experimental IE system, named Semanta, utilising the proposed architecture is also presented. In the following document, we describe five main Semanta services, which are Web user interface (WebUI), Web crawler service (WCS), parsing service (PS), IE service and manager

Our paper presents a modular architecture for a natural dialogue system. The architecture is applied in the construction of Logo - a dialogue system for Polish, based on the Discourse Representation theory, implementing some aspects of the pragmatic analysis and enabling communication with an agent acting in the virtual reality of a blocks world. Logo deals also with the selected issues of coreference resolution. The proposed architecture is intended to be flexible and open for utilisation of diverged language resources.