Selectively processing noisy utterances while effectively disregarding speech-specific elements poses no considerable challenge for humans, as they exhibit remarkable cognitive abilities to separate semantically significant content from speech-specific noise (i.e. filled pauses, disfluencies, and restarts). These abilities may be driven by mechanisms based on acquired grammatical rules that compose abstract syntactic-semantic structures within utterances. Segments without syntactic and semantic significance are consistently disregarded in these structures. The structures, in tandem with lexis, likely underpin language comprehension and thus facilitate effective communication.In our study, grounded in linguistically motivated experiments, we investigate whether large language models (LLMs) can effectively perform analogical speech comprehension tasks. In particular, we examine the ability of LLMs to extract well-structured utterances from transcriptions of noisy dialogues. We conduct two evaluation experiments in the Polish language scenario, using a dataset presumably unfamiliar to LLMs to mitigate the risk of data contamination. Our results show that not all extracted utterances are correctly structured, indicating that either LLMs do not fully acquire syntactic-semantic rules or they acquire them but cannot apply them effectively. We conclude that the ability of LLMs to comprehend noisy utterances is still relatively superficial compared to human proficiency in processing them.

This paper presents the objectives, organization and activities of the UniDive COST Action, a scientific network dedicated to universality, diversity and idiosyncrasy in language technology. We describe the objectives and organization of this initiative, the people involved, the working groups and the ongoing tasks and activities. This paper is also an pen call for participation towards new members and countries.

With the advancements of transformer-based architectures, we observe the rise of natural language preprocessing (NLPre) tools capable of solving preliminary NLP tasks (e.g. tokenisation, part-of-speech tagging, dependency parsing, or morphological analysis) without any external linguistic guidance. It is arduous to compare novel solutions to well-entrenched preprocessing toolkits, relying on rule-based morphological analysers or dictionaries. Aware of the shortcomings of existing NLPre evaluation approaches, we investigate a novel method of reliable and fair evaluation and performance reporting. Inspired by the GLUE benchmark, the proposed language-centric benchmarking system enables comprehensive ongoing evaluation of multiple NLPre tools, while credibly tracking their performance. The prototype application is configured for Polish and integrated with the thoroughly assembled NLPre-PL benchmark. Based on this benchmark, we conduct an extensive evaluation of a variety of Polish NLPre systems. To facilitate the construction of benchmarking environments for other languages, e.g. NLPre-GA for Irish or NLPre-ZH for Chinese, we ensure full customization of the publicly released source code of the benchmarking system. The links to all the resources (deployed platforms, source code, trained models, datasets etc.) can be found on the project website: https://sites.google.com/view/nlpre-benchmark.

We introduce the COMBO-based approach for EUD parsing and its implementation, which took part in the IWPT 2021 EUD shared task. The goal of this task is to parse raw texts in 17 languages into Enhanced Universal Dependencies (EUD). The proposed approach uses COMBO to predict UD trees and EUD graphs. These structures are then merged into the final EUD graphs. Some EUD edge labels are extended with case information using a single language-independent expansion rule. In the official evaluation, the solution ranked fourth, achieving an average ELAS of 83.79%. The source code is available at https://gitlab.clarin-pl.eu/syntactic-tools/combo.

We introduce COMBO – a fully neural NLP system for accurate part-of-speech tagging, morphological analysis, lemmatisation, and (enhanced) dependency parsing. It predicts categorical morphosyntactic features whilst also exposes their vector representations, extracted from hidden layers. COMBO is an easy to install Python package with automatically downloadable pre-trained models for over 40 languages. It maintains a balance between efficiency and quality. As it is an end-to-end system and its modules are jointly trained, its training is competitively fast. As its models are optimised for accuracy, they achieve often better prediction quality than SOTA. The COMBO library is available at: https://gitlab.clarin-pl.eu/syntactic-tools/combo.

BERT-based models are currently used for solving nearly all Natural Language Processing (NLP) tasks and most often achieve state-of-the-art results. Therefore, the NLP community conducts extensive research on understanding these models, but above all on designing effective and efficient training procedures. Several ablation studies investigating how to train BERT-like models have been carried out, but the vast majority of them concerned only the English language. A training procedure designed for English does not have to be universal and applicable to other especially typologically different languages. Therefore, this paper presents the first ablation study focused on Polish, which, unlike the isolating English language, is a fusional language. We design and thoroughly evaluate a pretraining procedure of transferring knowledge from multilingual to monolingual BERT-based models. In addition to multilingual model initialization, other factors that possibly influence pretraining are also explored, i.e. training objective, corpus size, BPE-Dropout, and pretraining length. Based on the proposed procedure, a Polish BERT-based language model – HerBERT – is trained. This model achieves state-of-the-art results on multiple downstream tasks.

The research presented in this paper aims at enriching the manually morphosyntactically annotated part of National Corpus of Polish (NKJP1M) with a syntactic layer, i.e. dependency trees of sentences, and at converting both dependency trees and morphosyntactic annotations of particular tokens to Universal Dependencies. The dependency layer is built using a semi-automatic annotation procedure. The sentences from NKJP1M are first parsed with a dependency parser trained on Polish Dependency Bank, i.e. the largest bank of Polish dependency trees. The predicted dependency trees and the morphosyntactic annotations of tokens are then automatically converted into UD dependency graphs. NKJP1M sentences are an essential part of Polish Dependency Bank, we thus replace some automatically predicted dependency trees with their manually annotated equivalents. The final dependency treebank consists of 86K trees (including 15K gold-standard trees). A natural language pre-processing model trained on the enlarged set of (possibly noisy) dependency trees outperforms a model trained on a smaller set of the gold-standard trees in predicting part-of-speech tags, morphological features, lemmata, and labelled dependency trees

The purpose of the research is to answer the question whether linguistic information is retained in vector representations of sentences. We introduce a method of analysing the content of sentence embeddings based on universal probing tasks, along with the classification datasets for two contrasting languages. We perform a series of probing and downstream experiments with different types of sentence embeddings, followed by a thorough analysis of the experimental results. Aside from dependency parser-based embeddings, linguistic information is retained best in the recently proposed LASER sentence embeddings.

This paper describes the ICS PAS system which took part in CoNLL 2018 shared task on Multilingual Parsing from Raw Text to Universal Dependencies. The system consists of jointly trained tagger, lemmatizer, and dependency parser which are based on features extracted by a biLSTM network. The system uses both fully connected and dilated convolutional neural architectures. The novelty of our approach is the use of an additional loss function, which reduces the number of cycles in the predicted dependency graphs, and the use of self-training to increase the system performance. The proposed system, i.e. ICS PAS (Warszawa), ranked 3th/4th in the official evaluation obtaining the following overall results: 73.02 (LAS), 60.25 (MLAS) and 64.44 (BLEX).

The paper presents the largest Polish Dependency Bank in Universal Dependencies format – PDBUD – with 22K trees and 352K tokens. PDBUD builds on its previous version, i.e. the Polish UD treebank (PL-SZ), and contains all 8K PL-SZ trees. The PL-SZ trees are checked and possibly corrected in the current edition of PDBUD. Further 14K trees are automatically converted from a new version of Polish Dependency Bank. The PDBUD trees are expanded with the enhanced edges encoding the shared dependents and the shared governors of the coordinated conjuncts and with the semantic roles of some dependents. The conducted evaluation experiments show that PDBUD is large enough for training a high-quality graph-based dependency parser for Polish.

The paper presents a procedure of building an evaluation dataset. for the validation of compositional distributional semantics models estimated for languages other than English. The procedure generally builds on steps designed to assemble the SICK corpus, which contains pairs of English sentences annotated for semantic relatedness and entailment, because we aim at building a comparable dataset. However, the implementation of particular building steps significantly differs from the original SICK design assumptions, which is caused by both lack of necessary extraneous resources for an investigated language and the need for language-specific transformation rules. The designed procedure is verified on Polish, a fusional language with a relatively free word order, and contributes to building a Polish evaluation dataset. The resource consists of 10K sentence pairs which are human-annotated for semantic relatedness and entailment. The dataset may be used for the evaluation of compositional distributional semantics models of Polish.

This paper presents an approach of automatic annotation of sentences with dependency structures. The approach builds on the idea of cross-lingual dependency projection. The presented method of acquiring dependency trees involves a weighting factor in the processes of projecting source dependency relations to target sentences and inducing well-formed target dependency trees from sets of projected dependency relations. Using a parallel corpus, source trees are transferred onto equivalent target sentences via an extended set of alignment links. Projected arcs are initially weighted according to the certainty of word alignment links. Then, arc weights are recalculated using a method based on the EM selection algorithm. Maximum spanning trees selected from EM-scored digraphs and labelled with appropriate grammatical functions constitute a target dependency treebank. Extrinsic evaluation shows that parsers trained on such a treebank may perform comparably to parsers trained on a manually developed treebank.