We present SuperGLUE benchmark adapted and translated into Slovene using a combination of human and machine translation. We describe the translation process and problems arising due to differences in morphology and grammar. We evaluate the translated datasets in several modes: monolingual, cross-lingual, and multilingual, taking into account differences between machine and human translated training sets. The results show that the monolingual Slovene SloBERTa model is superior to massively multilingual and trilingual BERT models, but these also show a good cross-lingual performance on certain tasks. The performance of Slovene models still lags behind the best English models.

The study of metaphors in media discourse is an increasingly researched topic as media are an important shaper of social reality and metaphors are an indicator of how we think about certain issues through references to other things. We present a neural transfer learning method for detecting metaphorical sentences in Slovene and evaluate its performance on a gold standard corpus of metaphors (classification accuracy of 0.725), as well as on a sample of a domain specific corpus of migrations (precision of 0.40 for extracting domain metaphors and 0.74 if evaluated only on a set of migration related sentences). Based on empirical results and findings of our analysis, we propose a novel metaphor annotation scheme containing linguistic level, conceptual level, and stance information. The new scheme can be used for future metaphor annotations of other socially relevant topics.

We describe the ULFRI system used in the Subtask 1 of SemEval-2022 Task 4 Patronizing and condescending language detection. Our models are based on the RoBERTa model, modified in two ways: (1) by injecting additional knowledge (coreferences, named entities, dependency relations, and sentiment) and (2) by leveraging the task uncertainty by using soft labels, Monte Carlo dropout, and threshold optimization. We find that the injection of additional knowledge is not helpful but the uncertainty management mechanisms lead to small but consistent improvements. Our final system based on these findings achieves F1 = 0.575 in the online evaluation, ranking 19th out of 78 systems.

We present a set of novel neural supervised and unsupervised approaches for determining the readability of documents. In the unsupervised setting, we leverage neural language models, whereas in the supervised setting, three different neural classification architectures are tested. We show that the proposed neural unsupervised approach is robust, transferable across languages, and allows adaptation to a specific readability task and data set. By systematic comparison of several neural architectures on a number of benchmark and new labeled readability data sets in two languages, this study also offers a comprehensive analysis of different neural approaches to readability classification. We expose their strengths and weaknesses, compare their performance to current state-of-the-art classification approaches to readability, which in most cases still rely on extensive feature engineering, and propose possibilities for improvements.

This paper describes Slav-NER: the 3rd Multilingual Named Entity Challenge in Slavic languages. The tasks involve recognizing mentions of named entities in Web documents, normalization of the names, and cross-lingual linking. The Challenge covers six languages and five entity types, and is organized as part of the 8th Balto-Slavic Natural Language Processing Workshop, co-located with the EACL 2021 Conference. Ten teams participated in the competition. Performance for the named entity recognition task reached 90% F-measure, much higher than reported in the first edition of the Challenge. Seven teams covered all six languages, and five teams participated in the cross-lingual entity linking task. Detailed valuation information is available on the shared task web page.

Transformer-based neural networks offer very good classification performance across a wide range of domains, but do not provide explanations of their predictions. While several explanation methods, including SHAP, address the problem of interpreting deep learning models, they are not adapted to operate on state-of-the-art transformer-based neural networks such as BERT. Another shortcoming of these methods is that their visualization of explanations in the form of lists of most relevant words does not take into account the sequential and structurally dependent nature of text. This paper proposes the TransSHAP method that adapts SHAP to transformer models including BERT-based text classifiers. It advances SHAP visualizations by showing explanations in a sequential manner, assessed by human evaluators as competitive to state-of-the-art solutions.

Large pretrained language models using the transformer neural network architecture are becoming a dominant methodology for many natural language processing tasks, such as question answering, text classification, word sense disambiguation, text completion and machine translation. Commonly comprising hundreds of millions of parameters, these models offer state-of-the-art performance, but at the expense of interpretability. The attention mechanism is the main component of transformer networks. We present AttViz, a method for exploration of self-attention in transformer networks, which can help in explanation and debugging of the trained models by showing associations between text tokens in an input sequence. We show that existing deep learning pipelines can be explored with AttViz, which offers novel visualizations of the attention heads and their aggregations. We implemented the proposed methods in an online toolkit and an offline library. Using examples from news analysis, we demonstrate how AttViz can be used to inspect and potentially better understand what a model has learned.

User commenting is a valuable feature of many news outlets, enabling them a contact with readers and enabling readers to express their opinion, provide different viewpoints, and even complementary information. Yet, large volumes of user comments are hard to filter, let alone read and extract relevant information. The research on the summarization of user comments is still in its infancy, and human-created summarization datasets are scarce, especially for less-resourced languages. To address this issue, we propose an unsupervised approach to user comments summarization, which uses a modern multilingual representation of sentences together with standard extractive summarization techniques. Our comparison of different sentence representation approaches coupled with different summarization approaches shows that the most successful combinations are the same in news and comment summarization. The empirical results and presented visualisation show usefulness of the proposed methodology for several languages.

This paper presents tools and data sources collected and released by the EMBEDDIA project, supported by the European Union’s Horizon 2020 research and innovation program. The collected resources were offered to participants of a hackathon organized as part of the EACL Hackashop on News Media Content Analysis and Automated Report Generation in February 2021. The hackathon had six participating teams who addressed different challenges, either from the list of proposed challenges or their own news-industry-related tasks. This paper goes beyond the scope of the hackathon, as it brings together in a coherent and compact form most of the resources developed, collected and released by the EMBEDDIA project. Moreover, it constitutes a handy source for news media industry and researchers in the fields of Natural Language Processing and Social Science.

Human annotations are an important source of information in the development of natural language understanding approaches. As under the pressure of productivity annotators can assign different labels to a given text, the quality of produced annotations frequently varies. This is especially the case if decisions are difficult, with high cognitive load, requires awareness of broader context, or careful consideration of background knowledge. To alleviate the problem, we propose two semi-supervised methods to guide the annotation process: a Bayesian deep learning model and a Bayesian ensemble method. Using a Bayesian deep learning method, we can discover annotations that cannot be trusted and might require reannotation. A recently proposed Bayesian ensemble method helps us to combine the annotators’ labels with predictions of trained models. According to the results obtained from three hate speech detection experiments, the proposed Bayesian methods can improve the annotations and prediction performance of BERT models.

In text processing, deep neural networks mostly use word embeddings as an input. Embeddings have to ensure that relations between words are reflected through distances in a high-dimensional numeric space. To compare the quality of different text embeddings, typically, we use benchmark datasets. We present a collection of such datasets for the word analogy task in nine languages: Croatian, English, Estonian, Finnish, Latvian, Lithuanian, Russian, Slovenian, and Swedish. We designed the monolingual analogy task to be much more culturally independent and also constructed cross-lingual analogy datasets for the involved languages. We present basic statistics of the created datasets and their initial evaluation using fastText embeddings.

Recent results show that deep neural networks using contextual embeddings significantly outperform non-contextual embeddings on a majority of text classification task. We offer precomputed embeddings from popular contextual ELMo model for seven languages: Croatian, Estonian, Finnish, Latvian, Lithuanian, Slovenian, and Swedish. We demonstrate that the quality of embeddings strongly depends on the size of training set and show that existing publicly available ELMo embeddings for listed languages shall be improved. We train new ELMo embeddings on much larger training sets and show their advantage over baseline non-contextual FastText embeddings. In evaluation, we use two benchmarks, the analogy task and the NER task.