No abstract

Abstract-This paper describes the automatic summarization system developed for the Polish language. The system implements sentence-based extractive summarization technique, which consists in determining most important sentences in document due to their computed salience. A structure of the system is presented, as well as the evaluation method and achieved results. The presented attempt is intended to serve as the baseline for future solutions, as it is the first summarization project evaluated against the Polish Summaries Corpus, the standardized corpus of summaries for the Polish language.

Abstract Neural Machine Translation (NMT) has recently achieved promising results for a number of translation pairs. Although the method requires larger volumes of data and more computational power than Statistical Machine Translation (SMT), it is believed to become dominant in near future. In this paper we evaluate SMT and NMT models learned on a domain-specific English-Polish corpus of a moderate size (1,200,000 segments). The experiment shows that both solutions significantly outperform a general-domain online translator. The SMT model achieves a slightly better BLEU score than the NMT model. On the other hand, the process of decoding is noticeably faster in NMT. Human evaluation carried out on a sizeable sample of translations (2,000 pairs) reveals the superiority of the NMT approach, particularly in the aspect of output fluency.

The paper presents a method for the automatic diachronic normalization of Polish texts – the procedure, which, for a given historical text, returns its contemporary spelling. The method applies finite-state transducers, defined in a sublanguage of the Thrax formalism. The paper discusses linguistic issues, such as evolution in spelling of the Polish language, as well as implementation aspects, such as efficiency or testing the proposed method.

The aim of the paper is to apply, for historical texts, the methodology used commonly to solve various NLP tasks defined for contemporary data, i.e. pre-train and fine-tune large Transformer models. This paper introduces an ML challenge, named Challenging America (Chal-lAm), based on OCR-ed excerpts from historical newspapers collected from the Chronicling America portal. ChallAm provides a dataset of clippings, labeled with metadata on their origin, and paired with their textual contents retrieved by an OCR tool. Three, publicly available, ML tasks are defined in the challenge: to determine the article date, to detect the location of the issue, and to deduce a word in a text gap (cloze test). Strong baselines are provided for all three ChallAm tasks. In particular, we pretrained a RoBERTa model from scratch from the historical texts. We also discuss the issues of discrimination and hate-speech present in the historical American texts.