This research explores the effects of various training settings from Polish to English Statistical Machine Translation system for spoken language. Various elements of the TED parallel text corpora for the IWSLT 2013 evaluation campaign were used as the basis for training of language models, and for development, tuning and testing of the translation system. The BLEU, NIST, METEOR and TER metrics...

Winners and Losers among Skilled Migrants: The Case of Post-Accession Polish Migrants to the UK We test if migration leads to increased wages. We take the example of Polish migrants to the United Kingdom and focus on the mobility of well educated Poles. We offer insights into absolute and relative change in wages of the migrants, utilizing the data from the UK and Polish labor force surveys. We...

This paper describes a novel weighted projection method of inducing grammatical dependency structures for Polish. Using a parallel English-Polish corpus, the English side is automatically annotated with a syntactic parser and the resulting annotations are projected to Polish via word alignment links. Projected arcs are weighted according to the certainty of word alignment links used in the proj...

This paper reviews recent stock market developments in Poland and the Czech Republic and provides a case-study of the direction of causality between stock market expansion and economic growth. It finds no evidence that the relative failure of the security market in the Czech Republic affected the country’s economy. It also analyses the composition of Polish private equity offerings and finds th...

We present DEBORA – a dependency-based approach to the problem of extraction of arbitrary relations between named entities from open-domain texts in Polish. The presented method is designed for the purpose of the conducted experiment and is adapted to morpho-syntactic properties of Polish, e.g. free word order, high degree of morphological marking. Our preliminary results show that the method i...

A recently started project on building the Polish WordNet is the background to the presented work. Here, an initial approach to automatic extraction of semantic similarity relation between Polish lexemes is discussed. The approach follows directly the main lines of Latent Semantic Analysis, but it is modified in order to cope with the rich inflection of Polish and the lack of a corpus comparabl...

Building on earlier work of Katětov, Uspenskij proved in [9] that the group of isometries of Urysohn’s universal metric space U, endowed with the product topology, is a universal Polish group (i.e it contains an isomorphic copy of any Polish group). Answering a question of Gao and Kechris, we prove here the following, more precise result: for any Polish group G, there exists a closed subset F o...

We present a prototype system for extracting arbitrary relations between named entities from open-domain texts in Polish based on DEBORA – a dependency-based approach to the problem. The presented method is designed for the purpose of the conducted experiment and is adapted to morpho-syntactic properties of Polish, e.g. free word order, high degree of morphological marking. Our preliminary resu...

The Bonn Open Synthesis System (BOSS) is an open-source software for the unit selection speech synthesis that has been used for the generation of high-quality German and Dutch speech. This article presents ongoing research and development aimed at adapting BOSS to the Polish language. In the first section, the origins and workings of the unit selection method for speech synthesis are explained....

The Polish text corpus was analysed to find information about phoneme statistics. We were especially interested in triphones as they are commonly used in many speech processing applications like HTK speech recogniser. An attempt to create the full list of triphones for Polish language is presented. A vast amount of phonetically transcribed text was analysed to obtain the frequency of triphone o...