Browsing by Author "Krynicki, Grzegorz"
Now showing 1 - 5 of 5
Results Per Page
Sort Options
Item Articulatory grounding of phonemic distinctions in English by means of electropalatography(2014) Krynicki, GrzegorzThe aim of the experiment described in this paper was to devise and test a procedure that would allow identification of a phoneme on the basis of only tongue-to-palate and labial contacts that accompanied its realization in continuous read speech. The hypothesis underlying this study was that the articulatory correlates of the phonemic distinctive features can be induced statistically from dimensionality-reduced electropalatographic data.Item Automatic English phoneme recognition from articulatory data generated by EPG systems with grid and anatomical layout of contact sensors(Australasian Speech Science and Technology Association Inc., 2019-08-22) Krynicki, Grzegorz; Dziubalska-Kołaczyk, Katarzyna; Weckwerth, Jarosław; Michalski, Grzegorz; Kaźmierski, Kamil; Maciejewska, Barbara; Wiskirska-Woźnica, Bożena; Żygis, Marzena; Kuczko, Wiesław; Sekuła, AlicjaThe aim of the study was to conduct automatic phoneme identification from articulatory data that accompanied the production of these phonemes in continuous speech. The articulatory data were obtained from 2 electropalatographic systems, Palatometer by Complete Speech and Linguagraph by Rose-Medical. Palatometer was used with the artificial palate containing 124 contact sensors in a grid layout, including 2 sensors monitoring the lip contact. The palate included a vacuum-thermoformed flexible printed circuit. Linguagraph was used with the acrylic artificial palate designed and developed for the purpose of this study, containing 62 electrodes in anatomical layout. Palatometer was used by one native of General American and Linguagraph by one native of General British, each reading 140 phonetically balanced sentences that included Harvard Sentences and TIMIT prompts. The EPG data were parametrised into dimensionality reduction indexes, which were analysed by means of linear discriminant analysis and a probabilistic neural network. The results of classifications are discussed.Item Corpus-based Online Word Formation Exercises for Advanced Learners of English – Challenges and Solutions(RAM-Verlag, 2013) Krynicki, GrzegorzThe paper presents the design and operation of an online platform for word formation practice. The system is based on a pre-defined list of pairs of base and derived forms and usage examples drawn automatically from the British National Corpus. A procedure for the extraction of example sentences is outlined. Results of 372 users’ interacting with the system for over 4.5 month are reviewed. The question about what factors influence users’ evaluation of specific exercises as more difficult is addressed. The results may be relevant in the area of language testing, preparation of examination materials, student-teacher online interaction and teaching English word formation.Item Performance of four sentence aligners on English Polish bitexts(Polish Phonetic Association, 2012) Krynicki, GrzegorzCollections of mutual translations gain in their value if aligned at the sentence level. As such they can be used e.g. in Statistical Machine Translation, Translation Studies and Lexicography. In this study, four leading systems of automatic sentence alignment are tested on four English-Polish translationally equivalent documents. Their performance is evaluated in terms of precision, recall and F-measure as well as in terms of their coverage of the source and target text. Some of the advantages and disadvantages of these methods with respect to different applications are discussed.Item Phrasal equivalents with alternative elements in bilingual dictionaries: presentation problems(Wydawnictwo Naukowe Szczecińskiej Szkoły Wyższej „Collegium Balticum", 2012) Szczepaniak, Renata; Krynicki, GrzegorzOne of the difficulties that inexperienced dictionary users face is the cryptic character of dictionary text, which is full of codes, abbreviations and symbols, the significance of which has to be mastered before the microstructure can be accessed. Such devices generally serve the purpose of space conservation in paper dictionaries, and can be termed collectively, after Wiegand (1996), “methods of textual condensation”. As Prinsloo and De Schryver (2002: 72) observe, “[i]ncreased text density, which should obviously stand in relation to the decoding skills of the target user, can – especially in paper dictionaries – be a virtue as long as that user can unambiguously retrieve the information.” Unambiguous retrieval of information is possible provided that principles of textual condensation are explained in the metatext of the dictionary or they are sufficiently intuitive. Unfortunately, this is not always the case, and, as a side-effect of the pursuit of economy of space, the convenience of dictionary users can be compromised. This study focuses on the use of space-saving devices indicating alternative elements of phrasal equivalents in two major bilingual dictionaries for Polish learners of English: PWN-Oxford Dictionary and Kosciuszko Foundation Dictionary. Firstly, it looks at the function of the aforementioned devices as defined in the dictionaries. Secondly, it attempts to highlight inconsistencies in their use and potential problems with their interpretation. From each side of both dictionaries, a random sample of 500 pairs of phrasal equivalents containing at least one alternation was extracted. Next, each phrase was manually annotated with respect to the difficulty of decoding as well as gravity of potential interpretation errors. The qualitative analysis of the results of annotation led to the identification and classification of potential problems with the interpretation of space-saving devices.