Adam Pawłowski

Cultural Heritage in CLEF CHiC 2013

The Cultural Heritage in CLEF 2013 lab comprised three tasks: multilingual ad-hoc retrieval and semantic enrichment in 13 languages Dutch, English, German, Greek, Finnish, French, Hungarian, Italian, Norwegian, Polish, Slovenian, Spanish, and Swedish, Polish ad-hoc retrieval and the interactive task, which studied user behavior via log analysis and questionnaires. For the multilingual and Polish sub-tasks, more than 170,000 documents were assessed for relevance on a tertiary scale. The multilingual task had 7 participants submitting 30 multilingual and 41 monolingual runs. The Polish task comprised 3 participating groups submitting manual and automatic runs. The interactive task had 4 participating research groups and 208 user participants in the study. For the multilingual task, results show that more participants are necessary in order to provide comparative analyses. The interactive task created a rich data set comprising of questionnaire of log data. Further analysis of the data is planned in the future.

Language in the Line vs. Language in the Mass: On the Efficiency of Sequential Modelling in the Analysis of Rhythm

The subject of the present article is the application of the ARIMA method of time-series analysis and of conventional statistical tests to the study of rhythm in text. The results obtained on the same set of samples with both investigative approaches are then compared. Sequential modelling by means of the ARIMA method turns out to be much more efficient than “mass” statistics.

Quantity or Stress? Sequential Analysis of Latin Prosody

Degrees of linear orderedness of Latin hexameter samples, coded respectively as sequences of long vs. short and stressed vs. unstressed syllables, were compared using the ARIMA method. Formal stochastic process models describing the sequential (metrical and/or rhythmical) text structure were identified and subsequently interpreted in linguistic terms. The average percentage of the original variance explained by the models turned out to be much higher for the stress series than for the series based on quantity coding. Contrary to received opinion, the underlying basis of Latin rhythm was not quantity but dynamic stress placed on the strong parts of consecutive metrical feet.

The Quantitative Approach in Cultural Anthropology: Application of Linguistic Corpora in the Analysis of Basic Colour Terms

Frequencies of colour terms are analysed in ten Indo-European languages (Czech, English, French, Italian, Polish, Russian, Rumanian, Slovak, Spanish and Ukrainian) on the basis of frequency dictionaries. The research reveals that cross-linguistic distributions of colour terms in these languages are similar, but more sensitive statistical tests (chi -square) show that they cannot be regarded as statistically independent. The quantitative structure of colour terms is then compared with the chronological-evolutionary scheme proposed by Berlin and Kay in 1969. The study proves that quantitative data based on lexical resources, including frequency dictionaries, are a useful and promising tool of research in the anthropology of culture.

Time‐Series analysis in linguistics: Application of the ARIMA method to cases of spoken Polish

Abstract In this paper the ARIMA method of time‐series analysis is applied to textual data. Four prosodic types of Polish are discussed (childrens verse, complex verse, rhetorical discourse and literary prose). The analysis proves that each of these prosodic types conveys rhythmical components. We have also defined and compared formal models of the sequential structure of text for the treated samples.

Evaluation of IR Strategies for Polish

The paper presents results and conclusions of an ad hoc evaluation lab concerning information retrieval for Polish. A corpus of ca. million document descriptions of Polish Europeana resources was indexed and matched against a set of fifty test queries. Different pre-processing procedures as well as different indexing and term weighting approaches were used and evaluated. Efficiency of different IR models was compared. Finally human-based relevance assessment was provided for retrieved documents.

Ewaluacja skuteczności systemów wyszukiwania informacji. Od eksperymentu Cranfield do laboratoriów TREC i CLEF. Geneza i metody

We present the genesis and evolution of methods and measures of IR systems evaluation. The design of the Cranfield experiment, a long-term model for evaluation methodology, is described. Evolution of current methodology of IR systems evaluation, developed at the annual TREC (Text REtrieval Conference) is provided, and the most popular and current measures described. The article presents also design of the CLEF (Conference and Labs of the Evaluation Forum) evaluation labs with special attention paid to CHiC (Cultural Heritage in CLEF). We describe the design of Polish Task in CHiClab and discuss conclusions from lab realisation.

Ewaluacja skuteczności systemów wyszukiwania informacji. Wyniki eksperymentu Polish Task realizowanego w ramach Conference and Labs of the Evaluation Forum (CLEF) 2012

W niniejszym artykule prezentujemy realizacje laboratorium ewaluacyjnego CLEF (Conference and Labs of the Evaluation Forum) ze specjalnym uwzglednieniem kampanii CHiC (Cultural Heritage in CLEF). Opisujemy realizacje oraz wyniki zadania Polish Task in ChiC. W artykule zaprezentowano wnioski z realzacji zadania. Zostaly omowione wyniki uzyskane przez uczestnikow zadania przy uzyciu roznych strategii indeksowania oraz wyszukiwania zasobow. Porownaliśmy efektywnośc metod tf-idf, OKAPI, DFR oraz data fusion.