期刊名称：Knjižnica : Revija za Področje Bibliotekarstva in Informacijske Znanosti
印刷版ISSN：0023-2424
电子版ISSN：1581-7903
出版年度：2002
卷号：46
期号：1-2
页码：111-136
出版社：Zveza Bibliotekarskih Društev Slovenije, Narodna in Univerzitetna Knjižnica
摘要：Prispevek predstavlja pripravo algoritma za krnjenje slovenskih besedil s področja bibliotekarstva, ki je potekal v treh fazah: učni, testni in evalvacijski. Predstavljena je priprava oz. učenje Optimalnega algoritma za krnjenje bibliotekarskih besedil, njegovo testiranje in primerjava z dvema drugima algoritmoma za krnjenje, imenovanima Popovičev in Generični. Za učenje je bil uporabljen korpus 790.000 besed s področja bibliotekarstva.Zgrajeni so bili seznami krnov, besednih končnic ter blokiranih besed. Testna faza je obsegala testiranje algoritma, predvsem zgrajenih sestavnih delov, z dodatnim korpusom,obsegajočim 167.000 besed. V evalvacijski fazi je bila izvedena primerjava delovanja omenjenih treh algoritmov na istem korpusu. Rezultati delovanja algoritmov so primerjani z intelektualno pripravljenim kontrolnim rezultatom. V njem so množice semantično povezanih besed, zastopane s krni. Spremljano je premalo natačno krnjenje – koliko krnov za semantično povezane besede izdela posamezen algoritem. Rezultati so statistično obdelani s Kruskal-Wallisovim testom. Optimalni algoritem daje najboljše rezultate. Največkrat doseže popolno ujemanje s kontrolnim rezultatom in hkrati izdela najmanj krnov za en pomen. Sledi Popovičev z majhnim odstopanjem. Najmanj natančen je Generični. Opisani postopki lahko predstavljajo izhodišče za nadaljnjo gradnjo orodij za avtomatsko indeksiranje dokumentov s področja bibliotekarstva in poizvedovanje po njih.
其他摘要：The theme of the article is the preparation of a stemming algorithm for Slovenian library science texts. The procedure consisted of three phases: learning, testing and evaluation.The preparation of the optimal stemmer for Slovenian texts from the field of library science is presented, its testing and comparison with two other stemmers for the Slovenian language: the Popovič stemmer and the Generic stemmer. A corpus of 790.000 words from the field of library science was used for learning. Lists of stems, word endings and stop-words were built. In the testing phase, the component parts of the algorithm were tested on an additional corpus of 167.000 words. In the evaluation phase, a comparison of the three stemmers processing the same word corpus was made. The results of each stemmer were compared with an intellectually prepared control result of the stemming of the corpus. It consisted of groups of semantically connected words with no errors. Understemming was especially monitored – the number of stems for semantically connected words, produced by an algorithm. The results were statistically processed with the Kruskal-Wallis test. The Optimal stemmer produced the best results.It matched best with the reference results and also gave the smallest number of stems for one semantic meaning. The Popovič stemmer followed closely. The Generic stemmer proved to be the least accurate. The procedures described in the thesis can represent a platform for the development of the tools for automatic indexing and retrieval for library science texts in Slovenian language.
关键词：avtomatsko krnjenje; algoritmi; slovenski jezik; bibliotekarstvo
其他关键词：stemming; stemming algorithms; Slovenian language; library and information science
