@article{Bubenzer2014, author = {Bubenzer, Johannes}, title = {Cycle-aware minimization of acyclic deterministic finite-state automata}, series = {Discrete applied mathematics}, volume = {163}, journal = {Discrete applied mathematics}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0166-218X}, doi = {10.1016/j.dam.2013.08.003}, pages = {238 -- +}, year = {2014}, abstract = {In this paper a linear-time algorithm for the minimization of acyclic deterministic finite-state automata is presented. The algorithm runs significantly faster than previous algorithms for the same task. This is shown by a comparison of the running times of both algorithms. Additionally, a variation of the new algorithm is presented which handles cyclic automata as input. The new cycle-aware algorithm minimizes acyclic automata in the desired way. In case of cyclic input, the algorithm minimizes all acyclic suffixes of the input automaton.}, language = {en} } @article{HeisterWuerznerBubenzeretal.2011, author = {Heister, Julian and W{\"u}rzner, Kay-Michael and Bubenzer, Johannes and Pohl, Edmund and Hanneforth, Thomas and Geyken, Alexander and Kliegl, Reinhold}, title = {dlexDB - A lexical database for the psychological and linguistic research}, series = {Psychologische Rundschau : offizielles Organ der Deutschen Gesellschaft f{\"u}r Psychologie}, volume = {62}, journal = {Psychologische Rundschau : offizielles Organ der Deutschen Gesellschaft f{\"u}r Psychologie}, number = {1}, publisher = {Hogrefe}, address = {G{\"o}ttingen}, issn = {0033-3042}, doi = {10.1026/0033-3042/a000029}, pages = {10 -- 20}, year = {2011}, abstract = {The lexical database dlexDB supplies in form of an online database frequency-based norms of numerous process-related word properties for psychological and linguistic research. These values include well known variables such as printed frequency of word form and lemma as documented also in CELEX (Baayen, Piepenbrock und Gulikers, 1995). In addition, we compute new values like frequencies based on syllables, and morphemes as well as frequencies of character chains, and multiple word combinations. The statistics are based on the Kernkorpus des Digitalen Wrterbuchs der deutschen Sprache (DWDS) with over 100 million running words. We illustrate the validity of these norms with new results about fixation durations in sentence reading.}, language = {de} } @article{HeisterWuerznerBubenzeretal.2011, author = {Heister, Julian and W{\"u}rzner, Kay-Michael and Bubenzer, Johannes and Pohl, Edmund and Hanneforth, Thomas and Geyken, Alexander and Kliegl, Reinhold}, title = {dlexDB : eine lexikalische Datenbank f{\"u}r die psychologische und linguistische Forschung}, doi = {10.1026/0033-3042/a000029}, year = {2011}, abstract = {Mit der lexikalischen Datenbank dlexDB stellen wir der psychologischen und linguistischen Forschung im World Wide Web online statistische Kennwerte f{\"u}r eine Vielzahl von verarbeitungsrelevanten Merkmalen von W{\"o}rtern zur Verf{\"u}gung. Diese Kennwerte umfassen die durch CELEX (Baayen, Piepenbrock und Gulikers, 1995) bekannten Variablen der H{\"a}ufigkeiten von Wortformen und Lemmata in Texten geschriebener Sprache. Dar{\"u}ber hinaus berechnen wir eine Reihe neuer Kennwerte wie die H{\"a}ufigkeiten von Silben, Morphemen, Zeichenfolgen und Mehrwortverbindungen sowie Wort{\"a}hnlichkeitsmaße. Die Datengrundlage bildet das Kernkorpus des Digitalen W{\"o}rterbuchs der deutschen Sprache (DWDS) mit {\"u}ber 100 Millionen laufenden W{\"o}rtern. Wir illustrieren die Validit{\"a}t dieser Kennwerte mit neuen Ergebnissen zu ihrem Einfluss auf Fixationsdauern beim Lesen von S{\"a}tzen.}, language = {de} }