@misc{MaierKuhnBeisegeletal., author = {Maier, Isidor Konrad and Kuhn, Johannes and Beisegel, Jesse and Huber-Liebl, Markus and Wolff, Matthias}, title = {Minimalist Grammar: Construction without Overgeneration}, series = {arXiv}, journal = {arXiv}, doi = {10.48550/arXiv.2311.01820}, pages = {51}, abstract = {In this paper we give instructions on how to write a minimalist grammar (MG). In order to present the instructions as an algorithm, we use a variant of context free grammars (CFG) as an input format. We can exclude overgeneration, if the CFG has no recursion, i.e. no non-terminal can (indirectly) derive to a right-hand side containing itself. The constructed MGs utilize licensors/-ees as a special way of exception handling. A CFG format for a derivation A_eats_B↦∗peter_eats_apples, where A and B generate noun phrases, normally leads to overgeneration, e.\,g., i_eats_apples. In order to avoid overgeneration, a CFG would need many non-terminal symbols and rules, that mainly produce the same word, just to handle exceptions. In our MGs however, we can summarize CFG rules that produce the same word in one item and handle exceptions by a proper distribution of licensees/-ors. The difficulty with this technique is that in most generations the majority of licensees/-ors is not needed, but still has to be triggered somehow. We solve this problem with ϵ-items called \emph{adapters}.}, language = {en} } @misc{KuhnWolffBorislavov, author = {Kuhn, Johannes and Wolff, Matthias and Borislavov, Borislav}, title = {Epsilon-Verarbeitung bei Minimalistischen Grammatiken f{\"u}r Zahlen}, series = {Elektronische Sprachsignalverarbeitung, Tagungsband der 35. Konferenz, 06.-08.03.2024, Regensburg}, journal = {Elektronische Sprachsignalverarbeitung, Tagungsband der 35. Konferenz, 06.-08.03.2024, Regensburg}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, issn = {0940-6832}, pages = {78 -- 85}, abstract = {Um bei Minimalistischen Grammatiken (MG) {\"U}bergenerierung zu vermeiden, kann man Eintr{\"a}ge mit leeren Exponenten (ε-Eintr{\"a}ge) verwenden. Ein Eintrag besteht aus einem Exponenten, der die {\"A}ußerung oder Schrift eines Wortes repr{\"a}sentiert, einer Merkmalsliste, welche die Syntax kodiert und einem λ-Ausdruck, der die Semantik repr{\"a}sentiert. Leere Eintr{\"a}ge f{\"u}hren allerdings zu einer schlechteren Verwendbarkeit der Grammatik f{\"u}r das Parsen. Die vorliegende Arbeit wird ein Umformungsalgorithmus f{\"u}r MGs vorstellen, sodass die Anzahl der ε-Eintr{\"a}ge verringert werden kann, um sie wieder f{\"u}r Parser verwendbar zu machen. Hierzu werden die ε-Eintr{\"a}ge mit den anderen Eintr{\"a}gen vorverarbeitet und dadurch neue Eintr{\"a}ge geschaffen. Die nun {\"u}berfl{\"u}ssigen ε-Eintr{\"a}ge k{\"o}nnen dann problemlos entfernt werden. Der Algorithmus wurde anhand von {\"u}ber 260 Zahlwortgrammatiken getestet.}, language = {de} } @misc{KuhnWolffMaier, author = {Kuhn, Johannes and Wolff, Matthias and Maier, Isidor Konrad}, title = {Wortgenerator f{\"u}r Minimalistische Grammatiken}, series = {Elektronische Sprachsignalverarbeitung, Tagungsband der 36. Konferenz, 05.-07.03.2025, Halle/Saale}, journal = {Elektronische Sprachsignalverarbeitung, Tagungsband der 36. Konferenz, 05.-07.03.2025, Halle/Saale}, editor = {Grawunder, Sven}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-803-9}, issn = {0940-6832}, pages = {27 -- 34}, abstract = {Um eine bidirektionale Verarbeitung von Sprache zu realisieren, ist es von Vorteil den gleichen Sprachformalismus f{\"u}r das Parsen und die Generierung zu verwenden. F{\"u}r Minimalistische Grammatiken gibt es eine ausgepr{\"a}gte Literatur zu Parsern, aber noch keine Ver{\"o}ffentlichung zu Generatoren. Diese Arbeit stellt einen ersten Generator vor, der mittels Minimalistischer Grammatiken und λ-Ausdr{\"u}cken, S{\"a}tze erzeugt. Der hier vorgestellte Generator kann entgegen manchen anderen Generatoren, von anderen Grammatikformalismen, mit ε-Regeln arbeiten.}, language = {de} } @misc{MaierKuhnDuckhornetal., author = {Maier, Isidor Konrad and Kuhn, Johannes Ferdinand Joachim and Duckhorn, Frank and Kraljevski, Ivan and Sobe, Daniel and Wolff, Matthias and Tsch{\"o}pe, Constanze}, title = {Word Class Based Language Modeling: A Case of Upper Sorbian}, series = {Proceedings of The Workshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced Languages in Eurasia within the 13th Language Resources and Evaluation Conference, Marseille, France}, journal = {Proceedings of The Workshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced Languages in Eurasia within the 13th Language Resources and Evaluation Conference, Marseille, France}, publisher = {European Language Resources Association}, isbn = {978-2-493814-07-4}, pages = {28 -- 35}, abstract = {In this paper we show how word class based language modeling can support the integration of a small language in modern applications of speech technology. The methods described in this paper can be applied for any language. We demonstrate the methods on Upper Sorbian. The word classes model the semantic expressions of numerals, date and time of day. The implementation of the created grammars was realized in the form of finite-state-transducers (FSTs) and minimalists grammars (MGs). We practically demonstrate the usage of the FSTs in a simple smart-home speech application, that is able to set wake-up alarms and appointments expressed in a variety of spontaneous and natural sentences. While the created MGs are not integrated in an application for practical use yet, they provide evidence that MGs could potentially work more efficient than FSTs in built-on applications. In particular, MGs can work with a significantly smaller lexicon size, since their more complex structure lets them generate more expressions with less items, while still avoiding wrong expressions.}, language = {en} } @misc{MaierKuhnDuckhornetal., author = {Maier, Isidor Konrad and Kuhn, Johannes and Duckhorn, Frank and Kraljevski, Ivan and Sobe, Daniel and Wolff, Matthias and Tsch{\"o}pe, Constanze}, title = {Word Class Based Language Modeling: A Case of Upper Sorbian, LREC 2022, Marseille}, series = {Language Resources and Evaluation Conference 2022 (LREC 2022), Marseille, 2022-06-13}, journal = {Language Resources and Evaluation Conference 2022 (LREC 2022), Marseille, 2022-06-13}, doi = {10.5281/zenodo.7501145}, pages = {1}, language = {en} }