@inProceedings{lange-ljunglof-2020-learning-291243, title = {Learning Domain-specific Grammars from a Small Number of Examples}, abstract = {In this paper we investigate the problem of grammar inference from a different perspective. The common approach is to try to infer a grammar directly from example sentences, which either requires a large training set or suffers from bad accuracy. We instead view it as a problem of grammar restriction or sub-grammar extraction. We start from a large-scale resource grammar and a small number of examples, and find a sub-grammar that still covers all the examples. To do this we formulate the problem as a constraint satisfaction problem, and use an existing constraint solver to find the optimal grammar. We have made experiments with English, Finnish, German, Swedish and Spanish, which show that 10–20 examples are often sufficient to learn an interesting domain grammar. Possible applications include computer-assisted language learning, domain-specific dialogue systems, computer games, Q/A-systems, and others.}, booktitle = {12th International Conference on Agents and Artificial Intelligence - Volume 1: NLPinAI}, author = {Lange, Herbert and Ljunglöf, Peter}, year = {2020}, publisher = {SciTePress}, ISBN = {978-989-758-395-7}, } @misc{alfter-etal-2020-proceedings-300071, title = {Proceedings of the 9th Workshop on Natural Language Processing for Computer Assisted Language Learning 2020}, abstract = {The workshop series on Natural Language Processing (NLP) for Computer-Assisted Language Learning (NLP4CALL) is a meeting place for researchers working on the integration of Natural Language Processing and Speech Technologies in CALL systems and exploring the theoretical and methodological issues arising in this connection. The latter includes, among others, the integration of insights from Second Language Acquisition (SLA) research, and the promotion of “Computational SLA” through setting up Second Language research infrastructures. This collection presents four selected papers describing use of Language Technology for language learning.}, author = {Alfter, David and Volodina, Elena and Pilán, Ildikó and Lange, Herbert and Borin, Lars}, year = {2020}, publisher = {Linköping University Electronic Press}, address = {Linköping}, ISBN = {978-91-7929-732-9}, } @book{lange-2020-learning-295656, title = {Learning Language (with) Grammars: From Teaching Latin to Learning Domain-Specific Grammars}, abstract = {This thesis describes work in three areas: grammar engineering, computer-assisted language learning and grammar learning. These three parts are connected by the concept of a grammar-based language learning application. Two types of grammars are of concern. The first we call resource grammars, extensive descriptions a natural languages. Part I focuses on this kind of grammars. The other are domain-specific or application-specific grammars. These grammars only describe a fragment of natural language that is determined by the domain of a certain application. Domain-specific grammars are relevant for Part II and Part III. Another important distinction is between humans learning a new natural language using computational grammars (Part II) and computers learning grammars from example sentences (Part III). Part I of this thesis focuses on grammar engineering and grammar testing. It describes the development and evaluation of a computational resource grammar for Latin. Latin is known for its rich morphology and free word order, both have to be handled in a computationally efficient way. A special focus is on methods how computational grammars can be evaluated using corpus data. Such an evaluation is presented for the Latin resource grammar. Part II, the central part, describes a computer-assisted language learning application based on domain-specific grammars. The language learning application demonstrates how computational grammars can be used to guide the user input and how language learning exercises can be modeled as grammars. This allows us to put computational grammars in the center of the design of language learning exercises used to help humans learn new languages. Part III, the final part, is dedicated to a method to learn domain- or application-specific grammars based on a wide-coverage grammar and small sets of example sentences. Here a computer is learning a grammar for a fragment of a natural language from example sentences, potentially without any additional human intervention. These learned grammars can be based e.g. on the Latin resource grammar described in Part II and used as domain-specific lesson grammars in the language learning application described Part II.}, author = {Lange, Herbert}, year = {2020}, publisher = {University of Gothenburg}, address = {Gothenburg}, ISBN = {978-91-7833-987-7}, }