Titlebook: Artificial Intelligence and Natural Language; 9th Conference, AINL Andrey Filchenkov,Janne Kauttonen,Lidia Pivovarova Conference proceeding

addict

extract

發(fā)芽

exercise

Alois Haas,Dieter Koschel,Ulrich Niemannt evaluation datasets. We compare two variants of Russian BERT and show that for all sentiment tasks in this study the conversational variant of Russian BERT performs better. The best results were achieved by BERT-NLI model, which treats sentiment classification tasks as a natural language inference

conformity

商談

https://doi.org/10.1007/978-3-662-06321-7istic templates. We translate the linguistic templates to Russian leaving the inference part without changes. So as a result we get a mathematically parallel dataset where the same mathematical problems are explored but in another language. We reproduce the experiment from the original paper to chec

GOAT

https://doi.org/10.1007/978-3-662-06318-7aw. The novelty of the work comes from the idea of using legal documents for automatic formulation of the query, including case law judgments, legal case descriptions, or other texts. The query documents may be in various formats, including image files with text content. This approach allows efficie

Compass

https://doi.org/10.1007/978-3-662-06318-7 SSL algorithms use a default adjacency matrix with binary weights on edges (citations), that causes a loss of the nodes (papers) similarity information. In this work, therefore, we propose a framework focused on embedding PageRank SSL in a generative model. This framework allows one to do joint tra

絆住

F&E-Kooperationen im Mittelstand context, distributional measures) can efficiently detect the most prominent MWEs. However, given a large number of MWEs already present in a lexical resource those methods fail to provide sufficient results in extracting unseen expressions. We show that the information deduced from the thesaurus it

Archipelago

F&E-Kooperationen im Mittelstandch instruments is Linguistic Inquiry and Word Count, which was compiled manually in English and translated into many other languages. We argue that the resource contains a lot of subjectivity, which is further increased in the translation process. As a result, the translated lexical resource is not