no code implementations • LREC 2022 • Baiba Saulite, Roberts Darģis, Normunds Gruzitis, Ilze Auzina, Kristīne Levāne-Petrova, Lauma Pretkalniņa, Laura Rituma, Peteris Paikens, Arturs Znotins, Laine Strankale, Kristīne Pokratniece, Ilmārs Poikāns, Guntis Barzdins, Inguna Skadiņa, Anda Baklāne, Valdis Saulespurēns, Jānis Ziediņš
LNCC is a diverse collection of Latvian language corpora representing both written and spoken language and is useful for both linguistic research and language modelling.
Cultural Vocal Bursts Intensity Prediction Language Modelling
no code implementations • EACL 2021 • Didzis Go{\v{s}}ko, Arturs Znotins, Inguna Skadina, Normunds Gruzitis, Gunta Ne{\v{s}}pore-B{\=e}rzkalne
Today, most dialogue systems are fully or partly built using neural network architectures.
no code implementations • CL 2020 • Aarne Ranta, Krasimir Angelov, Normunds Gruzitis, Prasanth Kolachina
Abstract syntax is an interlingual representation used in compilers.
no code implementations • LREC 2020 • Normunds Gruzitis, Roberts Dar{\c{g}}is, Laura Rituma, Gunta Ne{\v{s}}pore-B{\=e}rzkalne, Baiba Saulite
We propose an approach for generating an accurate and consistent PropBank-annotated corpus, given a FrameNet-annotated corpus which has an underlying dependency annotation layer, namely, a parallel Universal Dependencies (UD) treebank.
no code implementations • LREC 2020 • Roberts Dar{\c{g}}is, Peteris Paikens, Normunds Gruzitis, Ilze Auzina, Agate Akmane
Recent advances in neural speech synthesis have eText to speech (TTS) systems are necessary for any language to ensure accessibility and availability of digital language services.
no code implementations • SEMEVAL 2017 • Normunds Gruzitis, Didzis Gosko, Guntis Barzdins
By addressing both text-to-AMR parsing and AMR-to-text generation, SemEval-2017 Task 9 established AMR as a powerful semantic interlingua.
no code implementations • 6 Jul 2016 • John J. Camilleri, Normunds Gruzitis, Gerardo Schneider
Normative texts are documents based on the deontic notions of obligation, permission, and prohibition.
no code implementations • 20 Jun 2016 • Normunds Gruzitis, Guntis Barzdins
In the era of Big Data and Deep Learning, there is a common view that machine learning approaches are the only way to cope with the robust and scalable information extraction and summarization.
no code implementations • LREC 2016 • Andrejs Spektors, Ilze Auzina, Roberts Dargis, Normunds Gruzitis, Peteris Paikens, Lauma Pretkalnina, Laura Rituma, Baiba Saulite
We describe an extensive and versatile lexical resource for Latvian, an under-resourced Indo-European language, which we call Tezaurs (Latvian for {`}thesaurus{'}).
no code implementations • 20 Nov 2015 • Normunds Gruzitis, Guntis Barzdins
We show that micro-ontologies and multi-word units allow integration of the rich and polysemous multi-domain background knowledge into CNL thus providing interpretation for the content words.
no code implementations • 12 Nov 2015 • Normunds Gruzitis, Dana Dannélls
Berkeley FrameNet is a lexico-semantic resource for English based on the theory of frame semantics.
no code implementations • 26 Jun 2014 • Normunds Gruzitis, Peteris Paikens, Guntis Barzdins
In this paper we are focusing on verbs, investigating the possibility of creating a multilingual FrameNet-based GF library.
no code implementations • LREC 2014 • Dana Dann{\'e}lls, Normunds Gruzitis
We present the creation of an English-Swedish FrameNet-based grammar in Grammatical Framework.