Search Results for author:
Found 15 papers, 1 papers with code
Latvian National Corpora Collection – Korpuss.lv
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
Domain Expert Platform for Goal-Oriented Dialog Collection
Today, most dialogue systems are fully or partly built using neural network architectures.
Abstract Syntax as Interlingua: Scaling Up the Grammatical Framework from Controlled Languages to Robust Pipelines
Abstract syntax is an interlingual representation used in compilers.
Deriving a PropBank Corpus from Parallel FrameNet and UD Corpora
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.
Development and Evaluation of Speech Synthesis Corpora for Latvian
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.
RIGOTRIO at SemEval-2017 Task 9: Combining Machine Learning and Grammar Engineering for AMR Parsing and Generation
By addressing both text-to-AMR parsing and AMR-to-text generation, SemEval-2017 Task 9 established AMR as a powerful semantic interlingua.
Extracting Formal Models from Normative Texts
Normative texts are documents based on the deontic notions of obligation, permission, and prohibition.
The Role of CNL and AMR in Scalable Abstractive Summarization for Multilingual Media Monitoring
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.
T\=ezaurs.lv: the Largest Open Lexical Database for Latvian
We describe an extensive and versatile lexical resource for Latvian, an under-resourced Indo-European language, which we call Tezaurs (Latvian for {`}thesaurus{'}).
Polysemy in Controlled Natural Language Texts
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.
A Multilingual FrameNet-based Grammar and Lexicon for Controlled Natural Language
Berkeley FrameNet is a lexico-semantic resource for English based on the theory of frame semantics.
FrameNet Resource Grammar Library for GF
In this paper we are focusing on verbs, investigating the possibility of creating a multilingual FrameNet-based GF library.
Extracting a bilingual semantic grammar from FrameNet-annotated corpora
We present the creation of an English-Swedish FrameNet-based grammar in Grammatical Framework.
