Search Results for author: Guntis Barzdins

Found 17 papers, 4 papers with code

RIGA at SemEval-2022 Task 1: Scaling Recurrent Neural Networks for CODWOE Dictionary Modeling

no code implementations SemEval (NAACL) 2022 Eduards Mukans, Gus Strazds, Guntis Barzdins

Described are our two entries “emukans” and “guntis” for the definition modeling track of CODWOE SemEval-2022 Task 1.

Discrete Denoising Diffusion Approach to Integer Factorization

1 code implementation11 Sep 2023 Karlis Freivalds, Emils Ozolins, Guntis Barzdins

Integer factorization is a famous computational problem unknown whether being solvable in the polynomial time.

Denoising

Differentiable Disentanglement Filter: an Application Agnostic Core Concept Discovery Probe

no code implementations17 Jul 2019 Guntis Barzdins, Eduards Sidorovics

It has long been speculated that deep neural networks function by discovering a hierarchical set of domain-specific core concepts or patterns, which are further combined to recognize even more elaborate concepts for the classification or other machine learning tasks.

Disentanglement Visual Grounding +1

Multilingual Clustering of Streaming News

2 code implementations EMNLP 2018 Sebastião Miranda, Artūrs Znotiņš, Shay B. Cohen, Guntis Barzdins

Clustering news across languages enables efficient media monitoring by aggregating articles from multilingual sources into coherent stories.

Clustering

Integrating Multiple NLP Technologies into an Open-source Platform for Multilingual Media Monitoring

no code implementations WS 2018 Ulrich Germann, Ren{\=a}rs Liepins, Didzis Gosko, Guntis Barzdins

The open-source SUMMA Platform is a highly scalable distributed architecture for monitoring a large number of media broadcasts in parallel, with a lag behind actual broadcast time of at most a few minutes.

Automatic Speech Recognition (ASR) Machine Translation

The SUMMA Platform: A Scalable Infrastructure for Multi-lingual Multi-media Monitoring

no code implementations ACL 2018 Ulrich Germann, Ren{\=a}rs Liepins, Guntis Barzdins, Didzis Gosko, Mir, Sebasti{\~a}o a, David Nogueira

The open-source SUMMA Platform is a highly scalable distributed architecture for monitoring a large number of media broadcasts in parallel, with a lag behind actual broadcast time of at most a few minutes.

Clustering Document Summarization +2

The Role of CNL and AMR in Scalable Abstractive Summarization for Multilingual Media Monitoring

no code implementations20 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.

Abstractive Text Summarization Position +1

RIGA at SemEval-2016 Task 8: Impact of Smatch Extensions and Character-Level Neural Translation on AMR Parsing Accuracy

2 code implementations SEMEVAL 2016 Guntis Barzdins, Didzis Gosko

The first extension com-bines the smatch scoring script with the C6. 0 rule-based classifier to produce a human-readable report on the error patterns frequency observed in the scored AMR graphs.

AMR Parsing Sentence +2

Polysemy in Controlled Natural Language Texts

no code implementations20 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.

Word Sense Disambiguation

FrameNet Resource Grammar Library for GF

no code implementations26 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.

FrameNet CNL: a Knowledge Representation and Information Extraction Language

no code implementations10 Jun 2014 Guntis Barzdins

The paper presents a FrameNet-based information extraction and knowledge representation framework, called FrameNet-CNL.

Cannot find the paper you are looking for? You can Submit a new open access paper.