Search Results for author: Tomáš Brychcín

Found 4 papers, 1 papers with code

Linear Transformations for Cross-lingual Semantic Textual Similarity

no code implementations11 Jul 2018 Tomáš Brychcín

Cross-lingual semantic textual similarity systems estimate the degree of the meaning similarity between two sentences, each in a different language.

Cross-Lingual Semantic Textual Similarity Machine Translation +3

Cross-lingual Word Analogies using Linear Transformations between Semantic Spaces

no code implementations11 Jul 2018 Tomáš Brychcín, Stephen Eugene Taylor, Lukáš Svoboda

We compare several linear transformations and rank them for experiments with monolingual (no transformation), bilingual (one semantic space is transformed to another), and multilingual (all semantic spaces are transformed onto English space) versions of semantic spaces.

Unsupervised Dialogue Act Induction using Gaussian Mixtures

no code implementations20 Dec 2016 Tomáš Brychcín, Pavel Král

This paper introduces a new unsupervised approach for dialogue act induction.

New word analogy corpus for exploring embeddings of Czech words

1 code implementation2 Aug 2016 Lukáš Svoboda, Tomáš Brychcín

Our goal in this paper is to explore the behavior of state-of-the-art word embedding methods on Czech, the language that is characterized by very rich morphology.

Word Embeddings

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