2 citations · 3 across the 4 of their papers we have counts for
5 papers · 1 filter
Cross-lingual Word Analogies using Linear Transformations between Semantic Spaces
Tomáš Brychcín, Stephen Eugene Taylor, Lukáš Svoboda
We generalize the word analogy task across languages, to provide a new intrinsic evaluation method for cross-lingual semantic spaces. We experiment with six languages within differ…
Linear Transformations for Cross-lingual Semantic Textual Similarity
Tomáš Brychcín
Cross-lingual semantic textual similarity systems estimate the degree of the meaning similarity between two sentences, each in a different language. State-of-the-art algorithms usu…
Unsupervised Dialogue Act Induction using Gaussian Mixtures
Tomáš Brychcín, Pavel Král
This paper introduces a new unsupervised approach for dialogue act induction. Given the sequence of dialogue utterances, the task is to assign them the labels representing their fu…
New word analogy corpus for exploring embeddings of Czech words
Lukáš Svoboda, Tomáš Brychcín
The word embedding methods have been proven to be very useful in many tasks of NLP (Natural Language Processing). Much has been investigated about word embeddings of English words…
Latent Tree Language Model
Tomas Brychcin
In this paper we introduce Latent Tree Language Model (LTLM), a novel approach to language modeling that encodes syntax and semantics of a given sentence as a tree of word roles. T…