Investigating Sub-Word Embedding Strategies for the Morphologically Rich and Free Phrase-Order Hungarian

no code implementations • WS 2019 • B{\'a}lint D{\"o}br{\"o}ssy, M{\'a}rton Makrai, Bal{\'a}zs Tarj{\'a}n, Gy{\"o}rgy Szasz{\'a}k

For morphologically rich languages, word embeddings provide less consistent semantic representations due to higher variance in word forms.

Lemmatization Morphological Analysis +1

One format to rule them all -- The emtsv pipeline for Hungarian

1 code implementation • WS 2019 • Bal{\'a}zs Indig, B{\'a}lint Sass, Eszter Simon, Iv{\'a}n Mittelholcz, No{\'e}mi Vad{\'a}sz, M{\'a}rton Makrai

We present a more efficient version of the e-magyar NLP pipeline for Hungarian called emtsv.

300-sparsans at SemEval-2018 Task 9: Hypernymy as interaction of sparse attributes

no code implementations • SEMEVAL 2018 • G{\'a}bor Berend, M{\'a}rton Makrai, P{\'e}ter F{\"o}ldi{\'a}k

This paper describes 300-sparsians{'}s participation in SemEval-2018 Task 9: Hypernym Discovery, with a system based on sparse coding and a formal concept hierarchy obtained from word embeddings.

Hypernym Discovery Word Embeddings

Evaluating multi-sense embeddings for semantic resolution monolingually and in word translation

no code implementations • WS 2016 • G{\'a}bor Borb{\'e}ly, M{\'a}rton Makrai, D{\'a}vid M{\'a}rk Nemeskey, Andr{\'a}s Kornai

Translation Word Embeddings +1

Filtering Wiktionary Triangles by Linear Mbetween Distributed Word Models

no code implementations • LREC 2016 • M{\'a}rton Makrai

The former is exemplified by Wiktionary, a crowd-sourced dictionary with editions in many languages.

Translation

Competence in lexical semantics

1 code implementation • SEMEVAL 2015 • Andr{\'a}s Kornai, Judit {\'A}cs, M{\'a}rton Makrai, D{\'a}vid M{\'a}rk Nemeskey, Katalin Pajkossy, G{\'a}bor Recski

Applicative structure in vector space models

no code implementations • WS 2013 • M{\'a}rton Makrai, David Mark Nemeskey, Andr{\'a}s Kornai