Semantically Coherent Vector Space Representations

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F19%3A00109517" target="_blank" >RIV/00216224:14330/19:00109517 - isvavai.cz</a>

Výsledek na webu

<a href="https://mir.fi.muni.cz/posters/mlprague-2019-semantic_representations.pdf" target="_blank" >https://mir.fi.muni.cz/posters/mlprague-2019-semantic_representations.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Semantically Coherent Vector Space Representations

Popis výsledku v původním jazyce

<p>Our work is a scientific poster that was presented at the ML Prague 2019 conference during February 22–24, 2019.</p> <p>Content is king (<a href="http://web.archive.org/web/20010126005200/http://www.microsoft.com/billgates/columns/1996essay/essay960103.asp">Gates, 1996</a>). Decomposition of word semantics matters (<a href="https://arxiv.org/abs/1301.3781">Mikolov, 2013</a>). Decomposition of a sentence, paragraph, and document semantics into semantically coherent vector space representations matters, too. Interpretability of these learned vector spaces is the holy grail of natural language processing today, as it would allow accurate representation of thoughts and plugging-in inference into the game.</p> <p>We will show recent results of our attempts towards this goal by showing how decomposition of document semantics could improve the query answering, performance, and “horizontal transfer learning” based on word2bits could be achieved.</p> <p>Word representation in the form of binary features allows to use word lattice representation for feature inference by the well studied formal concept analysis theory, and for precise semantic similarity metric based on discriminative features. Also, the incremental learning of word features allows to interpret and infer on them, targeting the holy grail.</p>

Název v anglickém jazyce

Semantically Coherent Vector Space Representations

Popis výsledku anglicky

<p>Our work is a scientific poster that was presented at the ML Prague 2019 conference during February 22–24, 2019.</p> <p>Content is king (<a href="http://web.archive.org/web/20010126005200/http://www.microsoft.com/billgates/columns/1996essay/essay960103.asp">Gates, 1996</a>). Decomposition of word semantics matters (<a href="https://arxiv.org/abs/1301.3781">Mikolov, 2013</a>). Decomposition of a sentence, paragraph, and document semantics into semantically coherent vector space representations matters, too. Interpretability of these learned vector spaces is the holy grail of natural language processing today, as it would allow accurate representation of thoughts and plugging-in inference into the game.</p> <p>We will show recent results of our attempts towards this goal by showing how decomposition of document semantics could improve the query answering, performance, and “horizontal transfer learning” based on word2bits could be achieved.</p> <p>Word representation in the form of binary features allows to use word lattice representation for feature inference by the well studied formal concept analysis theory, and for precise semantic similarity metric based on discriminative features. Also, the incremental learning of word features allows to interpret and infer on them, targeting the holy grail.</p>

Druh

O - Ostatní výsledky

CEP obor

—

OECD FORD obor

10200 - Computer and information sciences

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2019

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů