Linear transformations for cross-lingual semantic textual similarity

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F20%3A43956550" target="_blank" >RIV/49777513:23520/20:43956550 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.sciencedirect.com/science/article/pii/S0950705119302941" target="_blank" >https://www.sciencedirect.com/science/article/pii/S0950705119302941</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.knosys.2019.06.027" target="_blank" >10.1016/j.knosys.2019.06.027</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Linear transformations for cross-lingual semantic textual similarity

Popis výsledku v původním jazyce

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 usually employ machine translation and combine vast amount of features, making the approach strongly supervised, resource rich, and difficult to use for poorly-resourced languages. In this paper, we study linear transformations, which project monolingual semantic spaces into a shared space using bilingual dictionaries. We propose a novel transformation, which builds on the best ideas from prior works. We experiment with unsupervised techniques for sentence similarity based only on semantic spaces and we show they can be significantly improved by the word weighting. Our transformation outperforms other methods and together with word weighting leads to very promising results on several datasets in different languages.

Název v anglickém jazyce

Linear transformations for cross-lingual semantic textual similarity

Popis výsledku anglicky

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 usually employ machine translation and combine vast amount of features, making the approach strongly supervised, resource rich, and difficult to use for poorly-resourced languages. In this paper, we study linear transformations, which project monolingual semantic spaces into a shared space using bilingual dictionaries. We propose a novel transformation, which builds on the best ideas from prior works. We experiment with unsupervised techniques for sentence similarity based only on semantic spaces and we show they can be significantly improved by the word weighting. Our transformation outperforms other methods and together with word weighting leads to very promising results on several datasets in different languages.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/EF17_048%2F0007267" target="_blank" >EF17_048/0007267: VaV inteligentních komponent pokročilých technologií pro plzeňskou metropolitní oblast</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2020

Kód důvěrnosti údajů

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

Název periodika

Knowledge-Based Systems

ISSN

0950-7051

e-ISSN

—

Svazek periodika

187

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

9

Strana od-do

1-9

Kód UT WoS článku

000501653900008

EID výsledku v databázi Scopus

2-s2.0-85068031029