Cross-lingual word analogies using linear transformations between semantic spaces

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F19%3A43955837" target="_blank" >RIV/49777513:23520/19:43955837 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.sciencedirect.com/science/article/pii/S0957417419304191" target="_blank" >https://www.sciencedirect.com/science/article/pii/S0957417419304191</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.eswa.2019.06.021" target="_blank" >10.1016/j.eswa.2019.06.021</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Cross-lingual word analogies using linear transformations between semantic spaces

Popis výsledku v původním jazyce

The ability to represent the meaning of words is one of the core parts of natural language understanding (NLU), with applications ranging across machine translation, summarization, question answering, information retrieval, etc. The need for reasoning in multilingual contexts and transferring knowledge in cross- lingual systems has given rise to cross-lingual semantic spaces, which learn representations of words across different languages. With growing attention to cross-lingual representations, it has became crucial to investigate proper evaluation schemes. The word-analogy-based evaluation has been one of the most common tools to evaluate linguistic relationships (such as male-female relationships or verb tenses) encoded in monolingual meaning representations. In this paper, we go beyond monolingual representations and generalize the word analogy task across languages to provide a new intrinsic evaluation tool for cross-lingual semantic spaces. Our approach allows examining cross-lingual projections and their impact on different aspects of meaning. It helps to discover potential weaknesses or advantages of cross-lingual methods before they are incorporated into different intelligent systems. We experiment with six languages within different language families, including English, German, Spanish, Italian, Czech, and Croatian. State-of-the-art monolingual semantic spaces are transformed into a shared space using dictionaries of word translations. 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. We show that tested linear transformations preserve relationships between words (word analogies) and lead to impressive results. We achieve average accuracy of 51.1%, 43.1%, and 38.2% for monolingual, bilingual, and multilingual semantic spaces, respectively.

Název v anglickém jazyce

Cross-lingual word analogies using linear transformations between semantic spaces

Popis výsledku anglicky

The ability to represent the meaning of words is one of the core parts of natural language understanding (NLU), with applications ranging across machine translation, summarization, question answering, information retrieval, etc. The need for reasoning in multilingual contexts and transferring knowledge in cross- lingual systems has given rise to cross-lingual semantic spaces, which learn representations of words across different languages. With growing attention to cross-lingual representations, it has became crucial to investigate proper evaluation schemes. The word-analogy-based evaluation has been one of the most common tools to evaluate linguistic relationships (such as male-female relationships or verb tenses) encoded in monolingual meaning representations. In this paper, we go beyond monolingual representations and generalize the word analogy task across languages to provide a new intrinsic evaluation tool for cross-lingual semantic spaces. Our approach allows examining cross-lingual projections and their impact on different aspects of meaning. It helps to discover potential weaknesses or advantages of cross-lingual methods before they are incorporated into different intelligent systems. We experiment with six languages within different language families, including English, German, Spanish, Italian, Czech, and Croatian. State-of-the-art monolingual semantic spaces are transformed into a shared space using dictionaries of word translations. 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. We show that tested linear transformations preserve relationships between words (word analogies) and lead to impressive results. We achieve average accuracy of 51.1%, 43.1%, and 38.2% for monolingual, bilingual, and multilingual semantic spaces, respectively.

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>S - Specificky vyzkum na vysokych skolach<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2019

Kód důvěrnosti údajů

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

Název periodika

Expert Systems with Applications

ISSN

0957-4174

e-ISSN

—

Svazek periodika

135

Číslo periodika v rámci svazku

NOV 30 2019

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

9

Strana od-do

287-295

Kód UT WoS článku

000480665800022

EID výsledku v databázi Scopus

2-s2.0-85067242443