When FastText Pays Attention: Efficient Estimation of Word Representations using Constrained Positional Weighting

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F22%3A00124923" target="_blank" >RIV/00216224:14330/22:00124923 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.3897/jucs.69619" target="_blank" >https://doi.org/10.3897/jucs.69619</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3897/jucs.69619" target="_blank" >10.3897/jucs.69619</a>

Jazyk výsledku

angličtina

Název v původním jazyce

When FastText Pays Attention: Efficient Estimation of Word Representations using Constrained Positional Weighting

Popis výsledku v původním jazyce

In 2018, Mikolov et al. introduced the positional language model, which has characteristics of attention-based neural machine translation models and which achieved state-of-the-art performance on the intrinsic word analogy task. However, the positional model is not practically fast and it has never been evaluated on qualitative criteria or extrinsic tasks. We propose a constrained positional model, which adapts the sparse attention mechanism from neural machine translation to improve the speed of the positional model. We evaluate the positional and constrained positional models on three novel qualitative criteria and on language modeling. We show that the positional and constrained positional models contain interpretable information about the grammatical properties of words and outperform other shallow models on language modeling. We also show that our constrained model outperforms the positional model on language modeling and trains twice as fast.

Název v anglickém jazyce

When FastText Pays Attention: Efficient Estimation of Word Representations using Constrained Positional Weighting

Popis výsledku anglicky

In 2018, Mikolov et al. introduced the positional language model, which has characteristics of attention-based neural machine translation models and which achieved state-of-the-art performance on the intrinsic word analogy task. However, the positional model is not practically fast and it has never been evaluated on qualitative criteria or extrinsic tasks. We propose a constrained positional model, which adapts the sparse attention mechanism from neural machine translation to improve the speed of the positional model. We evaluate the positional and constrained positional models on three novel qualitative criteria and on language modeling. We show that the positional and constrained positional models contain interpretable information about the grammatical properties of words and outperform other shallow models on language modeling. We also show that our constrained model outperforms the positional model on language modeling and trains twice as fast.

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

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2022

Kód důvěrnosti údajů

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

Název periodika

Journal of Universal Computer Science

ISSN

0948-695X

e-ISSN

0948-6968

Svazek periodika

28

Číslo periodika v rámci svazku

2

Stát vydavatele periodika

CZ - Česká republika

Počet stran výsledku

21

Strana od-do

181-201

Kód UT WoS článku

000767374300005

EID výsledku v databázi Scopus

2-s2.0-85127775769