Using Adversarial Examples in Natural Language Processing

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F18%3A10390133" target="_blank" >RIV/00216208:11320/18:10390133 - isvavai.cz</a>

Výsledek na webu

<a href="http://www.lrec-conf.org/proceedings/lrec2018/summaries/852.html" target="_blank" >http://www.lrec-conf.org/proceedings/lrec2018/summaries/852.html</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Using Adversarial Examples in Natural Language Processing

Popis výsledku v původním jazyce

Machine learning models have been providing promising results in many fields including natural language processing. These models are, nevertheless, prone to adversarial examples. These are artificially constructed examples which evince two main features: they resemble the real training data but they deceive already trained model. This paper investigates the effect of using adversarial examples during the training of recurrent neural networks whose text input is in the form of a sequence of word/character embeddings. The effects are studied on a compilation of eight NLP datasets whose interface was unified for quick experimenting. Based on the experiments and the dataset characteristics, we conclude that using the adversarial examples for NLP tasks that are modeled by recurrent neural networks provides a regularization effect and enables the training of models with greater number of parameters without overfitting. In addition, we discuss which combinations of datasets and model settings might benefit f

Název v anglickém jazyce

Using Adversarial Examples in Natural Language Processing

Popis výsledku anglicky

Machine learning models have been providing promising results in many fields including natural language processing. These models are, nevertheless, prone to adversarial examples. These are artificially constructed examples which evince two main features: they resemble the real training data but they deceive already trained model. This paper investigates the effect of using adversarial examples during the training of recurrent neural networks whose text input is in the form of a sequence of word/character embeddings. The effects are studied on a compilation of eight NLP datasets whose interface was unified for quick experimenting. Based on the experiments and the dataset characteristics, we conclude that using the adversarial examples for NLP tasks that are modeled by recurrent neural networks provides a regularization effect and enables the training of models with greater number of parameters without overfitting. In addition, we discuss which combinations of datasets and model settings might benefit f

Druh

D - Stať ve sborníku

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<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2018

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 11th International Conference on Language Resources and Evaluation (LREC 2018)

ISBN

979-10-95546-00-9

ISSN

—

e-ISSN

neuvedeno

Počet stran výsledku

8

Strana od-do

3693-3700

Název nakladatele

European Language Resources Association

Místo vydání

Paris, France

Místo konání akce

Miyazaki, Japan

Datum konání akce

7. 5. 2018

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—