Jabberwocky Parsing: Dependency Parsing with Lexical Noise

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F19%3A10427152" target="_blank" >RIV/00216208:11320/19:10427152 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.aclweb.org/anthology/W19-0112" target="_blank" >https://www.aclweb.org/anthology/W19-0112</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Jabberwocky Parsing: Dependency Parsing with Lexical Noise

Popis výsledku v původním jazyce

Parsing models have long benefited from the use of lexical information, and indeed currentstate-of-the art neural network models for dependency parsing achieve substantial improvementsby benefiting from distributed representations of lexical information. At the sametime, humans can easily parse sentences with unknown or even novel words, as in Lewis Carroll’s poem Jabberwocky. In this paper, we carry out jabberwocky parsing experiments, exploring how robust a state-of-the-art neural network parser is to the absence of lexicalinformation. We find that current parsing models, at least under usual training regimens, are in fact overly dependent on lexicalinformation, and perform badly in the jabberwocky context. We also demonstrate that the technique of word dropout drastically improves parsing robustness in this setting, and also leads to significant improvements in out-of-domain parsing.

Název v anglickém jazyce

Jabberwocky Parsing: Dependency Parsing with Lexical Noise

Popis výsledku anglicky

Parsing models have long benefited from the use of lexical information, and indeed currentstate-of-the art neural network models for dependency parsing achieve substantial improvementsby benefiting from distributed representations of lexical information. At the sametime, humans can easily parse sentences with unknown or even novel words, as in Lewis Carroll’s poem Jabberwocky. In this paper, we carry out jabberwocky parsing experiments, exploring how robust a state-of-the-art neural network parser is to the absence of lexicalinformation. We find that current parsing models, at least under usual training regimens, are in fact overly dependent on lexicalinformation, and perform badly in the jabberwocky context. We also demonstrate that the technique of word dropout drastically improves parsing robustness in this setting, and also leads to significant improvements in out-of-domain parsing.

Druh

O - Ostatní výsledky

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

—

Rok uplatnění

2019

Kód důvěrnosti údajů

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