A Rule-Based Parser in Comparison with Statistical Neuronal Approaches in Terms of Grammar Competence

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3AJ4MGKWD7" target="_blank" >RIV/00216208:11320/26:J4MGKWD7 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.3390/app15010087" target="_blank" >http://dx.doi.org/10.3390/app15010087</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3390/app15010087" target="_blank" >10.3390/app15010087</a>

Jazyk výsledku

angličtina

Název v původním jazyce

A Rule-Based Parser in Comparison with Statistical Neuronal Approaches in Terms of Grammar Competence

Popis výsledku v původním jazyce

The “Easy Language” standard was created to help individuals with cognitive disabilities understand texts more easily. Typically, text simplification is performed by language experts and is available for limited materials. We introduce a new software tool designed to analyze and simplify any text according to the “Easy Language” rules. This tool uses a rule-based system, conducting a full grammatical analysis of each sentence and then simplifying it into a grammatically correct form. Unlike neuronal approaches, which are based on statistics and are very popular today, our rule-based approach explicitly addresses language ambiguities by examining all possible interpretations and eliminating the incorrect ones. The purpose of the present study is to compare the performance of our rule-base parser with two state-of-the-art statistical parsers, one based on dependencies between words (SpaCy parser) and the other based on linguistic constituents (Stanford parser). Although large language models (LLMs), which are the technical basis of the software ChatGPT, were not designed specifically for grammatical parsing, because of their popularity, users, especially language learners, often ask them grammatical questions as well. Therefore, we use LLMs as supplementary models for comparison. LMMs produce grammatically correct text on any topic; however, their grammar knowledge is implicit within the trained weights. To evaluate how well state-of-the-art methods can perform a grammatical analysis, we parse ten sentences with our tool, the statistical parsers from SpaCy and Stanford, and ask two LLMs equivalent grammar questions. The results show that our rule-based method provides a more informative and reliable grammatical analysis compared to these two parsers and outperforms LLMs in that specific task. © 2024 by the authors.

Název v anglickém jazyce

A Rule-Based Parser in Comparison with Statistical Neuronal Approaches in Terms of Grammar Competence

Popis výsledku anglicky

The “Easy Language” standard was created to help individuals with cognitive disabilities understand texts more easily. Typically, text simplification is performed by language experts and is available for limited materials. We introduce a new software tool designed to analyze and simplify any text according to the “Easy Language” rules. This tool uses a rule-based system, conducting a full grammatical analysis of each sentence and then simplifying it into a grammatically correct form. Unlike neuronal approaches, which are based on statistics and are very popular today, our rule-based approach explicitly addresses language ambiguities by examining all possible interpretations and eliminating the incorrect ones. The purpose of the present study is to compare the performance of our rule-base parser with two state-of-the-art statistical parsers, one based on dependencies between words (SpaCy parser) and the other based on linguistic constituents (Stanford parser). Although large language models (LLMs), which are the technical basis of the software ChatGPT, were not designed specifically for grammatical parsing, because of their popularity, users, especially language learners, often ask them grammatical questions as well. Therefore, we use LLMs as supplementary models for comparison. LMMs produce grammatically correct text on any topic; however, their grammar knowledge is implicit within the trained weights. To evaluate how well state-of-the-art methods can perform a grammatical analysis, we parse ten sentences with our tool, the statistical parsers from SpaCy and Stanford, and ask two LLMs equivalent grammar questions. The results show that our rule-based method provides a more informative and reliable grammatical analysis compared to these two parsers and outperforms LLMs in that specific task. © 2024 by the authors.

Druh

J_SC - Článek v periodiku v databázi SCOPUS

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

2025

Kód důvěrnosti údajů

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

Název periodika

Applied Sciences (Switzerland)

ISSN

2076-3417

e-ISSN

—

Svazek periodika

15

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

37

Strana od-do

1-37

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-85214529812