Annif Analyzer Shootout: Comparing text lemmatization methods for automated subject indexing

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F22%3AJXM7A3CF" target="_blank" >RIV/00216208:11320/22:JXM7A3CF - isvavai.cz</a>

Výsledek na webu

<a href="https://journal.code4lib.org/articles/16719" target="_blank" >https://journal.code4lib.org/articles/16719</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Annif Analyzer Shootout: Comparing text lemmatization methods for automated subject indexing

Popis výsledku v původním jazyce

Automated text classification is an important function for many AI systems relevant to libraries, including automated subject indexing and classification. When implemented using the traditional natural language processing (NLP) paradigm, one key part of the process is the normalization of words using stemming or lemmatization, which reduces the amount of linguistic variation and often improves the quality of classification. In this paper, we compare the output of seven different text lemmatization algorithms as well as two baseline methods. We measure how the choice of method affects the quality of text classification using example corpora in three languages. The experiments have been performed using the open source Annif toolkit for automated subject indexing and classification, but should generalize also to other NLP toolkits and similar text classification tasks. The results show that lemmatization methods in most cases outperform baseline methods in text classification particularly for Finnish and Swedish text, but not English, where baseline methods are most effective. The differences between lemmatization methods are quite small. The systematic comparison will help optimize text classification pipelines and inform the further development of the Annif toolkit to incorporate a wider choice of normalization methods.

Název v anglickém jazyce

Annif Analyzer Shootout: Comparing text lemmatization methods for automated subject indexing

Popis výsledku anglicky

Automated text classification is an important function for many AI systems relevant to libraries, including automated subject indexing and classification. When implemented using the traditional natural language processing (NLP) paradigm, one key part of the process is the normalization of words using stemming or lemmatization, which reduces the amount of linguistic variation and often improves the quality of classification. In this paper, we compare the output of seven different text lemmatization algorithms as well as two baseline methods. We measure how the choice of method affects the quality of text classification using example corpora in three languages. The experiments have been performed using the open source Annif toolkit for automated subject indexing and classification, but should generalize also to other NLP toolkits and similar text classification tasks. The results show that lemmatization methods in most cases outperform baseline methods in text classification particularly for Finnish and Swedish text, but not English, where baseline methods are most effective. The differences between lemmatization methods are quite small. The systematic comparison will help optimize text classification pipelines and inform the further development of the Annif toolkit to incorporate a wider choice of normalization methods.

Druh

J_ost - Ostatní články v recenzovaných periodicích

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

2022

Kód důvěrnosti údajů

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

Název periodika

The Code4Lib Journal

ISSN

1940-5758

e-ISSN

2076-3425

Svazek periodika

—

Číslo periodika v rámci svazku

54

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

8

Strana od-do

1-8

Kód UT WoS článku

000856268200001

EID výsledku v databázi Scopus

2-s2.0-85138622509