A Gradient Boosting-Seq2Seq System for Latin POS Tagging and Lemmatization

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F20%3A10426949" target="_blank" >RIV/00216208:11320/20:10426949 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.aclweb.org/anthology/2020.lt4hala-1.19" target="_blank" >https://www.aclweb.org/anthology/2020.lt4hala-1.19</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

A Gradient Boosting-Seq2Seq System for Latin POS Tagging and Lemmatization

Popis výsledku v původním jazyce

The paper presents the system used in the EvaLatin shared task to POS tag and lemmatize Latin. It consists of two components. A gradient boosting machine (LightGBM) is used for POS tagging, mainly fed with pre-computed word embeddings of a window of seven contiguous tokens—the token at hand plus the three preceding and following ones—per target feature value. Word embeddings are trained on the texts of the Perseus Digital Library, Patrologia Latina, and Biblioteca Digitale di Testi Tardo Antichi, which together comprise a high number of texts of different genres from the Classical Age to Late Antiquity. Word forms plus the outputted POS labels are used to feed a seq2seq algorithm implemented in Keras to predict lemmas. The final shared-task accuracies measured for Classical Latin texts are in line with state-of-the-art POS taggers (∼0.96) and lemmatizers (∼0.95).

Název v anglickém jazyce

A Gradient Boosting-Seq2Seq System for Latin POS Tagging and Lemmatization

Popis výsledku anglicky

The paper presents the system used in the EvaLatin shared task to POS tag and lemmatize Latin. It consists of two components. A gradient boosting machine (LightGBM) is used for POS tagging, mainly fed with pre-computed word embeddings of a window of seven contiguous tokens—the token at hand plus the three preceding and following ones—per target feature value. Word embeddings are trained on the texts of the Perseus Digital Library, Patrologia Latina, and Biblioteca Digitale di Testi Tardo Antichi, which together comprise a high number of texts of different genres from the Classical Age to Late Antiquity. Word forms plus the outputted POS labels are used to feed a seq2seq algorithm implemented in Keras to predict lemmas. The final shared-task accuracies measured for Classical Latin texts are in line with state-of-the-art POS taggers (∼0.96) and lemmatizers (∼0.95).

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

2020

Kód důvěrnosti údajů

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