Cross-lingual transfer learning for relation extraction using Universal Dependencies

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F22%3A6TSMFV6D" target="_blank" >RIV/00216208:11320/22:6TSMFV6D - isvavai.cz</a>

Výsledek na webu

<a href="https://www.sciencedirect.com/science/article/pii/S0885230821000711" target="_blank" >https://www.sciencedirect.com/science/article/pii/S0885230821000711</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.csl.2021.101265" target="_blank" >10.1016/j.csl.2021.101265</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Cross-lingual transfer learning for relation extraction using Universal Dependencies

Popis výsledku v původním jazyce

This paper focuses on the task of cross-language relation extraction, which aims to identify the semantic relations holding between entities in the text. The goal of the task is to train classifiers for low-resource languages by means of the annotated data from high-resource languages. Related methods usually employ parallel data or Machine Translator (MT) to project annotated data from a source to a target language. However, the availability and the quality of parallel data and MT are big challenges for low-resource languages. In this paper, a novel transfer learning method is presented for this task. The key idea is to utilize a tree-based representation of data, which is highly informative for classifying semantic relations, and also shared among different languages. All the training and test data are shown using this representation. We propose to use the Universal Dependency (UD) parsing, which is a language-agnostic formalism for representation of syntactic structures. Equipping UD parse trees with multi-lingual word embeddings makes an ideal representation for the cross-language relation extraction task. We propose two deep networks to use this representation. The first one utilizes the Shortest Dependency Path of UD trees, while the second employs the UD-based positional embeddings. Experiments are performed using SemEval 2010-task 8 training data, whereas French and Farsi are the test languages. The results show 63.9% and 56.2% F1 scores, for French and Farsi test data, respectively, which are 14.4% and 17.9% higher than the baseline. This work can be considered a simple yet powerful baseline for further investigation into the cross-language tasks.

Název v anglickém jazyce

Cross-lingual transfer learning for relation extraction using Universal Dependencies

Popis výsledku anglicky

This paper focuses on the task of cross-language relation extraction, which aims to identify the semantic relations holding between entities in the text. The goal of the task is to train classifiers for low-resource languages by means of the annotated data from high-resource languages. Related methods usually employ parallel data or Machine Translator (MT) to project annotated data from a source to a target language. However, the availability and the quality of parallel data and MT are big challenges for low-resource languages. In this paper, a novel transfer learning method is presented for this task. The key idea is to utilize a tree-based representation of data, which is highly informative for classifying semantic relations, and also shared among different languages. All the training and test data are shown using this representation. We propose to use the Universal Dependency (UD) parsing, which is a language-agnostic formalism for representation of syntactic structures. Equipping UD parse trees with multi-lingual word embeddings makes an ideal representation for the cross-language relation extraction task. We propose two deep networks to use this representation. The first one utilizes the Shortest Dependency Path of UD trees, while the second employs the UD-based positional embeddings. Experiments are performed using SemEval 2010-task 8 training data, whereas French and Farsi are the test languages. The results show 63.9% and 56.2% F1 scores, for French and Farsi test data, respectively, which are 14.4% and 17.9% higher than the baseline. This work can be considered a simple yet powerful baseline for further investigation into the cross-language tasks.

Druh

J_imp - Článek v periodiku v databázi Web of Science

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

Computer Speech and Language

ISSN

0885-2308

e-ISSN

1095-8363

Svazek periodika

71

Číslo periodika v rámci svazku

2022-1-1

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

12

Strana od-do

1-12

Kód UT WoS článku

000761599000006

EID výsledku v databázi Scopus

2-s2.0-85111004456