Neural Cross-Lingual Relation Extraction Based on Bilingual Word Embedding Mapping

Abstract

Relation extraction (RE) seeks to detect and classify semantic relationships between entities, which provides useful information for many NLP applications. Since the state-ofthe-art RE models require large amounts of manually annotated data and language-specific resources to achieve high accuracy, it is very challenging to transfer an RE model of a resource-rich language to a resource-poor language. In this paper, we propose a new approach for cross-lingual RE model transfer based on bilingual word embedding mapping. It projects word embeddings from a target language to a source language, so that a welltrained source-language neural network RE model can be directly applied to the target language. Experiment results show that the proposed approach achieves very good performance for a number of target languages on both in-house and open datasets, using a small bilingual dictionary with only 1K word pairs.

Towards an entity relation extraction framework in the cross-lingual context

“…The target language data set was obtained by machine translation, and then the feature representation of the source language was transferred to the target language using the generative adversarial network. Ni and Florian (2019) proposed a cross-lingual relation extraction model by projecting word embedding from one space to another through leveraging a small dictionary. Yu et al (2020) attempted to decompose cross-lingual relation extraction into parallel corpus acquisition and AARE, but the experiments are limited to English and Chinese.…”

The RELX Dataset and Matching the Multilingual Blanks for Cross-Lingual Relation Classification

“…Before the introduction of multilingual transformers (Devlin et al, 2019;Conneau and Lample, 2019;Conneau et al, 2020), cross-lingual word embeddings have been widely used in zero-shot crosslingual transfer with word embedding alignments for different tasks such as named entity recognition (Xie et al, 2018) and natural language inference (Conneau et al, 2018). This approach has also been utilized for cross-lingual relation classification (Ni and Florian, 2019). However, recently, multilingual deep transformers have attracted lots of attention in several cross-lingual tasks such as question answering (Artetxe et al, 2020;Liu et al, 2019;Conneau et al, 2020), natural language inference (Conneau and Lample, 2019;Conneau et al, 2020;Wu and Dredze, 2019), and named entity recognition (Conneau et al, 2020).…”

“…Zou et al (2018) make use of a Generative Adversarial Network (GAN) to transfer the feature representations from the source language to the target language with the help of machine translation systems. Ni and Florian (2019) employ bilingual word embedding mappings trained with bilingual dictionaries to develop a cross-lingual relation classification model.…”

“…ACE05 includes data in English, Arabic, and Chinese; however, it is not freely available, and the number of relations is rather small, which is 6. In (Ni and Florian, 2019), a relation classification dataset for 6 languages with 53 relation types has been used, yet this dataset is not publicly available. In this paper, we release the RELX dataset created with human annotations and the RELX- Distant dataset compiled using distant supervision.…”

“…Then, we introduce an approach called Matching the Multilingual Blanks to improve the relation classification ability of mBERT in different languages with the help of a considerable number of relation pairs collected by distant supervision. Prior works on cross-lingual relation classification use additional resources in the target language such as aligned corpora (Kim and Lee, 2012), machine translation systems (Faruqui and Kumar, 2015), or bilingual dictionaries (Ni and Florian, 2019). Our mBERT baseline model does not require any additional resources in the target language.…”