Challenge: Current approaches for relation classification are focused on the English language and require lots of training data with human annotations.
Approach: They propose a baseline model based on Multilingual BERT and a new multilingual pretraining setup . they propose 'relationship classification' models that use distant supervision .
Outcome: The proposed model significantly improves the baseline model with distant supervision.

Similar Papers

DiS-ReX: A Multilingual Dataset for Distantly Supervised Relation Extraction (2022.acl-short)

Copied to clipboard

Challenge: Existing benchmarking datasets for multilingual relation extraction have been lacking .
Approach: They propose to use a new benchmark dataset to study multilingual relation extraction task by distant supervision.
Outcome: The proposed task is performed on a multilingual relation extraction dataset using an mBERT encoder.
MultiLexBATS: Multilingual Dataset of Lexical Semantic Relations (2024.lrec-main)

Copied to clipboard

Challenge: Prior work has focused on analysing lexical semantic relations in word embeddings or probing pretrained language models (PLMs) with some exceptions.
Approach: They propose to use a multilingual parallel dataset of lexical semantic relations adapted from BATS in 15 languages including low-resource languages such as Bambara, Lithuanian, and Albanian as an experiment on cross-lingual transfer of relational knowledge.
Outcome: The proposed dataset is adapted from a BATS-based dataset in 15 languages including low-resource languages such as Bambara, Lithuanian, and Albanian.
XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation (2020.emnlp-main)

Copied to clipboard

Challenge: XGLUE provides a benchmark dataset to train large-scale cross-lingual pre-trained models . XCLUE provides 11 diversified tasks that cover both understanding and generation scenarios .
Approach: They introduce a new benchmark dataset to train large-scale cross-lingual pre-trained models using multilingual and bilingual corpora.
Outcome: The proposed dataset is labeled in English and includes only natural language understanding tasks.
X-WikiRE: A Large, Multilingual Resource for Relation Extraction as Machine Comprehension (D19-61)

Copied to clipboard

Challenge: Existing knowledge bases are heavily biased towards English, but Wikipedias cover very different topics in different languages.
Approach: They propose a multilingual dataset that frams relation extraction as a machine reading problem.
Outcome: The proposed model can be used to transfer models cross-lingually and improves knowledge base completion across languages.
Can Monolingual Pretrained Models Help Cross-Lingual Classification? (2020.aacl-main)

Copied to clipboard

Challenge: Multilingual pretrained language models have shown impressive results for cross-lingual transfer, but due to the constant model capacity, multilingual pre-training usually lags behind the monolingual competitors.
Approach: They propose to transfer the knowledge from monolingual pretrained models to multilingual ones to improve zero-shot cross-lingual classification by using machine translation systems.
Outcome: The proposed methods outperform vanilla multilingual fine-tuning on two cross-lingual classification benchmarks.
Multilingual Entity and Relation Extraction Dataset and Model (2021.eacl-main)

Copied to clipboard

Challenge: HERBERTa is a pipeline for a multilingual task involving two separate BERT models.
Approach: They propose a dataset and a model that combines two independently pretrained BERT models for a multilingual setting to approach the task of Joint Entity and Relation Extraction.
Outcome: The proposed dataset achieves micro F1 81.49 for English on the SMiLER dataset . the proposed pipeline is close to the current SOTA on CoNLL, SpERT .
X-SRL: A Parallel Cross-Lingual Semantic Role Labeling Dataset (2020.emnlp-main)

Copied to clipboard

Challenge: Existing multilingual SRL datasets contain disparate annotation styles or come from different domains, hampering generalization in multilingual learning.
Approach: They propose to automatically construct an SRL corpus that is parallel in four languages with unified predicate and role annotations that are fully comparable across languages.
Outcome: The proposed method improves performance for English SRL in weaker languages.
UniteD-SRL: A Unified Dataset for Span- and Dependency-Based Multilingual and Cross-Lingual Semantic Role Labeling (2021.findings-emnlp)

Copied to clipboard

Challenge: Multilingual and cross-lingual Semantic Role Labeling (SRL) has attracted increasing attention as multilingual text representation techniques have become more effective and widely available.
Approach: They propose a benchmark for multilingual and cross-lingual, span- and dependency-based SRL that provides expert-curated parallel annotations using a common predicate-argument structure inventory.
Outcome: The proposed benchmark provides expert-curated parallel annotations using a common predicate-argument structure inventory, allowing direct comparisons across languages and encouraging studies on cross-lingual transfer in SRL.
CrossRE: A Cross-Domain Dataset for Relation Extraction (2022.findings-emnlp)

Copied to clipboard

Challenge: Relation Extraction (RE) evaluation is limited to in-domain setups . despite the drought of research on cross-domain RE, its practical importance remains .
Approach: They propose a cross-domain benchmark for relation extraction which includes multi-label annotations and meta-data to include explanations and flags of difficult instances.
Outcome: The proposed model includes explanations and flags of difficult instances.
A Corpus for Multilingual Document Classification in Eight Languages (L18-1)

Copied to clipboard

Challenge: a subset of the Reuters corpus volume 2 is used to evaluate cross-lingual document classification . current best practice is to evaluate document classification on resources in one language and transfer it to another without additional resources.
Approach: They propose to use a subset of the Reuters corpus to evaluate cross-lingual document classification . they propose to add Italian, Russian, Japanese and Chinese to the subset .
Outcome: The proposed subset of the Reuters corpus has balanced class priors for eight languages.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations