The RELX Dataset and Matching the Multilingual Blanks for Cross-Lingual Relation Classification
Relation classification is one of the key topics in information extraction, which can be used to construct knowledge bases or to provide useful information for question answering. Current approaches for relation classification are mainly focused on the English language and require lots of training data with human annotations. Creating and annotating a large amount of training data for low-resource languages is impractical and expensive. To overcome this issue, we propose two cross-lingual relation classification models: a baseline model based on Multilingual BERT and a new multilingual pretraining setup, which significantly improves the baseline with distant supervision. For evaluation, we introduce a new public benchmark dataset for cross-lingual relation classification in English, French, German, Spanish, and Turkish, called RELX. We also provide the RELX-Distant dataset, which includes hundreds of thousands of sentences with relations from Wikipedia and Wikidata collected by distant supervision for these languages. Our code and data are available at: https://github.com/boun-tabi/RELX
Code (1)
Tasks
ClassificationQuestion AnsweringRelationRelation ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
The RELX Dataset and Matching the Multilingual Blanks for Cross-Lingual Relation Classification
Relation classification is one of the key topics in information extraction, which can be used to construct knowledge bases or to provide useful information for question answering. Current approaches for relation classifi…
ClassificationGeneral ClassificationQuestion AnsweringRelation+1DiS-ReX: A Multilingual Dataset for Distantly Supervised Relation Extraction
Our goal is to study the novel task of distant supervision for multilingual relation extraction (Multi DS-RE). Research in Multi DS-RE has remained limited due to the absence of a reliable benchmarking dataset. The only …
BenchmarkingRelationRelation ExtractionMulti-blank Transducers for Speech Recognition
This paper proposes a modification to RNN-Transducer (RNN-T) models for automatic speech recognition (ASR). In standard RNN-T, the emission of a blank symbol consumes exactly one input frame; in our proposed method, we i…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionBlank Language Models
We propose Blank Language Model (BLM), a model that generates sequences by dynamically creating and filling in blanks. The blanks control which part of the sequence to expand, making BLM ideal for a variety of text editi…
Ancient Text RestorationLanguage ModelingLanguage ModellingStyle TransferTask-Conditional Flow Matching for Balanced Multilingual Text Embedding Adaptation
Multilingual text embedding models are commonly adapted using a single training objective across diverse tasks, despite different tasks requiring fundamentally different optimization strategies. We introduce Task-Conditi…