Cross Lingual Entity Linking
Related Papers
Design Challenges in Low-resource Cross-lingual Entity Linking
AbstractCross-lingual Entity Linking (XEL), the problem of grounding mentions of entities in a foreign language text into an English knowledge base such as Wikipedia, has seen a lot of research …...
Improving Candidate Generation for Low-resource Cross-lingual Entity Linking
AbstractCross-lingual entity linking (XEL) is the task of finding referents in a target-language knowledge base (KB) for mentions extracted from source-language texts. The first step of (X)EL is candidate generation, …...
Soft Gazetteers for Low-Resource Named Entity Recognition
AbstractTraditional named entity recognition models use gazetteers (lists of entities) as features to improve performance. Although modern neural network models do not require such hand-crafted features for strong performance, recent …...
Efficient Entity Candidate Generation for Low-Resource Languages
AbstractCandidate generation is a crucial module in entity linking. It also plays a key role in multiple NLP tasks that have been proven to beneficially leverage knowledge bases. Nevertheless, it …...
Prix-LM: Pretraining for Multilingual Knowledge Base Construction
AbstractKnowledge bases (KBs) contain plenty of structured world and commonsense knowledge. As such, they often complement distributional text-based information and facilitate various downstream tasks. Since their manual construction is resource- …...
Performance Prediction via Bayesian Matrix Factorisation for Multilingual Natural Language Processing Tasks
AbstractPerformance prediction for Natural Language Processing (NLP) seeks to reduce the experimental burden resulting from the myriad of different evaluation scenarios, e.g., the combination of languages used in multilingual transfer. …...
Probing Cross-Lingual Lexical Knowledge from Multilingual Sentence Encoders
AbstractPretrained multilingual language models (LMs) can be successfully transformed into multilingual sentence encoders (SEs; e.g., LaBSE, xMPNet) via additional fine-tuning or model distillation with parallel data. However, it remains unclear …...