Entity Linking In 100 Languages | Awesome LLM Papers Add your paper to Awesome LLM Papers

Awesome LLM Papers

A collection of research papers on LLMs.

Stay Updated

Contact Sean Moran about this survey or website. Made with Jekyll and Hyde.

Entity Linking In 100 Languages

Jan A. Botha, Zifei Shan, Daniel Gillick . Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) 2020 – 68 citations

[Code] [Paper]   Search on Google Scholar   Search on Semantic Scholar
Datasets EMNLP Evaluation Few Shot Interdisciplinary Approaches Training Techniques

We propose a new formulation for multilingual entity linking, where language-specific mentions resolve to a language-agnostic Knowledge Base. We train a dual encoder in this new setting, building on prior work with improved feature representation, negative mining, and an auxiliary entity-pairing task, to obtain a single entity retrieval model that covers 100+ languages and 20 million entities. The model outperforms state-of-the-art results from a far more limited cross-lingual linking task. Rare entities and low-resource languages pose challenges at this large-scale, so we advocate for an increased focus on zero- and few-shot evaluation. To this end, we provide Mewsli-9, a large new multilingual dataset (http://goo.gle/mewsli-dataset) matched to our setting, and show how frequency-based analysis provided key insights for our model and training enhancements.

Similar Work