Design Challenges in Low-resource Cross-lingual Entity Linking
This addresses the challenge of linking entities in low-resource language texts to English knowledge bases, which is crucial for improving multilingual NLP applications, though it is an incremental advance over prior methods.
The paper tackled the problem of cross-lingual entity linking for low-resource languages, where existing methods fail due to reliance on Wikipedia interlanguage links, and introduced QuEL, a zero-shot system using search engine query logs that improved gold candidate recall by 25% and linking accuracy by 13% over state-of-the-art baselines across 25 languages.
Cross-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 in recent years, with a range of promising techniques. However, current techniques do not rise to the challenges introduced by text in low-resource languages (LRL) and, surprisingly, fail to generalize to text not taken from Wikipedia, on which they are usually trained. This paper provides a thorough analysis of low-resource XEL techniques, focusing on the key step of identifying candidate English Wikipedia titles that correspond to a given foreign language mention. Our analysis indicates that current methods are limited by their reliance on Wikipedia's interlanguage links and thus suffer when the foreign language's Wikipedia is small. We conclude that the LRL setting requires the use of outside-Wikipedia cross-lingual resources and present a simple yet effective zero-shot XEL system, QuEL, that utilizes search engines query logs. With experiments on 25 languages, QuEL~shows an average increase of 25\% in gold candidate recall and of 13\% in end-to-end linking accuracy over state-of-the-art baselines.