|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
In this paper, we introduce a novel task of cross-modal consistency verification in real-world news and present a multimodal approach to quantify the entity coherence between image and text.
Cross-lingual entity linking (XEL) is the task of finding referents in a target-language knowledge base (KB) for mentions extracted from source-language texts.
We consider the zero-shot entity-linking challenge where each entity is defined by a short textual description, and the model must read these descriptions together with the mention context to make the final linking decisions.
KnowledgeNet is a benchmark dataset for the task of automatically populating a knowledge base (Wikidata) with facts expressed in natural language text on the web.
Despite of the recent success of collective entity linking (EL) methods, these "global" inference methods may yield sub-optimal results when the "all-mention coherence" assumption breaks, and often suffer from high computational cost at the inference stage, due to the complex search space.
However, most neural collective EL methods depend entirely upon neural networks to automatically model the semantic dependencies between different EL decisions, which lack of the guidance from external knowledge.
First, we show that strong reading comprehension models pre-trained on large unlabeled data can be used to generalize to unseen entities.
First, we construct a high recall list of candidate entities for each mention in an unlabeled document.
Short texts challenge NLP tasks such as named entity recognition, disambiguation, linking and relation inference because they do not provide sufficient context or are partially malformed (e. g. wrt.