Learning Entity Representations for Few-Shot Reconstruction of Wikipedia Categories
Language modeling tasks, in which words are predicted on the basis of a local context, have been very effective for learning word embeddings and context dependent representations of phrases. Motivated by the observation that efforts to code world knowledge into machine readable knowledge bases tend to be entity-centric, we investigate the use of a fill-in-the-blank task to learn context independent representations of entities from the contexts in which those entities were mentioned. We show that large scale training of neural models allows us to learn extremely high fidelity entity typing information, which we demonstrate with few-shot reconstruction of Wikipedia categories. Our learning approach is powerful enough to encode specialized topics such as Giro d’Italia cyclists.
Code (0)
등록된 구현이 없습니다.
Tasks
Entity TypingLanguage ModelingLanguage ModellingLearning Word EmbeddingsWord EmbeddingsWorld KnowledgeSimilar Papers 제목 키워드 기반
Entity Disambiguation with Web Links
Entity disambiguation with Wikipedia relies on structured information from redirect pages, article text, inter-article links, and categories. We explore whether web links can replace a curated encyclopaedia, obtaining en…
Entity DisambiguationEntity LinkingKnowledge Base PopulationDescription-Based Zero-shot Fine-Grained Entity Typing
Fine-grained Entity typing (FGET) is the task of assigning a fine-grained type from a hierarchy to entity mentions in the text. As the taxonomy of types evolves continuously, it is desirable for an entity typing system t…
Entity TypingVocal Bursts Type PredictionRecognizing Descriptive Wikipedia Categories for Historical Figures
Wikipedia is a useful knowledge source that benefits many applications in language processing and knowledge representation. An important feature of Wikipedia is that of categories. Wikipedia pages are assigned different …
DescriptiveInformation RetrievalRetrievalTAGWikipedia Entities as Rendezvous across Languages: Grounding Multilingual Language Models by Predicting Wikipedia Hyperlinks
Masked language models have quickly become the de facto standard when processing text. Recently, several approaches have been proposed to further enrich word representations with external knowledge sources such as knowle…
ArticlesKnowledge GraphsLearning Cross-Context Entity Representations from Text
Language modeling tasks, in which words, or word-pieces, are predicted on the basis of a local context, have been very effective for learning word embeddings and context dependent representations of phrases. Motivated by…
Entity LinkingLanguage ModelingLanguage ModellingLearning Word Embeddings+2