Uptraining for accurate deterministic question parsing. Zero-shot entity extraction from Web pages. Web-scale distributional similarity and entity set expansion. ![]() Dissecting German grammar and Swiss passports: Open-domain decomposition of compositional entries in large-scale knowledge repositories. Interpreting compound noun phrases using Web search queries. Inferring missing entity type instances for knowledge base completion: New dataset and methods. Transforming Wikipedia into a large scale multilingual concept network. Decoding Wikipedia categories for knowledge acquisition. ACM Transactions on Speech and Language Processing, 10(3):1-51, 2013. Semantic interpretation of noun compounds using verbal and other paraphrases. Composition in distributional models of semantics. Open language learning for information extraction. No noun phrase left behind: Detecting and typing unlinkable entities. Phrase clustering for discriminative learning. Automatic identification of non-compositional phrases. Class label enhancement via related instances. Large-scale noun compound interpretation using bootstrapping and the Web as a corpus. Understanding user's query intent with Wikipedia. Special Issue on Artificial Intelligence, Wikipedia and Semi-Structured Resources, 194:28-61, 2013. YAGO2: a spatially and temporally enhanced knowledge base from Wikipedia. ![]() Discovering emerging entities with ambiguous names. Automatic acquisition of hyponyms from large text corpora. Leveraging linguistic structure for open domain information extraction. Two is bigger (and better) than one: the Wikipedia Bitaxonomy project. Open information extraction: The second generation. Knowledge Vault: A Web-scale approach to probabilistic knowledge fusion. Extraction and approximation of numerical attributes from the Web. Websets: Extracting sets of entities from the Web using unsupervised information extraction. ![]() Scalable semantic parsing with partial ontologies. Toward an architecture for never-ending language learning. DBpedia - a crystallization point for the Web of data. Open information extraction from the Web. The method exploits the category network to associate constituents (Costa Rican) within names of Wikipedia categories, with attributes (nationality) that explain their role. As an illustration of the relationship between class labels and facts, the paper introduces an open-domain method for the better understanding of the semantics of class labels in one of the larger and most widely-used repositories of knowledge, namely the categories in the Wikipedia category network. A constituent (Costa Rican) within a class label (Costa Rican short story writers) of an instance may be indicative of a fact (nationality: Costa Rica) applicable to the instance and vice-versa. This paper argues that class labels and facts pertaining to an instance exist in symbiosis rather than as a dichotomy. From extraction through internal representation and storage, class labels and facts are treated as if they carved out disconnected slices within the larger space of factual knowledge. Given an instance (Julieta Pinto), most methods for open-domain information extraction focus on acquiring knowledge in the form of either class labels (Costa Rican short story writers, Women novelists) referring to concepts to which the instance belongs or facts (nationality: Costa Rica) connecting the instance (Julieta Pinto) to other instances or concepts (Costa Rica), where the fact and the other instance often take the form of an attribute (nationality) and a value (Costa Rica) respectively.
0 Comments
Leave a Reply. |