This paper proposes an open-domain method for automatically annotating modifier constituents (20th-century’) within Wikipedia categories (20th-century male writers) with properties (date of birth). The annotations offer a semantically-anchored understanding of the role of the constituents in defining the underlying meaning of the categories. In experiments over an evaluation set of Wikipedia categories, the proposed method annotates constituent modifiers as semantically-anchored properties, rather than as mere strings in a previous method. It does so at a better trade-off between precision and recall.

This tutorial examines the role of Wikipedia in tasks related to text analysis and retrieval. Text analysis tasks, which take advantage of Wikipedia, include coreference resolution, word sense and entity disambiguation and information extraction. In information retrieval, a better understanding of the structure and meaning of queries helps in matching queries against documents, clustering search results, answer and entity retrieval and retrieving knowledge panels for queries asking about popular entities.

We present a method for populating fine-grained classes (e.g., “1950s American jazz musicians”) with instances (e.g., Charles Mingus ). While state-of-the-art methods tend to treat class labels as single lexical units, the proposed method considers each of the individual modifiers in the class label relative to the head. An evaluation on the task of reconstructing Wikipedia category pages demonstrates a >10 point increase in AUC, over a strong baseline relying on widely-used Hearst patterns.

Through subsumption and instantiation, individual instances (“artificial intelligence”, “the spotted pig”) otherwise spanning a wide range of domains can be brought together and organized under conceptual hierarchies. The hierarchies connect more specific concepts (“computer science subfields”, “gastropubs”) to more general concepts (“academic disciplines”, “restaurants”) through IsA relations. Explicit or implicit properties applicable to, and defining, more general concepts are inherited by their more specific concepts, down to the instances connected to the lower parts of the hierarchies. Subsumption represents a crisp, universally-applicable principle towards consistently representing IsA relations in any knowledge resource. Yet knowledge resources often exhibit significant differences in their scope, representation choices and intended usage, to cause significant differences in their expected usage and impact on various tasks. This tutorial examines the theoretical foundations of subsumption, and its practical embodiment through IsA relations compiled manually or extracted automatically. It addresses IsA relations from their formal definition; through practical choices made in their representation within the larger and more widely-used of the available knowledge resources; to their automatic acquisition from document repositories, as opposed to their manual compilation by human contributors; to their impact in text analysis and information retrieval. As search engines move away from returning a set of links and closer to returning results that more directly answer queries, IsA relations play an increasingly important role towards a better understanding of documents and queries. The tutorial teaches the audience about definitions, assumptions and practical choices related to modeling and representing IsA relations in existing, human-compiled resources of instances, concepts and resulting conceptual hierarchies; methods for automatically extracting sets of instances within unlabeled or labeled concepts, where the concepts may be considered as a flat set or organized hierarchically; and applications of IsA relations in information retrieval.

Guided by multiple heuristics, a unified taxonomy of entities and categories is distilled from the Wikipedia category network. A comprehensive evaluation, based on the analysis of upward generalization paths, demonstrates that the taxonomy supports generalizations which are more than twice as accurate as the state of the art. The taxonomy is available at http://headstaxonomy.com.

This tutorial examines the characteristics, advantages and limitations of Wikipedia relative to other existing, human-curated resources of knowledge; derivative resources, created by converting semi-structured content in Wikipedia into structured data; the role of Wikipedia and its derivatives in text analysis; and the role of Wikipedia and its derivatives in enhancing information retrieval.

The identification of textual items, or documents, that best match a user’s information need, as expressed in search queries, forms the core functionality of information retrieval systems. Well-known challenges are associated with understanding the intent behind user queries; and, more importantly, with matching inherently-ambiguous queries to documents that may employ lexically different phrases to convey the same meaning. The conversion of semi-structured content from Wikipedia and other resources into structured data produces knowledge potentially more suitable to database-style queries and, ideally, to use in information retrieval. In parallel, the availability of textual documents on the Web enables an aggressive push towards the automatic acquisition of various types of knowledge from text. Methods developed under the umbrella of open-domain information extraction acquire open-domain classes of instances and relations from Web text. The methods operate over unstructured or semi-structured text available within collections of Web documents, or over relatively more intriguing streams of anonymized search queries. Some of the methods import the automatically-extracted data into human-generated resources, or otherwise exploit existing human-generated resources. In both cases, the goal is to expand the coverage of the initial resources, thus providing information about more of the topics that people in general, and Web search users in particular, may be interested in.

We introduce a low-complexity method for acquiring fine-grained classes of named entities from the Web. The method exploits the large amounts of textual data available on the Web, while avoiding the use of any expensive text processing techniques or tools. The quality of the extracted classes is encouraging with respect to both the precision of the sets of named entities acquired within various classes, and the labels assigned to the sets of named entities.