Abstract: Technologies for development of IsA repositories are described that can be applied to the interpretation of text by computing devices in a variety of settings. The use of features other than those computed over an underlying document collection, such as popularity in search queries of the terms in class labels, is described, for the purpose of determining, or improving, the relative ranking of various class labels, given a class instance.

Abstract: Named entities are disambiguated in search queries and other contexts using a disambiguation scoring model. The scoring model is developed using a knowledge base of articles, including articles about named entities. Various aspects of the knowledge base, including article titles, redirect pages, disambiguation pages, hyperlinks, and categories, are used to develop the scoring model.

Abstract: Methods, systems, and apparatus, including computer program products, for extracting information from unstructured text. Fact pairs are used to extract basic patterns from a body of text. Patterns are generalized by replacing words with classes of similar words. Generalized patterns are used to extract further fact pairs from the body of text. The process can begin with fact pairs, basic patterns, or generalized patterns.

Abstract: Technology is described herein for creating new, inferred queries that are suitable for use as query suggestions. The technology includes mapping different past queries that represent different information requests, but that share a number of terms having the same or similar form. An inferred query is created by replacing unshared terms in one mapped query with the unshared terms in another mapped query, based on the similarity between the unshared terms in the two mapped queries. The inferred query thus represents a new information request that is derived from the information requests of the past queries used to form it. The inferred query can then be provided as a query suggestion, which increases the likelihood of providing query suggestions that will assist users in finding the information they seek. In doing so, meaningful query suggestions can be provided to users seeking information outside the coverage of the past queries.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for extracting instance attributes from text are described. In one aspect, a method exploits weakly-supervised and unsupervised instance relatedness data, available in the form of labeled classes of instances and distributionally similar instances. The method organizes the data into a graph containing instances, class labels, and attributes. The method propagates attributes among related instances, through random walks over the graph.

Abstract: A plurality of images related to a particular image are determined, and a plurality of annotations associated with the plurality of images are identified. An ontology is determined based on the plurality of annotations, and an image annotation for the particular image is determined based on the ontology. The ontology may be a semantic ontology, for example.

Abstract: Methods and apparatus related to processing of at least one descriptive term of a query to obtain at least one query suggestion for a query. A descriptive term may be identified in a partial search query. A modified partial query suggestion request for the partial search query may be transmitted that omits the descriptive term. At least one query suggestion result for the modified partial query suggestion request may be received and the descriptive term reinserted into the query suggestion result.

Abstract: A classifier training system learns classifiers for categories by combining data from a category-instance repository comprising relationships between categories and more specific instances of those categories with a set of video classifiers for different concepts. The category-instance repository is derived from the domain of textual documents, such as web pages, and the concept classifiers are derived from the domain of video. Taken together, the category-instance repository and the concept classifiers provide sufficient data for obtaining accurate classifiers for categories that encompass other lower-level concepts, where the categories and their classifiers may not be obtainable solely from the video domain.

Abstract: Systems, techniques, and machine-readable instructions for inferring attributes from search queries. In one aspect, a method includes receiving a description of a collection of search queries, inferring attributes of entities from the description of the collection of search queries, associating the inferred attributes with identifiers of entities characterized by the attributes, and making the associations of the attributes and entities available.

Abstract: Methods and apparatus related to processing of at least one descriptive term of a query to obtain at least one query suggestion for a query. A descriptive term may be identified in a partial search query. A modified partial query suggestion request for the partial search query may be transmitted that omits the descriptive term. At least one query suggestion result for the modified partial query suggestion request may be received and the descriptive term reinserted into the query suggestion result.

Abstract: Methods and systems for retrieval of information items and associated sentence fragments are described. One method described comprises identifying at least a first entry in an index relevant to a search query, wherein the first entry comprises a first information item and a first associated sentence fragment, and wherein the index comprises a plurality of information items and associated sentence fragments, and generating a search result set relevant to the search query comprising at least the first information item.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for extracting instance attributes from text are described. In one aspect, a method exploits weakly-supervised and unsupervised instance relatedness data, available in the form of labeled classes of instances and distributionally similar instances. The method organizes the data into a graph containing instances, class labels, and attributes. The method propagates attributes among related instances, through random walks over the graph.

Abstract: Technology is described herein for creating new, inferred queries that are suitable for use as query suggestions. The technology includes mapping different past queries that represent different information requests, but that share a number of terms having the same or similar form. An inferred query is created by replacing unshared terms in one mapped query with the unshared terms in another mapped query, based on the similarity between the unshared terms in the two mapped queries. The inferred query thus represents a new information request that is derived from the information requests of the past queries used to form it. The inferred query can then be provided as a query suggestion, which increases the likelihood of providing query suggestions that will assist users in finding the information they seek. In doing so, meaningful query suggestions can be provided to users seeking information outside the coverage of the past queries.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for extracting semantic classes and corresponding instances from a collection of text. One aspect of the subject matter described in this specification can be embodied in methods that include the actions of receiving a collection of text; identifying an initial collection of instance-class pairs for the collection of text; clustering a collection of semantically similar phrases using the collection of text; generating, using one or more processors, an extracted collection of instance-class pairs using the initial collection of instance-class pairs and the semantically similar phrase clusters; and storing the extracted collection of instance-class pairs for use in information retrieval.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for extracting and scoring class-instance pairs. One method includes applying extraction patterns to document text to derive class-instance pairs, determining a frequency score and a diversity score for each distinct class-instance pair, and determining a pair score for each class-instance pair from the frequency score and the diversity score. Another method includes applying extraction patterns to document text to derive candidate class-instance pairs, determining, for each distinct candidate class-instance pair, a number of distinct phrases from which the distinct candidate class-instance pair was derived, and determining a pair score for each distinct candidate class-instance pair from the number of distinct phrases from which the candidate class-instance pair was extracted.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating query suggestions. In one aspect, a method includes receiving candidate text queries and class instance pairs and generating one or more query specializations from the candidate text queries and the class instance pairs. In another aspect, a method includes receiving a partial query entered by a user, identifying one or more query specializations for query completions for the partial query, and presenting query suggestions to the user, including presenting the identified query specializations.

Abstract: Methods and systems for identification of paraphrases from an index of information items and associated sentence fragments are described. One method described comprises identifying a pair of sentence fragments each having a same associated information item from an index, wherein the index comprises a plurality of information items and associated sentence fragments, and identifying a paraphrase pair from the pair of sentence fragments.

Abstract: Methods and systems for identification of paraphrases from an index of information items and associated sentence fragments are described. One method described comprises identifying a pair of sentence fragments each having a same associated information item from an index, wherein the index comprises a plurality of information items and associated sentence fragments, and identifying a paraphrase pair from the pair of sentence fragments.

Abstract: Methods and apparatus, including systems and computer program products, to acquire potential paraphrases from textual input. In one aspect, textual input is received, a first map is generated, where the key of the first map is an ngram identified in the textual input and the value associated with the key of the first map is a unique identifier, a second map is generated, where the key of the second map is an anchor identified from the ngram and the value associated with the key of the second map is one or more middle portions associated with the anchor, and a third map is generated, where the key of the third map is a potential paraphrase pair identified from the middle portions and the value associated with the key of the third map is the one or more unique anchors associated with the potential paraphrase pair.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for searching tables using recovered semantic information. In general, one aspect of the subject matter described in this specification can be embodied in methods that include the actions of receiving a collection of tables, each table including a plurality of rows, each row including a plurality of cells; recovering semantic information associated with each table of the collection of tables, the recovering including determining a class associated with each respective table according to a class-instance hierarchy including identifying a subject column of each table of the collection of tables; and labeling each table in the collection of tables with the respective class.