Abstract: Techniques for identifying attributes in a sentence and determining a number of attributes to be associated with the sentence is described.

Abstract: A system for augmenting click-through data with latent information present in the click-through data for use in generating search results that are better tailored to the information needs of a user submitting a query is provided. The augmentation system creates a three-dimensional matrix with the dimensions of users, queries, and documents. The augmentation system then performs a three-order singular value decomposition of the three-dimensional matrix to generate a three-dimensional core singular value matrix and a left singular matrix for each dimension. The augmentation system finally multiplies the three-dimensional core singular value matrix by the left singular matrices to generate an augmented three-dimensional matrix that explicitly contains the information that was latent in the un-augmented three-dimensional matrix.

Abstract: Providing sentiment classification of out of domain data are disclosed herein. In some aspects, a source domain having a trained classifier is matched to a target domain having a target classifier. The trained classifier may include identifiers that may be used to predict the sentiment of opinion data for the source domain. The target classifier may use the identifiers of the trained classifier to determine the sentiment of opinion data for the target domain.

Abstract: A search system and method is provided. The method includes constructing a graph-based query that is indicative of a user's preference-levels for different features of a search item (a product, for example). The constructed graph-based query is executed by comparing the user's preference-levels for the different features of the product, which are graphically represented in the query, with information related to sentiments expressed by other users regarding the product. Information related to the sentiments expressed by other users regarding the product can include system-generated product performance graphs constructed from comments regarding the product obtained from the World Wide Web (or other network). Results returned and output upon execution of the graph-based query include system-generated product performance graphs that are similar to the user-submitted query.

Abstract: A method of ranking a plurality of products includes obtaining a numerical user score for each of the plurality of products, calculating an opinion score for each of the plurality of products for which a written comparison sentiment applies, determining a final score by combining the numerical user rating and the opinion score for each of the plurality of products, and ranking the plurality of products based on the final score. The opinion score is derived from one or more written comparison sentiments containing a first product name and a second product name. In another aspect, a computer readable medium has instructions stored thereon which, when executed, cause a computer to perform a method of ranking a plurality of products including at least a first product and a second product.

Abstract: Methods and systems are provided for performing a comparative search. In one example, the comparative search is performed over a network, such as the web, or a database. In one exemplary implementation, a user transmits a plurality of queries which represent the topics that a user wants to compare, and a computing system can automatically retrieve and rank web pages or documents based on both their relevance to queries and the comparative contents they contain. In one such example, the comparative pages are displayed in a pair or other form of a grouping. In another example, comparative results having similar contents may be clustered into meaningful themes.

Abstract: A method and system is provided for classifying documents based on the subjectivity of the content of the documents using a part-of-speech analysis to help account for unseen words. A classification system trains a classifier using the parts of speech of training documents so that the classifier can classify unseen words based on the part of speech of the unseen word. The classification system then trains a part-of-speech model using the parts of speech of the n-grams of training data and labels of the training documents, and trains a term model using the term unigrams and labels. To classify a target document, the classification system applies the part-of-speech model to the part-of-speech n-grams of the target document and the term model to term n-grams of the target document.

Abstract: A sentiment classifier is described. In one implementation, a system applies both full text and complex feature analyses to sentences of a product review. Each analysis is weighted prior to linear combination into a final sentiment prediction. A full text model and a complex features model can be trained separately offline to support online full text analysis and complex features analysis. Complex features include opinion indicators, negation patterns, sentiment-specific sections of the product review, user ratings, sequence of text chunks, and sentence types and lengths. A Conditional Random Field (CRF) framework provides enhanced sentiment classification for each segment of a complex sentence to enhance sentiment prediction.

Abstract: Systems and methods for searching heterogeneous interrelated entities for a heterogeneous entities search query are disclosed herein. A user may enter the heterogeneous entities search query. The search retrieves and returns multiple types of heterogeneous entities. The retrieved heterogeneous interrelated entities are searched in a unified matrix that represents relationships between one or more heterogeneous entities. The retrieved heterogeneous interrelated entities may have one or more entity types. The set of retrieved interrelated entities may also be ranked based on the similarity between each entity and the search query. Feedback may also be incorporated into the system to improve search accuracy.

Abstract: A search system and method is provided. The method includes constructing a graph-based query that is indicative of a user's preference-levels for different features of a search item (a product, for example). The constructed graph-based query is executed by comparing the user's preference-levels for the different features of the product, which are graphically represented in the query, with information related to sentiments expressed by other users regarding the product. Information related to the sentiments expressed by other users regarding the product can include system-generated product performance graphs constructed from comments regarding the product obtained from the World Wide Web (or other network). Results returned and output upon execution of the graph-based query include system-generated product performance graphs that are similar to the user-submitted query.

Abstract: This disclosure describes various exemplary methods, computer program products, and user interfaces that provide results for a product review search with opinion snippets and opinion visual graphs. This disclosure describes identifying user opinions by extracting passages that contain subjective opinions from web pages; ranking the user opinions by incorporating sentiment orientations and sentiment topics, where the sentiment orientations are positive or negative; and generating review snippets to indicate user sentiment orientations and to describe user opinions toward product features. This disclosure improves a user product search experience from the following aspects: understanding the product review from snippets instead of browsing the web page; obtaining more information by reading reviews in a shorter time period; and obtaining overall opinions of users of the web through visualized opinion summarization.

Abstract: An exemplary computer implemented graphics-based Web search system includes a search input control and a results presentation control where the search input control is configured to receive user input to establish a relationship between a query and one or more information tags associated with search results provided by a search engine in response to the query and wherein the results presentation control is configured to re-order the search results in response to the relationship. Such a system allows a user to define and refine search intent and enhance the user's search experience. Various other exemplary systems, methods, devices, etc. are also disclosed.

Abstract: Described is a technology by which an intermediate taxonomy is processed (e.g., offline) with respect to a target taxonomy to determine relationship values between categories represented in the intermediate taxonomy and the target taxonomy. The relationship values are used to construct a bridging classifier for use in online query processing to relate queries to categories in the target taxonomy. The relation is based on each target category's relationship to one or more categories that were represented in the intermediate taxonomy. Further, only a relevant subset of the categories represented in the intermediate taxonomy may be chosen for use in the bridging classifier, e.g., based on relative probability scores and/or mutual information scores computed between the categories represented in the intermediate taxonomy and categories in the target taxonomy.

Abstract: Methods and systems are provided for performing a comparative search. In one example, the comparative search is performed over a network, such as the web, or a database. In one exemplary implementation, a user transmits a plurality of queries which represent the topics that a user wants to compare, and a computing system can automatically retrieve and rank web pages or documents based on both their relevance to queries and the comparative contents they contain. In one such example, the comparative pages are displayed in a pair or other form of a grouping. In another example, comparative results having similar contents may be clustered into meaningful themes.

Abstract: A system for augmenting click-through data with latent information present in the click-through data for use in generating search results that are better tailored to the information needs of a user submitting a query is provided. The augmentation system creates a three-dimensional matrix with the dimensions of users, queries, and documents. The augmentation system then performs a three-order singular value decomposition of the three-dimensional matrix to generate a three-dimensional core singular value matrix and a left singular matrix for each dimension. The augmentation system finally multiplies the three-dimensional core singular value matrix by the left singular matrices to generate an augmented three-dimensional matrix that explicitly contains the information that was latent in the un-augmented three-dimensional matrix.