Fuji Xerox Co., Ltd.

Microsoft Technology Licensing, LLC

Other

Fuji Xexox Co., Ltd.

Livia Polanyi

Martin Henk Van Den Berg

Giovanni Lorenzo Thione

Annie E Zaenen

Misty L Azara

Barney Pell

Richard Stamford Crouch

David D Ahn

Bee Yian Liew

Scott A Prevost

Olga Iosifovna Gurevich

Patrick Chiu

Franco Salvetti

Eleanor Rieffel

Alexandros Ntoulas

Yue Lu

Panayiotis Tsaparas

Christopher D Culy

James D Baker

Methods and computer-readable media for associating words or groups of words distilled from content, such as reported speech or an attitude report, of a document to form semantic relationships collectively used to generate a semantic representation of the content are provided. Semantic representations may include elements identified or parsed from a text portion of the content, the elements of which may be associated with other elements that share a semantic relationship, such as an agent, location, or topic relationship. Relationships may also be developed by associating one element that is in relation to, or is about, another element, thereby allowing for rapid and effective comparison of associations found in a semantic representation with associations derived from queries. The semantic relationships may be determined based on semantic information, such as potential meanings and grammatical functions of each element within the text portion of the content.

Identification of semantic relationships within reported speech

User generated reviews and scores associated with the reviews may be used to train a review scoring model with textual features of the reviews. The review scoring model may be used to predict scores for newly received reviews. One or more constraints based on social networking application data associated with an author of a review may be used to adjust the predicted score of the review.

Assessing quality of user reviews

Consumers receive module-computed composite reviews that are lively, informative, coherent, and representative of a larger underlying collection of reviews. Representative phrases from reviews are extracted and aggregated into coherent sentences to create the composite review. Clear automatable criteria are provided to define coherence and other qualities, such as representativeness, liveliness, and informativity. Sentence coherence criteria involve syntax, shared vocabulary, phrase connectors, and phrase sentiment polarity, for instance. Phrase representativeness criteria involve review ratings and derived phrase ratings, for instance. Phrase liveliness criteria involve sentiment expression frequency, superlatives, comparatives, degree modifiers, affect activation scores, and affect imagery scores, for instance. Phrase informativity criteria involve product-specific words, review length, and recency, for instance. Prohibited language is filtered out. Composite reviews are automatically distributed, e.g., in response to a web search on the reviewed product. Reviews can be generated with a repeatability and rapidity not attainable by human performance alone.

Automatic generation of digital composite product reviews

Tools and techniques related to calculating valence of expressions within documents. These tools may provide methods that include receiving input documents for processing, and extracting expressions from the documents for valence analysis, with scope relationships occurring between terms contained in the expressions. The methods may calculate calculating valences of the expressions, based on the scope relationships between terms in the expressions.

Calculating valence of expressions within documents for searching a document index

Techniques are provided for determining relevant information from a document based on document structure. A document is selected and structural elements within the document having a dominance relationship are determined. A first location within the document is selected. The structural element surrounding the first location is determined and the surrounding and non-surrounding structural elements are characterized. Additional documents are associated with the first location in the surrounding structural element based on the surrounding structural element characterization and the non-surrounding structural element characterization. Techniques for dynamically determining annotations for images based on document structure are also provided.

Systems and methods for determining relevant information based on document structure

Techniques are provided for segmenting text into categorized discourse constituents and attaching discourse constituents into a structural representation of discourse. Techniques for determining hybrid structural and non-structural summaries of a text are also provided. A text is segmented based on a theory of discourse analysis into at least a main discourse constituent containing spatio-temporal information about a single event in a possible world view. The discourse constituents are then inserted into a structural representation of discourse. Non-structural techniques are used to determine relevance scores and important discourse constituents are determined. Relevance scores are percolated through the structural representation of discourse to determine supporting preceding discourse constituents that preserve grammaticality. A hybrid text summary is then determined based on the structural representation of the discourse and relevance scores.

Systems and methods for hybrid text summarization

Techniques are provided for determining predictive models of discourse functions based on prosodic features of natural language speech. Inter and intra sentential discourse functions in a training corpus of natural language speech utterances are determined. The discourse functions are clustered. The exemplary prosodic features associated with each type of discourse function are determined. Machine learning, observation and the like are used to determine a subset of prosodic features associated with each type of discourse function useful in predicting the likelihood of each type of discourse function.

Systems and methods for determining predictive models of discourse functions

Techniques for dynamic personalized reading fluency instruction and improvement are provided by determining a user reading fluency level based on one or more spoken responses provided by the user during one or more reading aloud session of a text that has been evaluated for discourse structure and information structure of sentences. One or more reading fluency improvement aids are provided to the user based on one or more of: determined user-specific reading fluency deficiencies, user-personalized information responses and user class-specific reading fluency deficiencies as determined by the reading fluency improvement system.

Systems and methods for dynamic reading fluency instruction and improvement

A method for adaptively determining the attitudinal function of a lexical item occurring in a natural language document, comprising determining a base valence of the lexical item; identifying a contextual valence shifter (CVS) wherein the lexical item is within scope of the CVS; and determining an actual valence of the lexical item by adjusting the base valence based on the CVS.

System and method for dynamically determining the function of a lexical item based on context

Techniques are provided for determining and using interaction models. Discourse functions, prosodic features and turn information are determined from the speech information in a training corpus. Statistics, decision trees, rules and/or various other methods are used to determine a predictive interaction model based on the discourse functions, the prosodic features and the turn information. Predictive interaction models are optionally determined for individual users, genres, languages and/or other characteristics of the speech information. The predictive interaction model is useable to predict turns in a dialogue based on the discourse functions and prosodic features identified in the speech information. Speech information is presented and/or received based on the predictive interaction model.

Systems and methods for determining and using interaction models

Techniques for dynamic personalized reading instruction at word and sentence level are provided by determining word recognition level and learning gradient information for a user. Comprehension aids are associated with words classified by word recognition level and stored. Word recognition errors are determined, comprehension aids presented and word recognition level adjusted based on determined word recognition errors, learning gradient and current word recognition level. For sentence level dynamic personalized reading instruction personalization information, reading level and learning gradient are determined and a personalized grammatical tunable text summary generated. Based on the personalized grammatical tunable text summary, comprehension questions are generated and displayed. Based on comprehension responses, learning gradient and personalization information, the reading level is adjusted. Personalized reading instruction is provided by selectively changing display attributes of more salient information to help a user identify the important information in the sentence and to maintain fluid reading.

Dynamically changing the levels of reading assistance and instruction to support the needs of different individuals

A method for adaptively analyzing a natural language document containing at least one lexical item, said analysis to determine an attitude of an author towards an entity, comprising determining at least one actual valence for the at least one lexical item by analyzing the at least one lexical item in context, determining the attitude based on the at least one actual valence, associating the author, the entity and the attitude, and wherein the at least one lexical item encodes attitude information about the entity.

System and method for dynamically determining the attitude of an author of a natural language document

A method for adaptively determining the attitudinal function of a lexical item occurring in a natural language document, comprising determining a base valence of the lexical item; determining an actual valence of the lexical item by adjusting the base valence based on the discourse structure of the document; and wherein the actual valence denotes an attitude of an author towards an entity or event.

System and method for dynamically determining the function of a lexical item based on discourse hierarchy structure

A system and method of summarizing text comprising performing structural summarization of a source text and compressing at least one relationship in the structural summarization.

Growing community of inventors

Palo Alto, CA, United States of America

Livia Polanyi