Abstract: Embodiments relate to an artificially intelligence platform to resolve an analogy. representation. The aspect of providing a resolution to the analogy includes receiving a communication that includes an analogy. An analogical phrase within the communication is identified and an anaphora within the phrase is detected. The entity to the anaphora is denoted and utilized to resolve an explanation of the analogy. A template or structure is created and populated with both an action term and the entity identifying the anaphora. A contextual response that correlates to a sentiment reflected in the analogy phrase is retrieved and is utilized as an explanation of the analogy. A response is communicated as output, with the response including the populated structure and the explanation.

Abstract: A speech interpretation module interprets the audio of user utterances as sequences of words. To do so, the speech interpretation module parameterizes a literal corpus of expressions by identifying portions of the expressions that correspond to known concepts, and generates a parameterized statistical model from the resulting parameterized corpus. When speech is received the speech interpretation module uses a hierarchical speech recognition decoder that uses both the parameterized statistical model and language sub-models that specify how to recognize a sequence of words. The separation of the language sub-models from the statistical model beneficially reduces the size of the literal corpus needed for training, reduces the size of the resulting model, provides more fine-grained interpretation of concepts, and improves computational efficiency by allowing run-time incorporation of the language sub-models.

Abstract: Innovations in the areas of determining search areas and queries for database searches are presented. For example, a search tool receives input for a search area for a database search. For the database search, the search tool determines one or more target tables that fit the search area input. In this way, the search tool can determine “on-the-fly” which database tables are relevant for the database search. The search tool can also receive input for a search string and construct queries for the database search in the target table(s). For a field of a table, the search tool can selectively convert a search value to a data format of the field. If the search string input includes multiple search values, the search tool can construct an OR query and/or an AND query. The search results can indicate real-time status of the database, while accounting for complex structures of database tables.

Abstract: A computer system associates one or more actions with an emoji. The computer system detects a selection of the emoji within an electronic communication by a user. In response to the detecting the selection of the emoji within the electronic communication, the computer system initiates performance of at least one action of the one or more actions based on determining that one or more contextual factors associated with the electronic communication satisfy a set of conditions associated with the at least one action.

Abstract: An emotion function chain may be generated from an email thread and displayed to a user in one or more windows on a computer display of a computer system. An email content analyzer may extract emotion indicators from the body of an email within the email thread. Using the emotion indicators, an attitude factor for an email may be determined. The attitude factors determined from each email within the email thread may be pictorially depicted in the emotion function chain. In response to a user interaction with a pictorial depiction of an attitude factor within the emotion function chain, a second window may generated to display the body of the email used to calculate the attitude factor interacted with.

Abstract: An example method involves (i) accessing first data representing text; (ii) identifying a term within the represented text; (iii) using the identified term as a basis to select a text-editing rule from among a set of text-editing rules; (iv) generating second data that represents the represented text edited in accordance with the selected text-editing rule; and (v) providing output based on the generated second data.

Abstract: Systems and methods for converting an application to new programming language or framework is provided. A source application written in a legacy framework is analyzed and divided into smaller segments of code. The smaller segments are evaluated for quality in view of best practices design for writing applications. A rubric is determined for each segment and compared to a best practice threshold. Segments can be evaluated for features that can be passed through a model. The model converts the features into code in the new programming language. Machine learning and rules databases are updated with details of the conversion.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, relating to changing device settings based on an orientation or motion of a mobile device. The method includes receiving a user input, determining that the mobile device was oriented in a first orientation when the user input was received, selecting a first device setting or service request parameter that affects a mobile phone application or a web service experience and that are associated with the first orientation, providing, for output at the mobile device, a first response to the user input based on the first device setting, after providing the first response to the user input, determining that the mobile device has been reoriented in a different, second orientation, selecting a second device setting, and providing a second response to the user input, or to a revision of the user input, based on the second device setting.

Abstract: A method and system for providing personalized search results is disclosed. A computer receives input from a user to navigate to a web site (either directly or as a result of choosing a result from a search result page). The computer navigates to the web site and stores information about the web site in a file. The computer determines web sites associated with a search query of the user as the search query is being entered into a search area of a user interface. The associated web sites are sites that have been previously navigated to by the user. The determining step includes obtaining the web sites associated with the search query from a data structure previously generated from the file. The data structure includes parsed entries of URLs associated with the previously navigated web sites. Based on the determining step, web site links corresponding to the associated web sites are displayed as the search query is being entered.

Abstract: A computing device includes an operation unit configured to receive a first user input about an item to be purchased, a display unit configured to display a name of the item and an interface based on which a user can make a second user input about the user's preference of the item through the operation unit, and a communication unit configured to transmit data corresponding to the first and second user inputs to an external device configured to store information about items for sale and information about user preferences of the items.

Abstract: Provided are techniques for a domain specific representation of document text for accelerated natural language processing. A document is selected from a set of documents to be analyzed. A character stream from the document is converted into a token stream based on tokenization rules. Irrelevant tokens are removed from the token stream. The tokens remaining in the token stream are converted into an integer domain representation based on a domain specific ontology dictionary. The integer domain representation are stored to a Graphics Processing Unit (GPU) processing queue of each of one or more GPUs. Then, a result set is received from the one or more GPUs.

Abstract: Techniques are disclosed for improving the quality and durability of citations used within research documents. A method and apparatus may be sued to enhance the ability of researches to collaborate (or to simply be alerted) when the substance of a reference cited in one research document changes in a way that may conflict with how that reference is used in the citing document. For example, changes in cited reference may undermine (or enhance) the conclusions of a research paper stored in the managed repository.

Abstract: In a first step of a two step content selection operation, initial content can be selected by detecting movement of a content selection object with respect to a computing device. The selection area can be calculated based on the object movement that is detected. The content within the selection area can be selected and displayed in a second display area in which content of different types are separated into logical units. All or part of the initial content can be enlarged, enabling the second step of the selection operation in which a subset of the initial content is selected. Content can be transformed before being pasted into the target.

Abstract: Techniques for asynchronous rendering are described. An apparatus may comprise a character set converter application, an index server, and a ranking application. The character set converter application may receive a search string comprised of one or more first character set characters, and convert the search string to one or more second character set characters that are different than the first character set. The index server may execute a search on the converted search string to obtain ranked individual search results. The ranking application may compare any first character set characters in the ranked individual search results to the first character set characters in the search string and sub-rank the ranked individual search results based on the strength of any matches. Other embodiments are described and claimed.

Abstract: Systems and methods for assisting a user to redesign a live website using a browser-based interface are presented. A first computer server hosts a target website that includes a first code snippet configured to, once executed, create a communication channel to a second computer server. The second computer server is configured to, after execution of the first code snippet, retrieve a content of the target website using the communication channel, analyze the content of the target website to identify one or more candidate keywords to incorporate into the target website, transmit, through the communication channel, the one or more candidate keywords for selection by a user on the target website, receive, through the communication channel, a selection of one of the one or more candidate keywords, generate a second code snippet configured to modify the target website to incorporate the selected one of the one or more candidate keywords, and store the second code snippet on the second computer server.

Abstract: Techniques for graph based natural language processing are described. In one embodiment an apparatus may comprise a client service component operative on the processor circuit to receive a natural language user request from a device and to execute the natural language user request based on matched one or more objects and a social object relation component operative on the processor circuit to match the natural language user request to the one or more objects in an object graph, the object graph comprising token mappings for objects within the object graph, the token mappings based on data extracted from a plurality of interactions by a plurality of users of the network system, wherein the one or more objects are matched with the natural language user request based on the token mappings. Other embodiments are described and claimed.

Abstract: An information retrieval system uses phrases to index, retrieve, organize and describe documents. Phrases are identified that predict the presence of other phrases in documents. Documents are the indexed according to their included phrases. The document index is partitioned into multiple indexes, including a primary index and a secondary index. The primary index stores phrase posting lists with relevance rank ordered documents. The secondary index stores excess documents from the posting lists in document order.

Abstract: A system for associating data input by a user with at least one page of a file created by an application to allow selection of one or more pages associated with a selected navigation category is provided. In the system, metadata is received and associated with at least one page. A navigation category is assigned to the page, determined by its associated metadata. A navigation interface comprising at least one navigation category is generated as a component of the application. A selection of at least one navigation category by a user is received via the navigation interface. One or more pages associated with the selected navigation category are then gathered by the application for display to the user.

Abstract: A mechanism is provided for optimizing parsing of grammatical prose in a multi-prose electronic document. A received multi-prose electronic document is partitioned into a set of text segments of homogenous prose. A set of predefined Natural Language (NL) parsers is executed on each text segment in order to discern and measure a quality of parses by each NL parser throughout the multi-prose electronic document. A cross-parse analysis of the multi-prose electronic document and an aggregation of adjacent clauses or sentences of poor quality parses are performed. For each text segment, aggregation patterns yielding a best semantic role match are identified from one of the set of predefined NL parsers. Then, a parsed electronic document is generated using the set of predefined NL parsers such that each text segment is parsed by a NL parser that has the best semantic role match to that text segment.

Abstract: An information processing apparatus includes a text mining section configured to perform text mining on text data acquired from the outside and to output extracted information; an identification section configured to search a development database storing elements constituting a product and the relationship among the elements by using the information extracted by text mining to identify an element related to the information; and a notification section configured to notify the identified element to a user, a program for use in the information processing apparatus.

Abstract: A method of securely executing practically unbounded input stream of symbols, by non-interactive, multi-party computation, according to which the input stream is distributed among a plurality of parties, which do not communicate among themselves throughout execution, by a dealer with a secret initial state. The dealer distributes shares of the secret state between the parties. The input stream is executed by a finite-state automaton which may be an accumulating automaton with accumulating nodes or an automaton that is defined by a series of cascaded equations. During any execution stage, the input stream and the current state of the original automaton are concealed from any coalition of participants being smaller than a given threshold. Upon receiving a signal from the dealer, the parties terminate the execution and submit their internal state to the dealer, which computes the current state that defines the computation result.

Abstract: Matching objects using keys based on match rules is described. A system generates a match rule key based on a match rule, wherein the match rule specifies whether two objects match. The system creates candidate keys by applying the match rule key to data objects. The system creates a probe key by applying the match rule key to a probe object. The system determines whether the probe key matches a candidate key. The system determines whether the probe object matches a candidate object based on applying the match rule to the probe object and the candidate object if the probe key matches the candidate key corresponding to the candidate object. The system identifies the probe object and the candidate object as matching based on the match rule if the probe object matches the candidate object.

Abstract: A computer implemented method and an apparatus for facilitating voice user interface (VUI) design are provided. The method comprises identifying a plurality of user intentions from user interaction data. The method further comprises associating each user intention with at least one feature from among a plurality of features. One or more features from among the plurality of features are extracted from natural language utterances associated with the user interaction data. Further, the method comprises computing a plurality of distance metrics corresponding to pairs of user intentions from among the plurality of user intentions. A distance metric is computed for each pair of user intentions from among the pairs of user intentions. Furthermore, the method comprises generating a plurality of clusters based on the plurality of distance metrics. Each cluster comprises a set of user intentions. The method further comprises provisioning a VUI design recommendation based on the plurality of clusters.

Abstract: A method, system, and computer program product for generating and using a user semantic dictionary for natural language involving receiving a user dictionary element definition associated with a user ontological object; generating the user semantic dictionary based on the user dictionary element definition, analyzing by a hardware processor the user-provided text to identify a portion of the user-provided text matching the semantic-syntactic data; generating a node in a semantic-syntactic tree, and further natural language processing of the user-provided text using the generated semantic-syntactic tree. The semantic-syntactic tree includes connected nodes, including references to the user ontological object or a reference to the first semantic dictionary structure. The generated user semantic dictionary includes a semantic dictionary structure with semantic-syntactic data and an identifier of the user ontological object.

Abstract: A system for analyzing text-based information is presented. Each datum of information includes an author, a description and a timestamp. A fetcher fetches the raw information according to keywords. A parser parses the raw information to refine the results. A lexicon management module extracts lemmas from the raw information, and creates an edited lexicon containing the raw data and the lemmas for each datum. A data manager correlates lemmas in the edited lexicon and identifies clusters of lemmas that are correlated between each other. The results can be visually displayed to a user, and clusters of lemma that are less correlated than the other clusters can be visually identified. In one aspect, the user is able to excise the less correlated clusters, in order to further refine the results of the keyword search.

Abstract: The disclosed invention involves a method and systems of autonomic virtual network, which relates to three basic inventions in the area of autonomic computing: (1) systems and methods of multi-loop autonomic manager, preemptive contact point, i.e. sensors and effectors, and software-defined hardware resource, or abstraction and virtualization of the hardware functions; (2) service-delivery virtual network in the area of distributed network, and application assurance systems and methods; and (3) integration of these two fields of inventions, namely autonomic managed virtual network, such that the management of virtual networks which provide service delivery, is able to achieve n-tier architecture system and method ACRA.

Abstract: A system and method for associating a character string with one or more defined entities of a contact record. An input character string is received. The string is first evaluated to see if the structure of the string is recognized. If not, then the string is compared to entries in a look up table. If the string format is not recognized, and the string is not found in the look up table, then a posterior probability is calculated for a set of defined entities over a limited set of string processing features. The result of probabilistic scoring determines which of the defined entities to associate with the character string.

Abstract: A system and method for recommending a product to a user in response to a query for a product with a feature wherein the recommendation is accompanied by a quotation expressing a sentiment about the feature or the product.

Abstract: Techniques for graph based natural language processing are described. In one embodiment an apparatus may comprise a client service component operative on the processor circuit to receive a natural language user request from a device and to execute the natural language user request based on matched one or more objects and a social object relation component operative on the processor circuit to match the natural language user request to the one or more objects in an object graph, the object graph comprising token mappings for objects within the object graph, the token mappings based on data extracted from a plurality of interactions by a plurality of users of the network system, wherein the one or more objects are matched with the natural language user request based on the token mappings. Other embodiments are described and claimed.

Abstract: A method, system, and computer program product for generating and using a user ontological model for natural language processing of user-provided text, including receiving definitions of user ontological objects and generating user ontological models. A semantic-syntactic tree generated from user-provided text is analyzed. Information objects based on the user ontological objects are generated by the analysis.

Abstract: A natural-language processing system includes a registration-candidate storage section that stores therein registration-candidate dictionary data, a judgment means that compares input data against the registration-candidate dictionary data to thereby judge whether or not the input data includes a word corresponding to the registration-candidate dictionary data, an inquiry means that inquires to a user whether or not corresponding dictionary data is to be registered in a dictionary storage section to accept a user's instruction if it is judged that a corresponding word exists, a dictionary registration means that registers the corresponding dictionary data in the dictionary storage section based on the input instruction, and a natural-language processing means that executes a natural-language processing onto the input data by using the dictionary data registered in the dictionary storage section.

Abstract: An alert processing system and method are adapted for processing device alerts. The system includes a routing device in communication with a printer. The routing device receives at least one alert description in a source language transmitted from the printer. The routing device identifies a set of words derived from the alert description related to a condition of the associated device. The routing device compares the set of words, in a target language, to a categorization model and, based on the comparison, categorizes the set of words into to one of a predetermined set of alert categories.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for presenting a machine translation and alternative translations to a user, where a selection of any particular alternative translation results in the re-ranking of the remaining alternatives. The system then presents these re-ranked alternatives to the user, who can continue proofing the machine translation using the re-ranked alternatives or by typing an improved translation. This process continues until the user indicates that the current portion of the translation is complete, at which point the system moves to the next portion.

Abstract: Described herein are embodiments of systems, methods, apparatus and computer program products that accept student input and use a computer to process its mathematical meaning. The input can then be algorithmically tested for certain mathematical criteria. Those test results then allow the system to output immediate assessment, grades, and feedback.

Abstract: An apparatus and method for displaying on a portable terminal is provided. The apparatus includes a display unit configured to display information at a display location on a screen, a sensor configured to provide motion information of the portable terminal when the portable terminal is bent, and a controller configured to adjust the display location on the screen based on the motion information. A method comprises displaying information at a display location on a screen, providing motion information of the portable terminal when the portable terminal is bent and adjusting the display location on the screen based on the motion information provided.

Abstract: Systems and methods are provided for identifying one or more target words of a corpus that have a lexical relationship to a plurality of provided cue words. The cue words and statistical lexical information derived from a corpus of documents are analyzed to determine candidate words that have a lexical association with the cue words. The statistical information includes numerical values indicative of probabilities of word pairs appearing together as adjacent words in a well-formed text or appearing together within a paragraph of a well-formed text. For each candidate word, a statistical association score between the candidate word and each of the cue words is determined. An aggregate score for each of the candidate words is determined based on the statistical association scores. One or more of the candidate words are selected to be the one or more target words based on the aggregate scores.

Abstract: Systems, methods, and computer-readable storage media are provided for utilizing part-of-speech (POS) tagging of both the words included in a search query and the words included in potential search result documents to improve query alteration accuracy and search result ranking. Upon receiving a search query, POS tags are assigned to the words comprising the query to create query word-tag pairs. The query word-tag pairs are utilized to reformulate the query and are compared with document word-tag pairs included in a plurality of potential search result documents to determine a degree of similarity. The degree of similarity is utilized as an input in scoring and/or ranking the relevance of the potential search result documents with respect to one another.

Abstract: The translation assistance device is equipped with: a dictionary means storing dictionary data comprising terms in a specific language, and terms in another language corresponding to the terms in said specific language; a specification means specifying the selected range of a term to be searched for in a text containing the term; a search means searching for the longest full-string match corresponding to the term contained in the specified selected range using said dictionary data as the search target; and a display control means displaying the terms in the other language corresponding to the term matching in the search for the longest full-string match. The translation assistance device searches for the longest full-string match by searching the dictionary means using all characters in the selected range, and reducing the characters in the selected range one at a time from the head character if there is no match.

Abstract: A method, system, and/or computer program product uses speech traits of an entity to predict a future state of the entity. Units of speech are collected from a stream of speech that is generated by a first entity. Tokens from the stream of speech are identified, where each token identifies a particular unit of speech from the stream of speech, and where identification of the tokens is semantic-free. Nodes in a first speech graph are populated with the tokens, and a first shape of the first speech graph is identified. The first shape is matched to a second shape, where the second shape is of a second speech graph from a second entity in a known category. The first entity is assigned to the known category, and a future state of the first entity is predicted based on the first entity being assigned to the known category.

Abstract: A method for processing at least partially unstructured data is provided. The method includes receiving, at a data processing tool, at least partially unstructured data from at least one data source, and processing the at least partially unstructured data to generate at least partially structured data that includes tagged data, wherein processing the at least partially unstructured data includes at least one of processing the at least partially unstructured data using an associative memory application, and processing the at least partially unstructured data using a regular expression processing program. The method further includes transmitting the at least partially structured data to a main application, and incorporating the at least partially structured data into the main application based at least in part on the tagged data, wherein incorporating the at least partially structured data includes at least one of including and excluding data based on the existence, content and/or type of a tag.

Abstract: An information processing apparatus includes an inclusion relation memory, a correspondence relation memory, a data type identifying unit, a software application identifying unit, and a display controller. The inclusion relation memory stores inclusion relation between multiple data types. The correspondence relation memory stores correspondence relation between the data types and software applications used in input of data. The data type identifying unit analyzes acquired information to identify a data type corresponding to an input area of the acquired information. The software application identifying unit identifies a software application corresponding to each data type included in the identified data type in accordance with the inclusion relation and the correspondence relation. The display controller displays a display part in which the identified software application is used in a display.

Abstract: A computer system and methods are disclosed for automatically discovering topics and building a hierarchical topic structure, and for tagging and categorizing contents in a document or other natural language contents. The disclosed methods include steps for obtaining terms that best represent the topics in a text content, and building a hierarchical representation of topics of different levels or topic-comment relationships, and folder-subfolder structures. The methods further include obtaining, identifying, and selecting terms representing different degrees of informational importance based on the grammatical roles, parts of speech, and semantic attributes associated with the terms, using the terms to represent topics in the document, to automatically tag the document, to rank search results, and to build a category structure based on the selected terms.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for bootstrapping a language translation system. A system configured to practice the method performs a bidirectional web crawl to identify a bilingual website. The system analyzes data on the bilingual website to make a classification decision about whether the root of the bilingual website is an entry point for the bilingual website. The bilingual site can contain pairs of parallel pages. Each pair can include a first website in a first language and a second website in a second language, and a first portion of the first web page corresponds to a second portion of the second web page. Then the system analyzes the first and second web pages to identify corresponding information pairs in the first and second languages, and extracts the corresponding information pairs from the first and second web pages for use in a language translation model.

Abstract: A set of word embedding transforms are applied to transform text words of a set of documents into K-dimensional word vectors in order to generate sets or sequences of word vectors representing the documents of the set of documents. A probabilistic topic model is learned using the sets or sequences of word vectors representing the documents of the set of documents. The set of word embedding transforms are applied to transform text words of an input document into K-dimensional word vectors in order to generate a set or sequence of word vectors representing the input document. The learned probabilistic topic model is applied to assign probabilities for topics of the probabilistic topic model to the set or sequence of word vectors representing the input document. A document processing operation such as annotation, classification, or similar document retrieval may be performed using the assigned topic probabilities.

Abstract: Systems and processes for exemplar-based natural language processing are provided. In one example process, a first text phrase can be received. It can be determined whether editing the first text phrase to match a second text phrase requires one or more of inserting, deleting, and substituting a word of the first text phrase. In response to determining that editing the first text phrase to match the second text phrase requires one or more of inserting, deleting, and substituting a word of the first text phrase, one or more of an insertion cost, a deletion cost, and a substitution cost can be determined. A semantic edit distance between the first text phrase and the second text phrase in a semantic space can be determined based on one or more of the insertion cost, the deletion cost, and the substitution cost.

Abstract: Descriptions of communication interactions can be used to create a simulation of actual systems that send and receive communications including but not limited to messages complying with a protocol, events and so on. The communication interaction, event, state and state transitions of protocol or software components can be modeled to determine outcome and to validate the format and semantics of events, interaction values, etc. to identify variances against established policies or architectural guidelines.

Abstract: A method, system and computer-usable medium are disclosed for preserving conceptual distance within unstructured documents by characterizing conceptual relationships. Natural language processing is applied to content in a plurality of documents to identify topics and subjects. Analytic analysis is then applied to the identified topics and subjects to identify concepts. The content in each of the plurality of documents is partitioned into a first structured hierarchy, preserving at least one structure in each document inherent in the each document. Access is then provided to the content through a first index based upon utilizing the first structured hierarchy and through a second index utilizing a second structured hierarchy. The conceptual relationship criteria are based upon a directed graph with weights based upon a similarity and a distance based upon concepts.

Abstract: A method, system and computer-usable medium are disclosed for preserving conceptual distance within unstructured documents by characterizing conceptual relationships. Natural language processing is applied to content in a plurality of documents to identify topics and subjects. Analytic analysis is then applied to the identified topics and subjects to identify concepts. The content in each of the plurality of documents is partitioned into a first structured hierarchy, preserving at least one structure in each document inherent in the each document. Access is then provided to the content through a first index based upon utilizing the first structured hierarchy and through a second index utilizing a second structured hierarchy. The conceptual relationship criteria are based upon a directed graph with weights based upon a similarity and a distance based upon concepts.

Abstract: A method, system, and computer program product for displaying an automatically generated graphical display of a business process flow to facilitate user interaction with enterprise software applications. A compact symbolic annotation language is used in conjunction with a flow generator to automatically generate a computer renderable description of the business process flow. The method commences by defining symbols to form an alphabet to be used in the symbolic annotation language. The compact symbolic language is capable of representing rich semantics including process operations, fork operations, and join operations. Once an agent (e.g., a person, a computer agent) has captured a particular business process flow using symbols of the compact symbolic annotation language, then a computer process performs a mapping of the symbols to a markup language. The markup language can be rendered in a graphical display. The markup language can be HTML/CSS, SVG, UML, or another markup language.

Abstract: There is provided systems and method for content inversion for use in user searches and product recommendations. The methods include receiving a first content, wherein the first content includes a first sentence having at least one first sentiment expression, creating a syntactic parse tree of the first sentence, identifying a first sentiment in the at least one first sentiment expression, wherein the first sentiment corresponds to a first polarity, determining a first needs expression corresponding to the first sentiment, wherein the first needs expression includes a first subject. The method may further include creating a sub-tree corresponding to the first needs expression, and grouping the content with other content having similar sub-trees.