71 results about "Semantic interpretation" patented technology

Ordering recognition results produced by an automatic speech recognition (‘ASR’) engine for a multimodal application implemented with a grammar of the multimodal application in the ASR engine, with the multimodal application operating in a multimodal browser on a multimodal device supporting multiple modes of interaction including a voice mode and one or more non-voice modes, the multimodal application operatively coupled to the ASR engine through a VoiceXML interpreter, includes: receiving, in the VoiceXML interpreter from the multimodal application, a voice utterance; determining, by the VoiceXML interpreter using the ASR engine, a plurality of recognition results in dependence upon the voice utterance and the grammar; determining, by the VoiceXML interpreter according to semantic interpretation scripts of the grammar, a weight for each recognition result; and sorting, by the VoiceXML interpreter, the plurality of recognition results in dependence upon the weight for each recognition result.

A system, method and computer program product for conducting questions and answers with deferred type evaluation based on any corpus of data. The method includes processing a query including waiting until a “Type” (i.e. a descriptor) is determined AND a candidate answer is provided; the Type is not required as part of a predetermined ontology but is only a lexical / grammatical item. Then, a search is conducted to look (search) for evidence that the candidate answer has the required LAT (e.g., as determined by a matching function that can leverage a parser, a semantic interpreter and / or a simple pattern matcher). In another embodiment, it may be attempted to match the LAT to a known Ontological Type and then look for a candidate answer up in an appropriate knowledge-base, database, and the like determined by that type. Then, all the evidence from all the different ways to determine that the candidate answer has the expected lexical answer type (LAT) is combined and one or more answers are delivered to a user.

A computer-implemented method and system are provided for filling a graphic-based form field in response to a speech utterance. The computer-implemented method includes generating a grammar corresponding to the form field, the grammar being based on a user profile and comprising a semantic interpretation string. The method further includes creating an auto-fill event based upon the at least one grammar and responsive to the speech utterance, the auto-fill event causing the filling of the form field with data corresponding to the user profile. The system includes a grammar-generating module for generating a grammar corresponding to the form field, the grammar being based on a user profile and comprising a semantic interpretation string. The system also includes an event module for creating an auto-fill event based upon the at least one grammar and responsive to the speech utterance, the event causing the filling of the form field with data corresponding to the user profile.

Exemplary methods, systems, and products are disclosed for synchronizing visual and speech events in a multimodal application, including receiving from a user speech; determining a semantic interpretation of the speech; calling a global application update handler; identifying, by the global application update handler, an additional processing function in dependence upon the semantic interpretation; and executing the additional function. Typical embodiments may include updating a visual element after executing the additional function. Typical embodiments may include updating a voice form after executing the additional function. Typical embodiments also may include updating a state table after updating the voice form. Typical embodiments also may include restarting the voice form after executing the additional function.

A method, system, and computer program product for storing and managing a knowledge profile are described. The knowledge is stored in knowledge units representative of unconstrained natural language (NL). Any given knowledge unit is associatable with at least one other knowledge unit with the given knowledge unit being a context knowledge unit, and the at least one other knowledge unit being a detail knowledge unit of the associated context knowledge unit, and such that every given context knowledge unit that has at least one associated detail knowledge unit satisfies a NL relationship there-between that corresponds to one of the NL-expressible forms of the NL word "have". The profile includes a core set of knowledge units for a core vocabulary of words, at least some of which are associated with knowledge units to provide a basic meaning of the associated words. The profile further includes a core set of knowledge units for core processing and core parsing NL-expressible knowledge. The knowledge units are arranged in accordance with a predefined structure that reflects context-detail relationships and that is dynamically extensible to include other knowledge units during run-time; and the placement and relationships of knowledge units within the predefined structure further reflect semantic interpretations of the knowledge units and support algorithmic reasoning about the knowledge in the profile. In certain embodiments, the profile includes NL class structures to form knowledge units to represent NL words and phrases, and the profile includes NL word class structures to form knowledge units to represent NL words.

A system, method and computer program product for conducting questions and answers with deferred type evaluation based on any corpus of data. The method includes processing a query including waiting until a “Type” (i.e. a descriptor) is determined AND a candidate answer is provided. Then, a search is conducted to look (search) for evidence that the candidate answer has the required Lexical Answer Type (e.g., as determined by a matching function that can leverage a parser, a semantic interpreter and / or a simple pattern matcher). Prior to or during candidate answer evaluation, a process is provided for extracting and storing collections of entity-type pairs from semi-structured text documents. During QA processing and candidate answer scoring, a process is implemented to match the query LAT against the lexical type of each provided candidate answer and generate a score judging a degree of match.

A method and apparatus for capturing annotations about database material in a way that allows queries with conditions or predicates on both the database material and the annotations. Database material may be text, computer programs, graphics, audio, spreadsheets, or any other material which may be stored and indexed. Database material may be in one or multiple sources, and annotations may be stored together with the original material or in a separate store. Annotations can be used to capture information such as additional facts about the database material, the opinions and judgments of experts about the database material, and / or links to other related material. Annotations may be captured in a structured form to enhance queryability and semantic interpretation.

A method and apparatus for capturing annotations about database material in a way that allows queries with conditions or predicates on both the database material and the annotations. Database material may be text, computer programs, graphics, audio, spreadsheets, or any other material which may be stored and indexed. Database material may be in one or multiple sources, and annotations may be stored together with the original material or in a separate store. Annotations can be used to capture information such as additional facts about the database material, the opinions and judgments of experts about the database material, and / or links to other related material. Annotations may be captured in a structured form to enhance queryability and semantic interpretation.

A computer-implemented method and system are provided for filling a graphic-based form field in response to a speech utterance. The computer-implemented method includes generating a grammar corresponding to the form field, the grammar being based on a user profile and comprising a semantic interpretation string. The method further includes creating an auto-fill event based upon the at least one grammar and responsive to the speech utterance, the auto-fill event causing the filling of the form field with data corresponding to the user profile. The system includes a grammar-generating module for generating a grammar corresponding to the form field, the grammar being based on a user profile and comprising a semantic interpretation string. The system also includes an event module for creating an auto-fill event based upon the at least one grammar and responsive to the speech utterance, the event causing the filling of the form field with data corresponding to the user profile.

The invention discloses a short text topic modeling method based on word semantic similarity. The method comprises: according to word semantic similarity provided by external, establishing a similar word set of short text centralized words; determining the number of topics used in modeling; randomly distributing the topic of each short text; through a Gibbs sampling process, iteratively determining the topic of each short text and the distribution of the words in the topic; according to a final distribution result of the above variable, feeding back the word distribution under each topic and the topic associated to each short text. The method preferably solves problems of sparse information contents of short texts and unclear semantic expression. According to the model result, short texts can be preferably expressed as topic vectors, and the topic vectors are used as final feature vectors of a short essay. The topic vector-based expression has good semantic interpretability, and can be used as algorithm basis of various applications. The method can be widely applied in various short text data, and has wide actual meaning and commercial values.

A program, system and method for decoding a packed representation of multiple parses that creates an unpacked forest to be read by a semantic interpretation module from a packed representation is provided. The packaged representation includes at least one edgenode and each edgenode includes a substitution list. A current forest object is created and is replicated for each edgenode having a substitution list containing greater than one edgenode. Each replica of the current forest object is updated with one of the edgenodes from the substitution list. Each edgenode of the packed representation is traversed using a depth-first traversal.

A processing method of data transmitted from sensor nodes, including: providing a model list that stores preset model names; providing a semantic interpretation list that stores semantic information corresponding to a value of the data; providing an event table that stores monitoring conditions of values of data corresponding to the model names; receiving data corresponding to the model names from the sensor nodes; notifying an occurrence of an event when receiving data satisfying the monitoring conditions from the sensor nodes; and executing processing previously specified when an occurrence of an event is notified.

A system for deriving ontologies to support inferencing with changing context, including changes of time. Embodiment of the invention use a unique system for modeling context and the interactions among multiple contexts in order to compute functions that can modify ontologies for presentation to a reasoning system. A parallel unique system allows previous inferences to be retrospectively modified based on newly derived ontological semantics. The system allows for the creation of new ontological elements and auditable models of agency and cause. It can be implemented using methods that delay evaluation until semantic interpretation is required, either at the ontological or inferential level.

Ambiguities in a natural language expression are interpreted by jointly disambiguating multiple alternative syntactic and semantic interpretations. More than one syntactic alternative, represented by parse contexts, are analyzed together with joint analysis of referents, word senses, relation types, and layout of a semantic representation for each syntactic alternative. Best combinations of interpretations are selected from all participating parse contexts, and are used to form parse contexts for the next step in parsing.

The invention relates to a voice interaction method. The voice interaction method comprises the following steps: performing semantic interpretation operation on a received voice signal so as to acquire a control operation contained in the voice signal; judging a type of the control operation contained in the voice signal; when the type of the control operation contained in the voice signal is a selection instruction, parsing a subject term contained by the voice signal; and searching a corresponding multimedia file according to the subject term. The invention also provides an electronic device and a computer readable storage medium. According to the electronic device, the computer readable storage medium and the voice interaction method, by identifying the voice signal inputted by a user, the inconvenience caused by the control through a controller can be reduced, and the user experience can be improved.

Ambiguities in a natural language expression are interpreted by jointly disambiguating multiple alternative syntactic and semantic interpretations. More than one syntactic alternative, represented by parse contexts, are analyzed together with joint analysis of referents, word senses, relation types, and layout of a semantic representation for each syntactic alternative. Best combinations of interpretations are selected from all participating parse contexts, and are used to form parse contexts for the next step in parsing.

A framework for generating a semantic interpretation of natural language input includes an interpreter, a first set of types, and a second set of types. The interpreter is adapted to mediate between a client application and one or more analysis engines to produce interpretations of the natural language input that are valid for the client application. The first set of types is adapted to define interactions between the interpreter and the one or more analysis engines. The second set of types is adapted to define interactions between the interpreter and the client application.

The invention discloses a remote sensing object interpretation method based on a focusing weight matrix and a variable-scale semantic segmentation neural network. The remote sensing object interpretation method comprises the following steps: obtaining and preprocessing data; making a thematic map; cutting the sample; designing a multi-spatial-scale remote sensing image labeling strategy; making alabel of the sample set; constructing a multi-scale remote sensing image semantic interpretation model; selecting a training set and a verification set; setting training parameters; training model; designing based on a remote sensing object recognition algorithm of a focusing weight matrix; and verifying and analyzing the effect of the variable-scale remote sensing image semantic interpretation model. According to the invention, the LSTM is constructed, so that the relation between nouns in the obtained semantic description and an object mask graph obtained by semantic segmentation is obtained, and the spatial relationship in semantic description is transferred between the object mask graphs, so that the variable-scale semantic segmentation of the remote sensing object and the end-to-end identification of the spatial relationship are realized, and the image classification and identification work in the remote sensing application field is guided to step forward to a higher step.

A system and a method to correct semantic interpretation recognition errors presented in this invention applies to Automatic Speech Recognition systems returning recognition results with semantic interpretations. The method finds the most likely intended semantic interpretation given the recognized sequence of words and the recognized semantic interpretation. The key point is the computation of the conditional probability of the recognized sequence of words given the recognized semantic interpretation and a particular intended semantic interpretation. It is done with the use of Conditional Language Models which are Statistical Language Models trained on a corpus of utterances collected under the condition of a particular recognized semantic interpretation and a particular intended semantic interpretation. Based on these conditional probabilities and the joint probabilities of the recognized and intended semantic interpretations, new semantic interpretation confidences are computed. The semantic interpretation with the maximum new confidence is declared the corrected semantic interpretation.

The invention discloses a short text similarity computing method based on the searched result quantity, which includes the steps: 1 preprocessing short texts; 2 utilizing single short texts and combinations of each two short texts as search words and respectively submitting the search words to a large-scale corpus; and 3 computing similarity between each two short texts by the aid of the returned searched result quantity. The computing method does not depend on traditional text processing and is capable of quickly and effectively obtaining computed results. The short texts are utilized as the search words, and the large-scale corpus returns searched results including the short texts. Content of the searched results includes text interpretations on the short texts, and the searched result quantity can be regarded as a compressor and implies semantic interpretations of the short texts in the corpus.

The invention provides an entity relationship rapid extraction method based on an automaton. The entity relationship rapid extraction method comprises the following steps: step 1, customizing a rule file; step 2, performing grammar checking on each rule in the rule file, and detecting whether the rules in the rule file meet grammar requirements or not; if so, executing step 3; step 3, performing semantic interpretation on each rule in the rule file through grammar checking; step 4, analyzing and compiling each rule in the rule file subjected to the semantic interpretation to finish conversion from the rule to a stacked finite-state automaton, so as to obtain the finite-state automaton; step 5, extracting an entity attribute and an entity relationship from input text data by utilizing the finite-state automaton, so as to obtain a final entity attribute and entity relationship. The entity relationship rapid extraction method based on the automaton has the advantages that the rapid extraction of the entity attribute and the entity relationship of open domain texts can be carried out. Meanwhile, the entity relationship of a specific field can be subjected to customized extraction.

The method and system for modifications of grammars presented in this invention applies to automatic speech recognition systems which take a spoken utterance as input and use a grammar to assign word sequence(s) and, possibly, one or more semantic interpretations to that utterance. One type of modification may take a form of reducing the importance of select grammar components based on the analysis of the occurrence of these components in the original grammar. Another type of modification may take form of adding new grammar components to the grammar of some semantic interpretations based on the analysis of the occurrence of these components in the select set of other semantic interpretations. Both modifications can be carried out either automatically or offered for validation. Some benefits of the presented method and system are: reduced effort for building grammars, improvement of recognition accuracy, automatic adaptation of dynamic grammars to the context.

Disclosed herein are systems and methods for classifying unstructured datasets according to a classification system and generating an enhanced, classified and structured data-set enabling efficient supplemental computer-based processing. The exemplary computer-implemented classification algorithms involve, for each entry in the input dataset, semantically interpreting a text-based occupation description, analyzing the description according to an ontology of interrelated “concepts” and identifying semantically relevant concept(s) and any associated descriptors specific to the classification system. The system is also configured to expand the list of relevant concepts to include concepts that bear a relationship thereto, scoring the various concepts and associated descriptors and identifying the concept(s) and descriptors that most accurately correspond to the input data. Further, the system is configured to generate the new structured and classified occupation dataset by selectively combining certain input data and augmenting each entry with supplemental information inferred through the classification process.

The invention discloses a method and a system for acquiring answers of tax business questions based on semantic graphs, and belongs to the technical field of intelligent questions and answers. The method comprises the steps of defining a question Q and an answer of the question Q according to a state transition graph G, and mapping a semantic interpretation process of the question Q into a sub-graph sub-G query process of the state transition graph G; generating a logic expression; action transfer and conditions in the logic expression are repeated; and obtaining a tax business problem, inputting the tax business problem into the model, checking whether the tax business problem completes the logic expression X, and outputting a tax business problem answer when the tax business problem completes the logic expression X. The semantic parsing process is mapped into the retrieval process of the query graph, so that the retrieval space of problem parsing is reduced, the operation between entities is judged by using the deep convolutional neural network, and the predicate synonym ambiguity problem mentioned in the preamble is solved.

The invention discloses an address data matching mining platform based on the big data storage and mining technology. The address data matching mining platform is achieved through the following steps of the foundation preparation operation, wherein a segmentation library and a fragment library are built, a matching credential library is built, and an efficient index engine is built at the same time; the operation preparation, wherein operations of receiving, managing, check and the like of door address data to be matched is automatically finished; the matching operation, task packages made at the data preparation stage are processed based on a Chinese semantic interpretation technology, the data storage and mining technology and an address matching technology of non-structural data; check and verification, wherein operations of reception, check, verification, error correction, error determination and the like of the task packages to be checked are finished, after the verification operation, the task packages are submitted to an operation manager for check input storage or the task packages are submitted to operators for error elimination; finial verification input storage, wherein input storage process is conducted on the finished operations according to different content. The address data matching mining platform has the advantages of being high in automation degree, easy to operate and learn and the like.

The invention discloses an electronic medical record rapid recording system based on an incremental type term bank. The electronic medical record rapid recording system is composed of an intelligent medical input module and a term obtaining module. Medical record recording is achieved through the system, so that traditional Chinese medicine clinical terms from the real world can be applied to the traditional Chinese medicine clinical scientific research in the real world in a standardized mode, and therefore it is ensured that information can be accurately and efficiently collected in the clinical work, clinical electronic medical records which meet the quality control requirements can also be generated, meanwhile, it is ensured that new traditional Chinese medicine clinical terms are timely obtained, newly-obtained medical clinical terms are examined, uniform semantic interpretation is conducted on the authorized medical terms, and furthermore standardized application of the new terms is facilitated.

Methods, apparatus, and computer program products are described for automatic speech recognition (‘ASR’) that include accepting by the multimodal application speech input and visual input for selecting or deselecting items in a selection list, the speech input enabled by a speech recognition grammar; providing, from the multimodal application to the grammar interpreter, the speech input and the speech recognition grammar; receiving, by the multimodal application from the grammar interpreter, interpretation results including matched words from the grammar that correspond to items in the selection list and a semantic interpretation token that specifies whether to select or deselect items in the selection list; and determining, by the multimodal application in dependence upon the value of the semantic interpretation token, whether to select or deselect items in the selection list that correspond to the matched words.