Abstract: A method of assigning categories to electronic messages is performed at a computing device having one or more processors and memory. The method includes receiving an electronic message and extracting one or more syntactic pairs of words from content of the electronic message. At least one of syntactic pairs includes a verb in a first sentence and an object in the same sentence, where the verb operates on the object. The method forms a feature vector based on the extracted syntactic pairs and uses the feature vector as input to a classifier. The classifier is trained on a set of training feature vectors, and each training feature vector is associated with a respective category. The method assigns a first category to the electronic message based on output of the classifier and displays the message in a group with other messages associated with the first category.

Abstract: Systems and methods of the present disclosure enable context-aware haptic error notifications. The systems and methods include a processor to receive input segments into a software application from a character input component and determine a destination. A context identification model predicts a context classification of the input segments based at least in part on the software application and the destination. Potential errors are determined in the input segments based on the context classification. An error characterization machine learning model determines an error type classification and an error severity score associated with each potential error and a haptic feedback pattern is determined for each potential error based on the error type classification and the error severity score of each potential error of the one or more potential errors. And a haptic event latency is determined based on the error type classification and the error severity score of each potential error.

Abstract: An apparatus estimates, based on an input from a user to an interaction performed during a conversation between the user and the apparatus, an interest degree indicating a degree of interest of the user in a first topic included in the interaction, and estimates, based on the input from the user to the interaction, acceptability of the interaction by the user. The apparatus selects, in accordance with the interest degree and the acceptability, as an operation mode for performing the interaction, one of a first mode of leaving an interaction initiative to the user and a second mode in which the interaction proceeds under an initiative of a system for a specific topic. The apparatus generates interaction data according to the selected operation mode, and causes an output device to output the generated interaction data.

Abstract: A messaging server employs a chat agent for gather and transmitting abbreviations and definitions via a messaging application. In this application, abbreviations include acronyms, shortened phrases, and colloquial terms or language. Definitions describe an abbreviation and may include textual information and contextual media. The chat agent may receive an abbreviation and definition from a user or may automatically determine the abbreviation and definition from messages on the messaging application. The chat agent transmits the definition and abbreviation to an approval system, which verifies the definition. Once approved, the abbreviation database stores the abbreviation and definition. When another user requests the definition for an abbreviation, the chat agent queries abbreviation database and returns the definition in a message to the user via the messaging application.

Abstract: This document provides systems and methods for altering text presentation to increase reading accuracy, efficiency, and retention. This can include identification text specific attributes from machine readable text (through parsing of the text), varying the text presentation in accordance with the attributes, and creating an enhanced visual product for enhancing the reading experience. For example, a computer system can extract attributes such as parts of speech from an input sentence and display that sentence in cascading text segments down and across a display screen. The system can further use domain-specific dictionaries derived from domain-specific texts to identify domain-specific compound noun phrases and verb phrases that require specific linguistic tagging to be usable in other linguistic analysis steps.

Abstract: Techniques for generating unregistered internet domain names using machine learning are presented. The techniques include parsing terms in an embedding training corpus of computer-readable text produce a tokenized embedding training corpus of text; adding tag(s) to produce a tagged tokenized embedding training corpus of text; vectorizing to produce a vector space embedding model mapping tagged tokenized terms to vectors; parsing domain names of a domain name training corpus of registered domain names to obtain a tokenized domain name training corpus; adding at least one tag to tokens to obtain a tagged tokenized domain name training corpus; vectorizing using the vector space model to produce a vectorized domain name training corpus; training a machine learning algorithm with the vectorized domain name training corpus to produce a trained machine learning model; generating an output domain name by the trained machine learning model; and outputting the output domain name.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: determining a category of a domain having content documents and gathering search terms frequently used in similar domains associated with the category. A ground truth table has domain search results as discovered from searches by use of the search terms from the similar domains. Ground truths are utilized in later searches for optimal search results.

Abstract: Systems and processes for accelerating task performance are provided. An example method includes, at an electronic device including a display and one or more input devices, displaying, on the display, a user interface including a suggestion affordance associated with a task, detecting, via the one or more input devices, a first user input corresponding to a selection of the suggestion affordance, in response to detecting the first user input: in accordance with a determination that the task is a task of a first type, performing the task, and in accordance with a determination that the task is a task of a second type different than the first type, displaying a confirmation interface including a confirmation affordance.

Abstract: Provided are a computer program product, system, and method for generating a plurality of document plans to generate questions from source text. The declarative source text is processed to generate a plurality of document plan data structures. To generate each document plan data structure, at least a portion of the declarative source text is included in the document plan data structure. A determination is made of at least one relation of arguments in the declarative source text. The determined at least one relation and the arguments are indicated in the document plan data structure. Entity types of the arguments are determined and indicated in the document plan data structure. A natural language generation module processes each of the document plan data structures to generate a plurality of questions, which are stored with the declarative source text.

Abstract: The present disclosure provides for augmenting a presentation document to auto-cite references to material present in non-displayed parts of the presentation document identified via natural language processing (NLP) via displaying, in a graphical user interface (GUI), a given zone of a plurality of zones included in a presentation document; identifying, in an utterance received while the given zone is displayed in the GUI, a given key concept; identifying, via a content association map associated with the presentation document that identifies key concepts recited in the presentation document and which zones of the plurality of zones the key concepts appear in, a different zone of the plurality of zones that is not currently displayed in the GUI but in which the given key concept appears; and displaying, in the GUI concurrently with display of the given zone, a visual indicator related to the different zone.

Abstract: Systems, computer-implemented methods and/or computer program products that facilitate answering questions that involve mathematical computations are provided. In one embodiment, a computer-implemented method comprises: transforming, by a system operatively coupled to a processor, a natural language query into a first logical representation and extrinsic knowledge into a second logical representation relevant to the natural language query; merging, by the system, the first logical representation and the second logical representation into a third logical representation; and generating, by the system, answers for the natural language query based on processing of the third logical representation.

Abstract: A computer implemented method is used for changing a password in a multi-domain environment. The method includes obtaining a private key and a public key from a security card at a user device in a user domain, transferring the public key to a controller in a secure domain, requesting a password change, receiving a public key encrypted new password from the secure domain, and decrypting the new password using the private key.

Abstract: A method for electronically utilizing content in a communication between a customer and a customer representative is provided. An audible conversation between a customer and a service representative is captured. At least a portion of the audible conversation is converted into computer searchable data. The computer searchable data is analyzed during the audible conversation to identify relevant meta tags previously stored in a data repository or generated during the audible conversation. Each meta tag is associated with the customer. Each meta tag provides a contextual item determined from at least a portion of one of a current or previous conversation with the customer. A meta tag determined to be relevant to the current conversation between the service representative and the customer is displayed in real time to the service representative currently conversing with the customer.

Abstract: Provided is a computer implemented method for suggesting one or more candidate words from a list of words based on an input string received at an electronic device. Preferably, the list of words comprises an ordered list of words. The method comprises a first step of providing an array in memory for receiving edit distance values between initial substrings of the input string and initial substrings of each word in a set of some or all of the words in the list of words. The method includes applying an edit distance algorithm comparing a selected word to a received input string in order to obtain the aforementioned edit distance values. The selected word may comprise an empty string of no characters.

Abstract: Methods and apparatus for detecting abusive language are disclosed. In one embodiment, a set of character N-grams is ascertained for a set of text. Feature values for a plurality of features of the set of text are determined, based, at least in part, on the set of character N-grams. A computer-generated model is applied to the feature values for the plurality of features to generate a score for the set of text, where the model includes a plurality of weights, each of the weights corresponding to one of the features. It may then be determined whether the set of text includes abusive language based, at least in part, on the score.

Abstract: System and method for automatic entity relationship (ER) model generation for services as software is disclosed. ER model generation by automated knowledge acquisition is disclosed, and automation of knowledge generation process is disclosed. Information extraction process is automated and multilevel validation of information extraction process is provided. System comprises training module to train information extraction model, and knowledge generation module for population of ER model. Standard Operators are generated based on the ER model so generated (populated). Context aware entity extraction is implemented for the ER model generation. System and method leverages existing ER model to make the system self-learning and intelligent, and provides common platform for knowledge generation from different data sources comprising documents, database, website, web corpus, and blog.

Abstract: In one embodiment, a method for searching for drawings found in a set of patent-related documents includes receiving a search query, and searching a parts index for part names matching one or more terms in the search query. The method further includes displaying one or more drawings, wherein the one or more drawings include at least one part name within the search query and the part name is stored within the parts index. In another embodiment, a method for searching for drawings includes receiving a request to search for drawings relating to a select drawing of a patent-related document, extracting parts information from the select drawing, and comparing the extracted parts information with parts information stored in a parts index. The method further includes determining that one or more drawings are similar to the select drawing, and displaying the one or more drawings.

Abstract: A method and system for searching encrypted data using wildcard keywords. The method includes: obtaining, by a first computing device, a keyword for data to be encrypted, where the keyword has a fixed length; generating a sequence of primes; determining corresponding one prime from the sequence of primes for each character of the keyword; and defining a product of the corresponding primes of the characters of the keyword as index of the encrypted data, where the index can be searched using a wildcard search keyword.

Abstract: Systems and methods for improved conversation translation are disclosed. The system receives a first portion of a conversation in a first language. The system translates the first portion of the conversation to a second language. The system generates a predicted second portion of the conversation. The first portion and the predicted second portion are sent to a second user device as a predictive translation. The system then receives an actual second portion of the conversation, translates it to the second language, and sends the first portion and the actual second portion to the second user device as a batch translation. The system compares the batch translation to the predictive translation to identity any differences and generates a color-coded translation highlighting any differences between the batch translation and the predictive translation. The system sends the color-coded translation to the second user device for display on the second user device.

Abstract: A signal processing terminal is provided that includes a signal transmission circuit and a processor. The signal transmission circuit is configured to receive a first electrical signal and a second electrical signal respectively from a first communication terminal and a second communication terminal, and to attach a first user identification header to the first electrical signal and attach a second user identification header to the second electrical signal. The processor is electrically coupled to the signal transmission circuit, and configured to process the first and second electrical signals according to the first and second user identification headers in sequence within a bus, and to generate and transmit a first and a second processed results back to the signal transmission circuit.

Abstract: A server system includes: a related word storage unit that stores information representing a relation between a plurality of registered words; a content storage unit that stores information about a content corresponding to any one of the plurality of words; a communication unit that acquires an input word; a related word search unit that searches for a related word, which is related to the acquired input word, by using the related word storage unit; and a content determination unit that provides a user with any of information about a content corresponding to the input word and information about a content corresponding to the related word.

Abstract: Systems, devices, and methods of the present invention calculate a rhetorical relationship between one or more sentences. In an example, a computer-implemented method accesses a sentence comprising a plurality of fragments. At least one fragment includes a verb and a words. Each word includes a role of the words within the fragment. Each fragment is an elementary discourse unit. The method generates a discourse tree that represents rhetorical relationships between the sentence fragments. The discourse tree includes nodes including nonterminal and terminal nodes, each nonterminal node representing a rhetorical relationship between two of the sentence fragments, and each terminal node of the nodes of the discourse tree is associated with one of the sentence fragments. The method matches each fragment that has a verb to a verb signature, thereby creating communicative discourse tree.

Abstract: Systems and methods including one or more processing modules and one or more non-transitory storage modules storing computing instructions configured to run on the one or more processing modules and perform acts of receiving a plurality of normalization rules, using the plurality of normalization rules and a multi-class classification algorithm to train a classification model for one or more product attributes of a plurality of products, determining additional normalization rules for transforming additional structured values to additional final normalized values based on a classification of un-normalized additional raw source values with the classification model, validating the additional normalization rules, and adding the additional normalization rules to the classification model if the additional normalization rules are validated.

Abstract: A data processing system analyzes a corpus of conversation data received at an interactive conversation service to train a response recommendation model. The response recommendation model generates response vectors based on custom responses and using the trained model and generates a context vector based on received input at the interactive conversation service. The context vector is compared to the set of response vectors to identify a set of recommended responses, which are recommended to an agent conversing with a user using the interactive conversation service.

Abstract: Systems, devices, and methods of the present invention detect affective argumentation in text. In an example, an application executing on a computing device accesses text comprising fragments. The application creates a discourse tree from the text. The discourse tree includes nodes, each nonterminal node representing a rhetorical relationship between two of the fragments and each terminal node of the nodes of the discourse tree is associated with one of the fragments. The application matches each fragment that has a verb to a verb signature, thereby creating a communicative discourse tree. The application determines whether the communicative discourse tree represents text that includes affective argumentation by applying a classification model trained to detect affective argumentation to the communicative discourse tree.

Abstract: In particular embodiments, in response a data subject submitting a request to delete their personal data from an organization's systems, the system may: (1) automatically determine where the data subject's personal data is stored; (2) in response to determining the location of the data (which may be on multiple computing systems), automatically facilitate the deletion of the data subject's personal data from the various systems; and (3) determine a cause of the request to identify one or more processing activities or other sources that result in a high number of such requests.

Abstract: In an approach to content selection, one or more computer processors receive a first query from a user. The one or more computer processors retrieve a first response for the first query. The one or more computer processors determine whether the first response exceeds a threshold for a policy for content usage associated with the first response, wherein the policy for content usage specifies one or more restrictions for usage of a content asset. In response to determining the first response exceeds the threshold for the policy for content usage, the one or more computer processors select a first subset of the first response to meet the threshold for the policy for content usage. The one or more computer processors send the first subset of the first response to the user.

Abstract: A machine-readable medium that gathers a plurality of key terms is described. In an exemplary embodiment, the machine-readable medium receives a plurality of terms and selects a plurality of key terms from the plurality of terms, wherein each of the plurality of key terms is a term that is highlighted in a running application. The machine-readable medium further associates a predictive search query for each of the plurality of key terms, wherein the predictive search query is executed when that term is found in a running application and the user selects this term in the running application. The machine-readable medium additionally sends the plurality of key terms to a plurality of devices, wherein each of the plurality of devices matches at least one of the plurality of key terms in that device.

Abstract: An electronic device is provided. The electronic apparatus includes a communicator; a storage configured to store a channel map including a channel name, and a broadcasting frequency and a channel number corresponding to the channel name; and a processor to extract a first keyword from a first voice command and search the channel map for the first keyword, store the first keyword, extract a second keyword from a second voice command within a predetermined period of time of the first voice command, and search the channel map for the second keyword in response to the first keyword not being found in the channel map, and generate a control command to select a channel number corresponding to the second keyword in the channel map and add the first keyword as a pseudo channel name for the selected channel number in response to the second keyword being found in the channel map.

Abstract: Systems, devices, and methods of the present invention validate argumentation in text. In an example, an application forms a communicative discourse tree from a subset of text by matching each fragment of the subset that has a verb to a verb signature. The application identifies that the subset includes an argument by applying a classification model trained to detect argumentation to the communicative discourse tree. The application further creates a logic system based on a claim of the argument, a domain definition clause associated with a domain of the text, a set of defeasible rules based on the communicative discourse tree, and a set of facts from one or more of the communicative actions of the communicative discourse tree. The application evaluates a consistency of the argument with respect to itself and with respect to the domain definition clauses by solving the logic system, thereby validating a claim associated with the argument.

Abstract: To assign an appropriate pronunciation to a word or phrase having a unique pronunciation or a word or phrase having a pronunciation incorrectly used by a user, a terminal device divides a first word or phrase indicated by a first recognition result acquired from a speech recognition server into morphemes and assigns a pronunciation to each of the morphemes, and divides a second word or phrase indicated by a second recognition result acquired from a speech recognition module into morphemes. Further, the terminal device selects, for a morpheme having the same character string as that of any one of the morphemes forming the second word or phrase among the morphemes forming the first word or phrase, a pronunciation of the morpheme indicated by the second recognition result.

Abstract: A mobile device is provided. The mobile device may include a communication interface; a display; a memory configured to store one or more instructions; and at least one processor configured to execute the one or more instructions stored in the memory to: control the communication interface to communicate with an image display apparatus; control a viewpoint of a 360-degree image based on an input; and control the communication interface to transmit, to the image display apparatus, at least one among an image corresponding to the viewpoint of the 360-degree image, and viewpoint control information corresponding to the viewpoint of the 360-degree image.

Abstract: An antecedent determining method is performed by at least one processor, and includes obtaining statement information, and determining whether a pronoun exists in the statement information. The method further includes extracting candidate antecedents and lexical features of the candidate antecedents, from the statement information, in response to the pronoun being found in the statement information, and determining, based on the lexical features of the candidate antecedents, a target antecedent that is referred to by the pronoun, among the candidate antecedents.

Abstract: A cascaded finite-state-transducer array includes a plurality of finite-state-transducers, the finite-state-transducers being distributed in space. The finite-state-transducer array is configured with dedicated data transfer channels between the finite-state-transducers to transfer specific data types. Each data stream on a dedicated data transfer channel may transmit a particular data type, which may be sorted in increasing order of start offsets or token IDs.

Abstract: Systems and methods for constructing an artificially diverse corpus of training data includes evaluating a corpus of utterance-based training data samples, identifying a slot replacement candidate; deriving distinct skeleton utterances that include the slot replacement candidate, wherein deriving the distinct skeleton utterances includes replacing slots of each of the plurality of distinct utterance training samples with one of a special token and proper slot classification labels; selecting a subset of the distinct skeleton utterances; converting each of the distinct skeleton utterances of the subset back to distinct utterance training samples while still maintaining the special token at a position of the slot replacement candidate; altering a percentage of the distinct utterance training samples with a distinct randomly-generated slot token value at the position of the slot replacement candidate; and constructing the artificially diverse corpus of training samples based on a collection of the percentage of

Abstract: Systems, devices, and methods of the present invention calculate a rhetorical relationship between one or more sentences. In an example, a computer-implemented method accesses a sentence comprising a plurality of fragments. At least one fragment includes a verb and a words. Each word includes a role of the words within the fragment. Each fragment is an elementary discourse unit. The method generates a discourse tree that represents rhetorical relationships between the sentence fragments. The discourse tree includes nodes including nonterminal and terminal nodes, each nonterminal node representing a rhetorical relationship between two of the sentence fragments, and each terminal node of the nodes of the discourse tree is associated with one of the sentence fragments. The method matches each fragment that has a verb to a verb signature, thereby creating communicative discourse tree.

Abstract: A natural language processing system has a hierarchy of user intents related to a domain of interest, the hierarchy having specific intents corresponding to leaf nodes of the hierarchy, and more general intents corresponding to ancestor nodes of the leaf nodes. The system also has a trained understanding model that can classify natural language utterances according to user intent. When the understanding model cannot determine with sufficient confidence that a natural language utterance corresponds to one of the specific intents, the natural language processing system traverses the hierarchy of intents to find a more general user intent that is related to the most applicable specific intent of the utterance and for which there is sufficient confidence. The general intent can then be used to prompt the user with questions applicable to the general intent to obtain the missing information needed for a specific intent.

Abstract: A computing system comprises, in one example, a display system, a portal hierarchy model have a plurality of nodes arranged in hierarchical parent/child relationships, each node representing a set of one or more portals and having associated portal configuration data, and a portal rendering system configured to detect a user request to render content in a given one of the portals and to obtain a set of portal configuration data for the given portal by identifying a first node in the portal hierarchy model that represents the given portal and traversing the portal hierarchy model from the first node to a second node that is a parent of the first node. The computing system also includes a display system controller configured to control the display system to generate portal user interface displays based on the set of portal configuration data.

Abstract: Apparatus, systems, devices, other articles of manufacture and associated methods are disclosed and described herein to process medical data to generate a classification of the medical data using artificial intelligence. An example apparatus includes a processor to execute instructions to implement a history of past illness (HPI) receiver to receive an HPI formatted as a string, the string including one or more words, the words organized in sentences, a natural language processor to tokenize the one or more words into tokens based on a context associated with at least one of the one or more words and a tensor generator to convert the tokens into hashes, each of the hashes forming a dimension of a tensor based on the context. The apparatus further includes a neural network to embed each of the hashes into vectors, process the vectors to classify the HPI as extended or brief based on a similarity to a set of classified HPIs and output a classification for the HPI.

Abstract: Performance sensitive selection of audio signal data is disclosed. A first rank value for the processed audio signal data can be based on a level of fidelity to an input audio signal. A second rank value for the processed audio signal data can be based on a performance metric of a processing scheme for processing the input audio signal into the processed audio signal. A third rank for the processed audio signal data can be based on an indication of a level of satisfaction for performance of the processed audio signal by a receiving device. A fourth rank for the processed audio signal data can be based on a network condition for a network conveying the processed audio signal to a device for performing the processed audio signal. Selection of the processed audio signal data can be based on the first, second, third, fourth rank, or combinations thereof.

Abstract: A method includes performing, at a device, an analysis of a domain-specific corpus to identify a base term and a modifier term. The modifier term modifies the base term in at least a portion of the domain-specific corpus. The method also includes accessing, by the device, a first entry in lexicon data. The first entry includes core data corresponding to domain-independent lexical information for the base term. The method further includes adding, based on the analysis, non-core data to the first entry. The non-core data corresponds to domain-specific lexical information for the base term. The non-core data identifies the modifier term as a domain-specific modifier of the base term.

Abstract: A computer program product for domain-specific data generation. The computer program product including a computer-readable storage medium having program instructions embodied therewith. The program instructions executable by a processor to cause the processor to perform operations including performing an analysis on a domain-specific corpus to identify a base term and a modifier term. The modifier term modifies the base term in at least a portion of the domain-specific corpus. The operations also include accessing a first entry in lexicon data. The first entry including core data corresponding to domain-independent lexical information for the base term. The operations further include adding, based on the analysis, non-core data to the first entry, the non-core data corresponding to domain-specific lexical information for the base term, wherein the non-core data identifies the modifier term as a domain-specific modifier of the base term.

Abstract: System for obtaining and analyzing data on online user behavior and other activity having regard to Internet connectable user devices, optionally mobile devices, the system being configured to collect data from a plurality of data sources, wherein the collected data includes at least individual user-level data acquired from user devices and census-level data indicating behavior and demographic characteristics across the entire population of users, active or measured services, with the user-level data being preferably collected using at least one user research panel of controlled constitution, preferably from multiple devices of each participant in the panel, the collected data being indicative of Internet, content, media, application, and/or device usage, organize the obtained user-level and census-level data into a multivalent categorized data set utilizing an ontological metadata schema, determine an electronic deliverable based on an integration of the user-level data and census-level data wherein census-l

Abstract: A mechanism is provided in a data processing system comprising at least one processor and at least one memory, the at least one memory comprising instructions executed by the at least one processor to cause the at least one processor to implement an automated lexicon expansion for an identified corpus. For a selected corpus in a set of corpora, the mechanism determines an estimated number of new terms in the selected corpus that are not in the lexicon based on a frequency count known terms in the selected corpus. Responsive to the estimated number of new terms in the selected corpus being greater than a threshold, the mechanism performs lexicon expansion using the selected corpus to form an expanded lexicon. Responsive to the estimated number of new terms in the selected corpus not being greater than the threshold, the mechanism halts lexicon expansion.

Abstract: Structured exploration of available data provides insight allowing early detection/analysis of emerging issues. An in-memory database engine applies specialized information sources and filter criteria to an original data set to successively produce various exploration levels. Evidence relating to a particular exploration level (e.g., resulting data subset, metadata indicating chains of information sources/filter criteria) are stored at the user's instruction within an evidence package of the in-memory database. Information sources may be licensed from third parties, and may be present in the in-memory database. To improve computer performance, embodiments may delete results of previous exploration levels outside of the evidence package. Evidence from the evidence package may be displayed to afford insight into relationships between data subsets and an emerging issue. One structured exploration references a source of geographic information (e.g.

Abstract: Systems, computer-program products and methods for annotating electronic text documents with multiple entities defined in a controlled vocabulary extracted from a compound noun phrase are disclosed. In one embodiment, a method of annotating an electronic text document includes searching, by a computing device, the electronic text document for instances of congruent compound noun phrases including a head and a modifier. If a congruent compound noun phrase is found, the method further includes determining a preceding word that precedes the modifier of the congruent compound noun phrase, and searching a controlled vocabulary for a second full term having the preceding word and the head of the congruent compound noun phrase. If the second full term is found in the controlled vocabulary, the method further includes annotating the electronic text document with the second full term having the preceding word and the head of the congruent compound noun phrase.

Abstract: Systems for inputting text into an electronic device are provided. The systems are configured to receive a sequence of characters input into the device. The systems comprise a means configured to generate from the sequence of characters a sequence of word-segments. The systems also comprise a text prediction engine comprising a language model having stored sequences of word-segments. The text prediction engine is configured to receive the sequence of word-segments. In a first embodiment, the text prediction engine is configured to determine whether each word-segment of the sequence of word-segments corresponds to a stored word-segment of the language model and output the sequence of word-segments as a candidate prediction when each of the word-segments of the sequence of word-segments corresponds to a stored word-segment of the language model, regardless of whether the sequence of word-segments corresponds to a stored sequence of word-segments. Various other systems and corresponding methods are provided.

Abstract: Example aspects of the present disclosure are directed to processing voice commands or utterances. For instance, data indicative of a voice utterance can be received. A device topology representation can be accessed. The device topology representation can define a plurality of smart devices associated with one or more structures. The device topology representation can further define a location of each of the plurality of devices within the associated structures. A transcription of the voice utterance can be determined based at least in part on the device topology representation. One or more selected devices and one or more actions to be performed by the one or more selected devices can be determined based at least in part on the determined transcription and the device topology representation.

Abstract: The language analysis method includes collecting an online document, performing coined word filtering on the collected document based on a predetermined coined word extraction pattern and a dictionary to extract a coined word candidate which corresponds to the coined word extraction pattern and is not registered in a coined stop word dictionary, performing morpheme analysis on the extracted coined word candidate to verify a coined word candidate which does not correspond to a predetermined part of speech and is not registered in a pre-stored morpheme dictionary, refining the coined word extraction pattern, based on a result of the verification and updating the verified coined word candidate in the coined stop word dictionary, and updating the verified coined word candidate in the morpheme dictionary, based on the result of the verification.

Abstract: Systems and methods of automated ontology development include a corpus of communication data. The corpus of communication data includes communication data from a plurality of interactions and is processed. A plurality of terms are extracted from the corpus. Each term of the plurality is a plurality of words that identify a single concept within the corpus. An ontology is automatedly generated from the extracted terms.