Abstract: The present disclosure provides a method, apparatus, electronic device and readable storage medium for translation and relates to translation technologies. In the embodiments of the present disclosure, the at least one knowledge element is obtained according to associated information of content to be translated, and respective knowledge element in the at least one knowledge element comprise an element of the first language type and an element of the second language type so that the at least one knowledge element can be used to obtain a translation result of the content to be translated. Since the at least one knowledge element obtained in advance is taken as global information of the translation task of this time, it can be ensured that the translation result of the same content to be translated is consistent, thereby improving the quality of the translation result.

Abstract: An audio system for user hearing assessment includes one or more audio capture devices, and processing circuitry. The one or more audio capture devices are configured to capture audio of a conversation of a user and convert the audio to audio signals. The processing circuitry is configured to use the audio signals to identify multiple conditions associated with user hearing difficulty. The conditions include any of words, phrases, frequencies, or phonemes, and environmental audio conditions that are followed by an indication of user hearing difficulty. The processing circuitry is configured to generate a hearing profile for the user based on the identified conditions associated with user hearing difficulty. The processing circuitry is configured to adjust an operation of an audio output device using the hearing profile to reduce a frequency of user hearing difficulty if the user requires audio enhancement.

Abstract: The present disclosure is generally directed to the generation of domain-specific, voice-activated systems in interconnected networks. The system can receive input signals that are detected at a client device. The input signals can be voice-based input signals, text-based input signals, image-based input signals, or other type of input signals. Based on the input signals, the system can select domain-specific knowledge graphs and generate responses based on the selected knowledge graph.

Abstract: Devices, systems, and methods for improving results returned from a query. A method can include identify, based on a term embedding of a corpus of terms, expansion terms of a raw query term that are nearest the raw query term, normalize distances between the raw query term and the identified expansion terms, identify, based on the term embedding, expansion term neighbors of an expansion term that are nearest the expansion term; normalize distances between the expansion term and the identified expansion term neighbors, determine a WMA weight between the raw query term and the expansion term, and execute the query with the raw query terms and the expansion terms (determined based on the WMA weight) to generate query results.

Abstract: Systems, devices, and methods of the present invention detect rhetoric agreement between texts. In an example, a rhetoric agreement application accesses a multi-part initial query and generates a question communicative discourse tree that represents rhetorical relationships between fragments of the query. The application identifies a sub-discourse tree from the question communicative discourse tree. The application generates a candidate answer communicative discourse tree for each candidate answer of a set of candidate answers. The application computes a level of complementarity between the sub-discourse tree and each candidate answer discourse tree by applying a classification model to the sub-discourse tree and candidate answer communicative discourse trees. The application selects an answer from the candidate answers based on the computed complementarity, thereby building a dialogue structure of an interactive session.

Abstract: Techniques are presented for applying fine-grained client-specific rules to divide (e.g., chunk) data statements to achieve cost reduction and/or failure rate reduction associated with executing the data statements over a subject dataset. Data statements for the subject dataset are received from a client. Statement attributes derived from the data statements are processed with respect to fine-grained rules and/or other client-specific data to determine whether a data statement chunking scheme is to be applied to the data statements. If a data statement chunking scheme is to be applied, further analysis is performed to select a data statement chunking scheme. A set of data operations are generated based at least in part on the selected data statement chunking scheme. The data operations are issued for execution over the subject dataset. The results from the data operations are consolidated in accordance with the selected data statement chunking scheme and returned to the client.

Abstract: An intelligent user manual system for vehicles includes: a digital manual database; an input module including a voice input device which is configured to receive a voice input of the user; a recognition module communicatively connected with the input module and configured to recognize a query instruction input by the user via the input module; a processor module communicatively connected with the recognition module and the manual database and configured to perform a checking operation based on the user's query instruction that has been recognized by the recognition module; and an output module communicatively connected with the processor module and configured to output content to the user that has been obtained by the processor module.

Abstract: A system, method and program product that provides user specific text suggestions across a set of hosted applications. A disclosed method includes: initiating a session with an application hosting platform for a user using a client device, wherein the platform includes a plurality of applications; accessing a dictionary associated with the user, wherein the dictionary provides text suggestions in response to inputted keyboard data and the dictionary is applicable for the user across each of the plurality of applications; deploying a selected application from the to the user at the client device; intercepting keyboard data entered by the user within the selected application; analyzing intercepted keyboard data and generating text suggestions specific to the user using the dictionary associated with the user; and outputting text suggestions within the selected application. The text suggestions are generated independently of capabilities of deployed application and operating systems running on the client device.

Abstract: Systems, methods, and other techniques for extracting data from obituaries are provided. In some embodiments, an obituary containing a plurality of words is received. Using a machine learning model, an entity tag from a set of entity tags may be assigned to each of one or more words of the plurality of words. Each particular tag from the set of entity tags may include a relationship component and a category component. The relationship component may indicate a relationship between a particular word and the deceased individual. The category component may indicate a categorization of the particular word to a particular category from a set of categories. The extracted data may be stored in a genealogical database.

Abstract: Example implementations described herein involve extracting keywords and dependency information from a text; and generating a co-occurrence dictionary for the text, the generating the co-occurrence dictionary involving selecting ones of the keywords for inclusion in the co-occurrence dictionary based on a number of times the ones of the keywords satisfy the dependency rules; determining for the selected ones of the keywords included in the co-occurrence dictionary, surrounding words to be associated with the selected ones of the keywords in the co-occurrence dictionary based on a number of instances of co-occurrence of the surrounding words with the selected ones of the keywords; and generating weights for each of the selected ones of the keywords in the co-occurrence dictionary based on a number of the surrounding words associated with the selected ones of the keywords.

Abstract: Systems and methods for improving machine learning systems used to model topics on a plurality of calls are described herein. In an embodiment, a server computer receives plurality of digitally stored call transcripts that have been prepared from digitally recorded voice calls. The server computer uses a topic model of an artificial intelligence machine learning system, the topic model modeling words of a call as a function of one or more word distributions for each topic of a plurality of topics, to generate an output of the topic model which identifies the plurality of topics represented in the plurality of call transcripts. The server computer computes, for a particular topic of the plurality of topics a first value representing a vocabulary of the particular topic and a second value representing a consistency of the particular topic in two more call transcripts of the plurality of call transcripts which include the particular topic.

Abstract: There is a need for more effective and efficient natural language processing (NLP) solutions. This need can be addressed by, for example, solutions for performing NLP-based document prioritization by utilizing joint sentiment-topic (JST) modeling.

Abstract: Techniques for generating a multidimensional database query are disclosed. A system receives a user-supplied natural language query and performs natural language processing to extract a literal from the natural language query. The system performs a lookup of the literal in one or more dictionary data structures associated with a multidimensional database, to determine that the literal is associated with a particular dimension of multiple dimensions in the multidimensional database. The system performs a lookup of the literal and the dimension in the one or more dictionary data structures, to determine that the literal is associated with a particular member of the dimension. The system generates a multidimensional database query to satisfy the user-supplied natural language query. The multidimensional database query includes a query clause that references the particular member of the dimension.

Abstract: Methods and systems are provided for mapping clinical terminology with natural language processing. In one embodiment, an example method includes generating a word relationship graph for a plurality of mappings between a first code set and a second code set, receiving a first code of the first code set, and automatically mapping a second code of the second code set to the first code based on the word relationship graph. In this way, seemingly different code descriptions from different medical vocabularies may be automatically mapped to each other with reduced processing and reduced human intervention.

Abstract: In some embodiments, a method comprises receiving an electronic message. In response to determining that the electronic message includes an express indication from a user that a classification applies or does not apply, the method comprises identifying message attributes of the electronic message that correspond to policy attributes of a machine learning policy and determining values of the policy attributes based on the identified message attributes. The method additionally comprises providing information to a machine learning trainer adapted to train the machine learning policy based on the information. The information comprises the values of the policy attributes and information indicating the classification that applies or does not apply to the electronic message, where such information is based on the express indication that the user included in the electronic message.

Abstract: At least some embodiments are directed to a computer-implemented method that comprises receiving original input text that includes a term, comparing a definition of the term to definitions of multiple candidate replacement terms to generate a set of candidate replacement terms, and substituting each of the candidate replacement terms in the set for the term in the original input text to produce a plurality of modified input texts. The method also comprises determining the grammatical accuracy of each of the plurality of modified input texts, comparing meanings of the modified input texts to a meaning of the original input text, and modifying the set of candidate replacement terms based on the determinations of grammatical accuracy and the comparisons of the meanings. The method still further comprises ranking the modified set of candidate replacement terms using one or more criteria, and displaying the ranking on a display.

Abstract: Improved systems and methods for generating training data for classification models are disclosed. In an example, a training application accesses two fragments of text. The application represents each fragment of text as a parse thicket. The parse thickets jointly represent syntactic and discourse information. From the parse thickets, the application generalizes the text by identifying common entities or common rhetorical relations between parse thickets. The generalized text is added to a training data set, thereby increasing the coverage of the training set.

Abstract: A method includes generating a plurality of entigen groups from a plurality of phrases, where the plurality of entigen groups represents a plurality of most likely meanings for the plurality of phrases. The method further includes determining an initial interpretation of the related topic based on the plurality of most likely meanings for the plurality of phrases and generating a plurality of scores for the plurality of entigen groups based on the initial interpretation and source information of the plurality of phrases. The method further includes interpreting the plurality of scores in relation to the initial interpretation to determine a confidence level of the initial interpretation and when the confidence level of the initial interpretation compares favorably to a confidence threshold, indicating that the initial interpretation is reliable.

Abstract: Techniques are disclosed for detecting distributed incompetence in text of a conversation using communicative discourse trees and then inserting an automatic response from an autonomous agent (chatbot) or other entity. For example, a computing system generates a communicative discourse tree from utterances from multiple agents to a user. The computing system obtains a prediction of whether the text includes distributed incompetence by applying a trained predictive model to the communicative discourse tree. Based on the detection, the computing system generates an updated response to a user device.

Abstract: A system is configured to analyze a corpus of historical chat data to identify the list of “best” responses. As such, the user is not required to identify a list of canned responses for input into the system. The described system uses a context word embedding function and response word embedding function to generate context vectors and response vectors corresponding to the corpus of conversation data, and the vectors are represented by a respective context matrix and a response matrix. The system processes these matrices to generate scores for responses, clusters the responses, and identifies the responses corresponding to the best scores for each cluster.

Abstract: A pair of records is tokenized to form a normalized representation of an entity represented by each record. The tokens are correlated to a machine learning system by determining whether a learned resolution already exists for the two entities. If not, the normalized records are compared to generate a comparison measure to determine whether the records match. The normalized records can also be used to perform a web search and web search results can be normalized and used as additional records for matching. When a match is found, the records are updated to indicate that they match, and the match is provided to the machine learning system to update the learned resolutions.

Abstract: Embodiments relate to a system, program product, and method for dictionary membership management directed at identifying ambiguity in semantic resources. A dictionary of seed terms is applied to a text corpus and matching items in the corpus are identified. The linguistic properties for each matching item are characterized and a context pattern of each matching item is constructed. Each context pattern is applied to the dictionary and matching content between the seed terms and the context pattern is identified and quantified. Lexicon items from the dictionary that have anomalous behavior reflected in the quantification are identified. One or more seed words identified as having anomalous behavior are selectively removed from the dictionary.

Abstract: A monitoring platform may obtain information that identifies a product or service and may collect one or more reviews associated with the product or service from a plurality of sources, wherein each review includes respective review information. The monitoring platform may process the one or more reviews to determine respective additional review information associated with each review of the one or more reviews. The monitoring platform may select, using a machine learning model, a particular review, of the one or more reviews, based on the review information and the additional review information associated with the one or more reviews. The monitoring platform may cause display, on a display of a client device, of a prompt for a response to the particular review and may obtain the response from the client device. The monitoring platform may cause the response to be posted to a source associated with the particular review.

Abstract: Techniques for using noisy-robust discourse trees to determine a rhetorical relationship between sentences. In an example, a rhetoric classification application creates a noisy-robust communicative discourse tree. The application accesses accesses a first communicative discourse tree derived from a first sentence, a third sentence, and a fourth sentence and a second communicative discourse tree derived from a second sentence, the third sentence, and the fourth sentence. The application determines that syntactic parse trees cannot be generated for the first sentence and the second sentence. The application identifies a common rhetorical relationship between the first communicative discourse tree and the second communicative discourse tree. The application removes an elementary discourse unit that does not correspond to the common rhetorical relationship from the first communicative discourse tree and the second communicative discourse tree.

Abstract: A system for automatic prediction and generation of a Q-Code based on a text description provided in a NOTAM is provided. The present system may be utilized at a top level to generate a Q-Code from a text description or at a mid-level in the flight planning process to verify and/or confirm a human-generated Q-Code based on the text description in a NOTAM. Further, the present disclosure may allow for higher accuracy in the generation of Q-Codes thereby reducing the number of incorrect suboptimal and/or rejected flight plans produced by automatic flight planning systems.

Abstract: An abstract semantic recommending device, comprising an abstract semantic expression obtaining unit to obtain a plurality of abstract semantic expressions; a receiving unit to receive an initial request message; a word segmentation unit to perform a word segmentation process on the initial request message to obtain one or more single words; a part-of-speech tagging unit to perform a part-of-speech tagging process on at least one of the one or more single words to obtain its part-of-speech information; a wordclass determination unit to perform a wordclass determination process on at least one of the one or more single words to obtain its wordclass information; a searching unit to acquire an abstract semantic candidate set relevant to the initial request message; and a matching unit to derive one or more abstract semantic expressions by performing a matching process on the several abstract semantic expressions in the abstract semantic candidate set.

Abstract: An information processing device stores, in a keyword database, keywords extracted from speech sounds picked up by a speech-sound processing device as keywords matching keyword entries in a dictionary database of the speech-sound processing device. The information processing device receives, from the speech-sound processing device, an instruction to update the dictionary database of the speech-sound processing device, and then determines, by inference, words related to the keywords stored in the keyword database, prepares an update of the dictionary database on the basis of the keywords stored in the keyword database and the related words determined by inference, and transmits the update of the dictionary database to the speech-sound processing device.

Abstract: This disclosure relates generally to an information retrieval technology and more particularly to a creation of a taxonomy to facilitate subsequent search and retrieval of information. In one embodiment, an information retrieval device is disclosed, that comprises a processor and a memory that stores instructions, which, on execution, causes the processor to receive an input corpus. Thereafter, input document clusters are generated from top input n-grams associated with the input corpus. Further, top-ranked input n-grams are determined from the top input n-grams. Thereafter, an external corpus is identified based on the top-ranked input n-grams. An enriched corpus (external and input corpus), is clustered based on top enriched n-grams associated with the enriched corpus to generate enriched document clusters. Further, for each n-gram of the enriched corpus, corresponding n-gram clusters are determined.

Abstract: Embodiments of the present disclosure provide a method and an apparatus for translating a polysemy, and a medium. The method includes: obtaining a source language text; identifying and obtaining the polysemy from the source language text; inquiring related words corresponding to each interpretation of the polysemy; determining a target interpretation corresponding to the related words contained in the source language text; and translating the polysemy into the target interpretation.

Abstract: Disclosed is system for presenting information related to a search query, comprising: a client device configured to receive the search query; a database arrangement; an ontological databank and a server arrangement communicably coupled to the client device and the database arrangement, wherein the server arrangement is configured to: receive the search query, segment the search query into one or more query segments; identify one or more query concepts associated with one or more query segments, wherein each of the one or more query concepts are tagged with a corresponding entity class; determine a data structure for the information related to the search query based on one or more metrics of the relationships of the one or more query concepts, and render, on the client device, the information related to the search query presented in the data structure.

Abstract: The invention is a data processing method and system for suggesting insightful and surprising sentences to geoscientists from unstructured text. The data processing system makes the necessary calculations to assign a surprisingness score to detect sentences containing several signals which when combined exponentially, have tendencies to give rise to surprise. In particular, the data processing system operates on any digital unstructured text derived from academic literature, company reports, web pages and other sources. Detected sentences can be used to stimulate ideation and learning events for geoscientists in industries such as oil and gas, economic mining, space exploration and Geo-health.

Abstract: Examples described herein include systems and methods for providing user-specific previews for terms within text. An example method can include receiving tracked user behavior reflecting terms selected by a user and entered into a search. A representation of known words can be created based on the tracked user behavior. By training machine-learning models for each individual user, personalized previews can be presented when each user encounters a new body of text, such as in a webpage or email. The preview can apply to a term not previously known to the user but likely to be searched by the user, relying on content gathered from a search on a search medium that the user was likely to use. The content can be presented to the user in a graphical user interface allowing for interaction and feedback.

Abstract: A method and computer product encoding the method is available for preparing a domain or subdomain specific glossary. The method included using probabilities, word context, common terminology and different terminology to identify domain and subdomain specific language and a related glossary updated according to the method.

Abstract: Systems, apparatuses, methods, and computer program products are disclosed for processing electronic information indicative of natural language. An example method includes receiving first electronic information indicative of a sequence of words provided by a user and identifying, based on the first electronic information, a first word and a first natural language. The example method further includes receiving second electronic information indicative of an exogenous event and identifying, based on the second electronic information, the exogenous event. The example method further includes generating one or more natural language attribute data sets based on the identified first word, first language, and exogenous event. The example method further includes generating a natural language transliteration data set based on the one or more natural language attribute data sets.

Abstract: A mixing pattern system for networks is provided. One or more nodes in a network are analyzed. Grouping the one or more nodes into one or more classes within the network. A computer device analyzes one or more transactions between the one or more nodes in the network that include nodes within similar or distinct classes of the one or more nodes. A computer device identifies one or more mixing patterns associated with one or more transactions between the one or more nodes.

Abstract: A system and method for determining a sentiment, a gender and an age group of a subject in a video while the video is being played back. The video is separated into visual data and audio data, the video data is passed to a video processing pipeline and the audio data is passed to both an acoustic processing pipeline and a textual processing pipeline. The system and method performs, in parallel, a video feature extraction process in the video processing pipeline, an acoustic feature extraction process in the acoustic processing pipeline, and a textual feature extraction process in the textual processing pipeline. The system and method combines a resulting visual feature vector, acoustic feature vector, and a textual feature vector into a single feature vector, and determines the sentiment, the gender and the age group of the subject by applying the single feature vector to a machine learning model.

Abstract: An apparatus and method of identifying semantically related records, including receiving input data from an input device, splitting the input data into a plurality of clusters according to semantic relationship, each of the clusters including a plurality of source terms and a plurality of target terms, transforming each of the plurality of clusters based on the transformation which includes tokenization of the plurality of clusters, for each of the plurality of clusters that are transformed, finding relatedness scores of a plurality of semantic relatedness measures with the plurality of target terms, building a vector of similarity scores for each of the plurality of target terms, and for each of the plurality of source terms, selecting a predetermined number of the plurality of target terms according to the similarity scores.

Abstract: Present invention concerns a method of relation extraction from a text corpus, the method comprising extracting instances from the text corpus based on seeds, wherein the seeds include at least one set of template seeds and at least one set of entity seeds. The invention also pertains to related devices and methods.

Abstract: Systems and methods are provided for identifying relevant information for an entity, referred to as a seed entity. A plurality of search queries can be generated each comprising a property of a seed entity or one of the entities associated with the seed entity (seed-linked entities). Preferably, a collection of search queries includes ones representing different properties of the seed entity and properties of different seed-linked entities. Optionally, the collection of search queries is optimized to reduce search burden. Searches can then be conducted with the search queries in one or more data sources to obtain a plurality of search results, wherein each search result comprises a hit entity and one or more entities associated with the hit entity (hit-linked entity).

Abstract: A method for topic early warning includes: acquiring a self-defined keyword; calculating similarity between the self-defined keyword and each word in a corpus, and acquiring extended keywords related to the self-defined keyword from the corpus according to the similarity; selecting a target keyword from the extended keywords according to a type of the extended keywords and similarity between the extended keywords and the self-defined keyword, and adding the target keyword to a target keyword list; performing real-time monitoring according to the target keyword in the target keyword list; and performing topic early warning when it is monitored that the number of topics corresponding to the target keyword reaches a preset threshold.

Abstract: A system for determining a source and topic of content for posting in a chat group is disclosed. The system includes a memory and at least one processor. The at least one processor may be configured to perform operations including identifying a user as a source of content; identifying a topic from the content using a language analysis application; determining, from the identified topic, a particular chat group from among a set of chat groups; and posting a portion of the content as a new message from the user in a message thread for the particular chat group.

Abstract: Certain aspects of the present disclosure provide techniques for mapping natural language to stored information. The method generally includes receiving a long-tail query comprising a natural language utterance from a user of an application associated with a set of topics and providing the natural language utterance to a natural language model configured to identify nodes of a knowledge graph. The method further includes, based on output of the natural language model, identifying a node of a knowledge graph associated with the natural language utterance, wherein the output of the natural language model includes a node identifier for the node of the knowledge graph and providing the node identifier to the knowledge engine. The method further includes receiving a response associated with the node of the knowledge graph from the knowledge engine and transmitting the response to the user in response to the long-tail query.

Abstract: A method and associated system. Multiple virtual triples for an entity of multiple entities identified within a first data source are generated. Each virtual triple consists of a subject, a predicate, and an object. The subject is the entity. The predicate is a relationship between the entity and other entities identified within the first data source. The object is associated with an attribute of the entity. The subject, the predicate, and the object are each identified within the first data source. A degree of similarity between two entities of the two or more entities is identified by comparing the respective frequency metrics of the two entities. The two entities within the data structure are associated in response to a determination that an identified degree of similarity between the two entities exceeds a first predetermined threshold.

Abstract: Mechanisms are provided to perform embedding of content of a natural language document. The mechanisms receive a document data object of an electronic document and analyze a structure of the electronic document to identify one or more structural document elements that have a relationship with the document data object. A dependency data structure is generated, representing the electronic document, where edges define relationships between document elements and at least one edge represents at least one relationship between the one or more structural document elements and the document data object. The mechanisms embed the document data object based on the at least one relationship to thereby represent the document data object as a vector data structure. The mechanisms perform natural language processing on the portion of natural language content based on the vector data structure. The one or more structural document elements are non-local non-contiguous with the document data object.

Abstract: A system and method for named entity linking from the output of speech-to-text systems by using an approximate string matching that normalizes common sounds, removes ambiguities, removes silent consonants, and accounts for speech slurring for long names. Additionally, the system and method for named entity linking from the output of speech-to-text systems employs a hierarchical matching system that performs multiple attempts using various mechanisms for resolving the name, starting with a very strict mechanism, and proceeding sequentially through less strict mechanisms.

Abstract: A method for determining credibility of content in a number of documents includes: obtaining topics from each document; for each document, generating topic combinations, each topic combination being a subset of the topics of the document; for each topic combination, obtaining a summary from the corresponding document; performing a semantic similarity test on each pair of two summaries that are respectively from two documents, so as to obtain a similarity percentage between the two summaries; for a group of the topic combinations that are identical combinations of topic(s), calculating a credibility score for the group based on the similarity percentage(s) calculated for the summaries that correspond to the topic combinations in the group.

Abstract: A computer-implemented method for word meaning generation is provided. In this method, a vocabulary notebook is obtained, wherein the vocabulary notebook stores at least one existing word that has been looked up. A concerned category is then identified based on the vocabulary notebook. It will be further determined whether a new page to be displayed contains at least one new word belonging to the concerned category. And responsive to determining that the new page contains the at least one new word, a respective meaning of the at least one new word is generated.

Abstract: Provided are techniques for indexing and archiving multiple statements using a single statement dictionary in a document containing the multiple statements. A document comprising a statement dictionary and one or more statements is indexed by extracting a statement metadata corresponding to each of the one or more statements from the statement dictionary. Each statement metadata is stored in a database. In response to a search request for a statement, the statement is retrieved using the corresponding statement metadata.

Abstract: Provided are techniques for indexing and archiving multiple statements using a single statement dictionary in a document containing the multiple statements. A document comprising a statement dictionary and one or more statements is indexed by extracting a statement metadata corresponding to each of the one or more statements from the statement dictionary. Each statement metadata is stored in a database. In response to a search request for a statement, the statement is retrieved using the corresponding statement metadata.

Abstract: Techniques for document analysis using machine learning are provided. A selection of an index is received document, and a plurality of documents that refer to the index document is identified. For each respective document in the plurality of documents, a respective portion of the respective document is extracted, where the respective portion refers to the index document, and a respective vector representation is generated for the respective portion. A plurality of groupings is generated for the plurality of documents based on how each of the plurality of documents relate to the index document, by processing the vector representations using a trained classifier. Finally, at least an indication of the plurality of groupings is provided, along with the index document.