Abstract: Provided are a computer program product, system, and method for classifying text to determine a goal type used to select machine learning algorithm outcomes. Natural language processing of text is performed to determine features in the text and their relationships. A classifier classifies the text based on the relationships and features to determine a goal type. The determined features and relationships from the text are inputted into a plurality of different machine learning algorithms to generate outcomes. For each of the machine learning algorithms, a determination is made of performance measurements resulting from the machine learning algorithms generating the outcomes. A determination is made of at least one machine learning algorithm having performance measurements that are highly correlated to the determined goal type. An outcome is determined from at least one of the outcomes.

Abstract: A facility for identifying multi-word expressions in a natural language sentence is described. The facility provides the sentence to each of multiple natural language processing modules including a first module, a second module, and a third module. Each natural language processing module uses a different approach to identify a multi-word expression and a type of the multi-word expression. Upon determining that the multiple identifiers of the multi-word expression differ, the facility determines the multi-word expression using a resolution process, which can involve a logical rule set or a machine learning model.

Abstract: An apparatus has a network interface circuit to receive a source sentence from a network connected client device. A processor is connected to the network interface circuit. A memory is connected to the processor. The memory stores parameters of a multilingual neural review system and instructions executed by the processor to operate the multilingual neural review system trained on a corpus of source sentences, draft target sentences and corrected target sentences. The multilingual neural review system produces a corrected target sentence from a draft target sentence representing a proposed translation of the source sentence. The draft target sentence and the corrected target sentence are supplied to the network connected client device. Approval for the corrected target sentence is received from the network connected client device. Parameters of the multilingual neural review system are updated based upon the approval for the corrected target sentence.

Abstract: An apparatus includes a text information extraction unit that extracts character information from a video including characters, a text coincidence detection unit that detects character information included in dialogue information that is data of a dialogue associated with the video data from the extracted character information, a text translation unit that translates the character information, a display position calculation unit that calculates a display position of translated text information in the video data on the basis of a text region information that indicates a region in which a video corresponding to the character information is displayed in the video data and on the basis of the translated text information, and a subtitle synthesizing unit that adds, as a subtitle, the translated text information on the basis of display position information.

Abstract: A foreign currency transaction system and method can allow both users and merchants to carry out foreign currency transactions without using a point-of-sale (POS) device. In addition, users can carry out foreign currency transactions without knowing much of a foreign language in order to engage with a merchant in a foreign country. In addition, a user may lock-in a foreign currency exchange rate so that the user is able to have some certainty in relation to the foreign currency transaction, and can simplify the use of payment cards for foreign currency transactions by capturing an electronic image of a pricing indicator at a juncture of initiating a foreign currency transaction, and processing the electronic image to automatically determine a required payment amount represented on the pricing indicator.

Abstract: A method, apparatus, and system for join operations of a plurality of relations that are distributed over a plurality of storage locations over a network of computing components.

Abstract: A system for identifying a language in audio data includes a feature extraction module for receiving an unknown input audio data stream and dividing the unknown input audio data stream into segments. A similarity module receives the segments and receives known-language audio data models for known languages. For each segment, the similarity module performs comparisons between the segment and the known-language audio data models and generates probability values representative of the probabilities that the segment includes audio data of the known languages. A processor receives the probability values for each segment and computes an entropy value for the probabilities for each segment. If the entropy value for a segment is less than the entropy value for a previous segment, the processor terminates the comparisons prior to completing comparisons for all segments.

Abstract: A method, apparatus, and system for join operations of a plurality of relations that are distributed over a plurality of storage locations over a network of computing components.

Abstract: A system for identifying a language in audio data includes a feature extraction module for receiving an unknown input audio data stream and dividing the unknown input audio data stream into segments. A similarity module receives the segments and receives known-language audio data models for known languages. For each segment, the similarity module performs comparisons between the segment and the known-language audio data models and generates probability values representative of the probabilities that the segment includes audio data of the known languages. A processor receives the probability values for each segment and computes an entropy value for the probabilities for each segment. If the entropy value for a segment is less than the entropy value for a previous segment, the processor terminates the comparisons prior to completing comparisons for all segments.

Abstract: A computer generates a plurality of encoded sentences in the first language by encoding a plurality of sentences in the first language in prescribed units. Next, the computer generates a plurality of encoded sentences in the second language by encoding a plurality of sentences in the second language, each of which is associated with each of the plurality of sentences in the first language, in the prescribed units. The computer generates alignment information based on a code included in each of the plurality of encoded sentences in the first language and a code included in an encoded sentence in the second language, which is associated with each of the plurality of encoded sentences in the first language. The alignment information indicates an alignment between a plurality of codes in the first language and a plurality of codes in the second language.

Abstract: A recommended content display method includes: receiving an operation signal directed to a target statement in a page displayed on a user interface of an application; determining an interested character sequence on the page according to the operation signal; and additionally displaying at least one group of recommended content on the user interface of the application. The interested character sequence includes the target statement and at least one of a preceding statement before the target statement or a following statement after the target statement. The recommended content is information content associated with the interested character sequence.

Abstract: A method of providing real-time translation for video chat is provided. The method includes: continuously receiving first-language voice data and at least one second-language word from a first terminal; continuously displaying the at least one second-language word at the same time as reproduction of the voice data; acquiring a second-language translation of an ended sentence included in a voice recognition result for the voice data; and substituting at least one word, which corresponds to the ended sentence in the displayed at least one second-language word, with the acquired translation. The at least one second-language word corresponds to respective words included in the voice recognition result for the voice data.

Abstract: A system and method that translates sentences of natural language text into sets of axioms of formal logic that are consistent with parses resulting from NLP and acquired constraints as they accumulate. The system and method further present these axioms so as to facilitate further disambiguation of such sentences and produces axioms of formal logic suitable for processing by automated reasoning technologies, such as first-order or description logic suitable for processing by various reasoning algorithms, such as logic programs, inference engines, theorem provers, and rule-based systems.

Abstract: An information processing apparatus includes a generation unit and an instruction unit. The generation unit generates a display image including information on speech or action of a target person, based on history information that the target person has made speech or action. The instruction unit instructs a display device, which displays an image of a virtual space so as to be superimposed in a real space, to display the generated display image as the image of the virtual space.

Abstract: A computer-implemented method and system are provided for teaching syntax for training a neural network based natural language inference model. The method includes selectively performing, by the hardware processor, person reversal on a set of hypothesis sentences, based on person reversal prevention criteria, to obtain a first training data set. The method further includes enhancing, by the hardware processor, a robustness of the neural network based natural language inference model to syntax changes by training the neural network based natural language inference model on original training data combined with the first data set.

Abstract: Systems, methods, and computer readable media related to information retrieval. Some implementations are related to training and/or using a relevance model for information retrieval. The relevance model includes an input neural network model and a subsequent content neural network model. The input neural network model and the subsequent content neural network model can be separate, but trained and/or used cooperatively. The input neural network model and the subsequent content neural network model can be “separate” in that separate inputs are applied to the neural network models, and each of the neural network models is used to generate its own feature vector based on its applied input. A comparison of the feature vectors generated based on the separate network models can then be performed, where the comparison indicates relevance of the input applied to the input neural network model to the separate input applied to the subsequent content neural network model.

Abstract: A computer-implemented method for dual sequence inference using a neural network model includes generating a codependent representation based on a first input representation of a first sequence and a second input representation of a second sequence using an encoder of the neural network model and generating an inference based on the codependent representation using a decoder of the neural network model. The neural network model includes a plurality of model parameters learned according to a machine learning process. The encoder includes a plurality of coattention layers arranged sequentially, each coattention layer being configured to receive a pair of layer input representations and generate one or more summary representations, and an output layer configured to receive the one or more summary representations from a last layer among the plurality of coattention layers and generate the codependent representation.

Abstract: An information processing apparatus includes an acquisition unit that acquires an information group in which an abbreviated name is used, a specification unit that specifies a position where the abbreviated name is used in the information group from a type of information group acquired, a first extraction unit that extracts the abbreviated name from the specified position, a second extraction unit that extracts a formal name on the basis of a character related to the information group, and an association unit that associates the abbreviated name and the formal name with each other.

Abstract: There is a need for solutions that perform preprocessing and/or searching of documents with semantic intelligence. This need can be addressed by, for example, by performing pre-processing of each document of a plurality of documents to generate an indexed representation for the document by identifying sentences in the document; determining, for each n-gram of one or more n-grams associated with the document, one or more n-gram semantic scores based semantic proximity indicators for the n-gram; determining, based at least in part on each one or more n-gram semantic scores, one or more sentence semantic labels for each sentence in the document; and determining the indexed representation for the document based at least in part on the one or more sentence semantic labels for the document; performing the search query based each indexed representation associated with a document; and transmitting the result to a computing device associated with the search query.

Abstract: Various examples are directed to systems and methods for identifying textual information regarding a first topic. A computer system may access a plurality of text units and detect that a first text unit of the plurality of text units is in a first language. The computer system may access a first language keyword set for the first topic, where the first language keyword set comprises a first plurality of keywords associated with the first language. The computer system may determine a first relevance score for the first text unit based at least in part on the first language keyword set. If the first relevance score is greater than a relevance score threshold, the computer system translates the first text unit to a base language and determines a text unit classification for the first text unit using a classification model trained with training data in the base language.

Abstract: A translation device is configured to acquire utterance spoken by a speaker in a first language and translate contents of the utterance into a second language for information presentation, and includes an input unit, a controller, a notification unit, and a storage. The input unit acquires the utterance in the first language and generates voice data from the utterance. The controller acquires a first evaluation value. The notification unit presents the speaker with information on utterance reinput request. The notification unit presents first information on utterance reinput request when the first evaluation value is less than or equal to a first predetermined value. The controller generates new voice recognition data with reference to the past voice recognition data and voice recognition data of reinput utterance, when the voice recognition data of the reinput utterance has an evaluation value less than or equal to a predetermined value.

Abstract: In accordance with some implementations of the disclosed subject matter, mechanisms for presenting recommended media content items are provided.

Abstract: Embodiments of the present invention relate to the field of terminal technologies, and provide a method and an apparatus for displaying a candidate word, and a graphical user interface to improve efficiency of a user in entering information by using an input method. The method is applied to a scenario in which a user enters information by using an input method. The method includes: determining a type of an application that invokes the input method; determining, according to the type, dimension information corresponding to the type; determining, according to the dimension information, a lexicon corresponding to the dimension information; and displaying, in a default candidate option area of the input method, at least one candidate word that is in the lexicon and meets a preset condition.

Abstract: A system for text summarization includes an encoder for encoding input tokens of a document and a decoder for emitting summary tokens which summarize the document based on the encoded input tokens. At each iteration the decoder generates attention scores between a current hidden state of the decoder and previous hidden states of the decoder, generates a current decoder context from the attention scores and the previous hidden states of the decoder, and selects a next summary token based on the current decoder context. The selection of the next summary token prevents emission of repeated summary phrases in a summary of the document.

Abstract: A processor may generate initial subspaces by reducing data of a plurality of domains to a same dimensionality, cluster data within each initial subspace into clusters, create an input data matrix by projecting data from each cluster to an associated one of a plurality of generative subspaces associated with the plurality of clusters, perform a parallel transport between first and second sets of generative subspaces to identify a set of directions between pairs of subspaces of the first and second sets, sample points comprising a plurality of intermediate representations along the directions via an exponential mapping, create an expanded set of prior information by projecting the data from the first and second sets to the plurality of intermediate representations, perform a sparse coding with the input data matrix and the expanded set of prior information, and perform a cross domain inference using the output of the sparse coding.

Abstract: A translation device includes an input unit and a controller. The input unit obtains first text data in a first language. The controller generates second text data in a second language that is a translation of the first text data. The controller further generates first replacement data by replacing a first term, of a predetermined type, contained in the first text data by a parameter, obtains second replacement data, in the second language, corresponding to the first replacement data, and generates the second text data by replacing the parameter contained in the second replacement data by a second term in the second language that is a translation of the first term.

Abstract: The disclosed technology provides computer-to-wireless-voice integration methods and systems. In some implementations, the methods and systems deliver real-time voice instructions to users of required time-sensitive actions and ensure that such directives are received and a recipient effectively acts on the directives. The systems and methods include receiving a notification of an event from a terminal in a wireless active voice engine (WAVE) system, determining an active voice directive corresponding to the event with a WAVE module, converting the active voice directive into a voice event via a directive converter, and notifying a targeted recipient of the active voice directive corresponding to the event with a communications module. In some implementations, the systems and methods include sending a confirmation event via the receiver to the communications module that the active voice directive was received by the targeted recipient and communicating the active voice directive has been completed.

Abstract: At least one processing device, operating upon a body of text in a document, identifies occurrences of at least one content type in the body of text. The at least one processing device thereafter generates a user interface that includes portions of text from the body of text that are representative of at least some of the occurrences of the at least one content type in the document. For each content type, the occurrences corresponding to that content type can be grouped together to provide grouped content type occurrences that are subsequently collocated in the user interface. Those portions of text corresponding to the grouped content type occurrences may be arranged in alphanumeric order. The user interface may comprise at least a portion of the body of text as well as indicia indicating instances of the occurrences within the portion of the body of text.

Abstract: Improvements in speech recognition in a new domain are provided via the student/teacher training of models for different speech domains. A student model for a new domain is created based on the teacher model trained in an existing domain. The student model is trained in parallel to the operation of the teacher model, with inputs in the new and existing domains respectfully, to develop a neural network that is adapted to recognize speech in the new domain. The data in the new domain may exclude transcription labels but rather are parallelized with the data analyzed in the existing domain analyzed by the teacher model. The outputs from the teacher model are compared with the outputs of the student model and the differences are used to adjust the parameters of the student model to better recognize speech in the second domain.

Abstract: Hybrid classification system and method are described. The method commences when an input detector detects a raw input string that represents a value of a category in a member profile maintained by the on-line social network. The machine learning classifier derives a standardized value corresponding to the raw input string. The trigger module provides the raw input string to the correcting filter. The correcting filter determines a corrected standardized value corresponding to the raw input string based on the raw input string and a corrective rule. The label module then identifies the member profile as associate with the corrected standardized value.

Abstract: Database systems handle queries represented in different character sets. A database system allows data stored in the same database column to be represented in different character sets. In response to a query, the database system returns query results in the same character set as the received query even though the data stored in the database column is in a different character set. The database system creates and maintains a metadata table that stores attributes of database columns. The attributes of database columns include, among others, a data type, and a collation attribute. By tracking the collation attributes for data stored in database columns, the database system determines whether to convert data stored in a database column when processing database queries.

Abstract: Systems and methods are disclosed for determine creditworthiness based on the stability of the customer's occupation. Occupational risk scores may be used to group stable or unstable occupations and may be used in conjunction with other indicators of creditworthiness. Risk band scores may also be used to determine creditworthiness. Other aspects of the disclosed embodiments are described herein.

Abstract: Methods, apparatus, systems, computing devices, computing entities, and/or the like for a hybrid question-answering (QA) application are provided. The hybrid QA application includes both a retrieval QA application and a deep QA application, as well as a question classification model that determines whether the retrieval QA application or the deep QA application can generate a better answer to an input question.

Abstract: Methods and systems for compressing data, such as ion-mass information data in mass spectrometry spectra, to reduce index size are provided. Data in an index, such as fragment-ion data in a fragment-ion index, can be transformed for reduction of entropy and then encoded using a running counter technique to compress repetitive and redundant information in the index.

Abstract: Systems and methods are disclosed for utilizing a comment moderation bot for detecting and normalizing neologisms in social media. One method comprises transmitting, by a neologism normalization system, a comment moderation bot for detecting neologisms on an online platform maintained by one or more publisher systems. The comment moderation bot may aggregate data related to user comments and transmit the aggregated data to the neologism normalization system for further processing. The neologism normalization system implements unsupervised machine learning models for detecting neologisms in the aggregated data through tokenization and filtering; and normalizing the neologisms through similarity analysis and lattice decoding.

Abstract: A search server may receive a request to generate a set of indexes based at least in part on content associated with a user. The search server may generate a set of segments to divide the content. For a particular segment the search service then selects an indexing strategy to be used to generate an index for the particular segment. Other indexing strategies may be used to generate indexes for other segments. In addition, along with storing the index, the search server may store information indicating an association with the particular segment and the selected indexing strategy.

Abstract: Methods, systems, and computer program products for a semi-automatic process for creating a natural language processing resource are provided herein. A computer-implemented method includes identifying multiple annotation tasks in connection with natural language processing of input text, and automatically determining, based on analysis of (i) parameters related to the identified annotation tasks and (ii) parameters related to annotation task users, routing instructions for the identified annotation tasks, wherein the routing instructions comprise (a) instructions to route a first sub-set of the identified annotation tasks to non-expert annotation task users and (b) instructions to route a second sub-set of the identified annotation tasks to expert annotation task users.

Abstract: Systems and methods for a media guidance application that generates results in multiple languages for search queries. In particular, the media guidance application resolves multiple language barriers by taking automatic and manual user language settings and applying those settings to a variety of potential search results.

Abstract: According to one embodiment of the present invention, a method for providing a translation service by using an electronic device can comprise the steps of: receiving an original text written in a first language; displaying the original text in a first area on a display; generating a translation created by translating the original text into a second language; extracting a keyword from the translation; displaying the translation in a second area on the display; and displaying content related to the keyword in a third area on the display if the keyword is selected from the translation. In addition, other examples are also possible.

Abstract: Methods and systems are provided for improving speech recognition of multilingual named entities. In some embodiments, a list comprising a plurality of named entities may be accessed by a computing device. A first named entity represented in the native language may be compared with the first named entity represented in the foreign language. One or more words that appear in both the first named entity represented in the native language and the first named entity represented in the foreign language may be identified as one or more foreign words. A grapheme-to-phoneme (G2P) conversion may be applied to the one or more foreign words, wherein graphemes of the one or more foreign words are mapped to phonemes in the native language. The G2P conversion may result in a native pronunciation for each of the one or more foreign words, which are added to a recognition dictionary along with the native pronunciations.

Abstract: Techniques to provide contextual content are disclosed. In various embodiments, a set of topics inferred programmatically from a corpus of raw content data is obtained. An input is received. A topic with which the input is associated is determined, based at least in part on the input and the set of topics. A contextual content associated with the topic is provided.

Abstract: A speaker adaption method and a speaker adaption apparatus, a device and a storage medium are provided. The method includes: acquiring first speech data of a target speaker; inputting the first speech data to a pre-trained batch normalization (BN) network to be subjected to an adaptive training to acquire a speech recognition model including a speech parameter of the target speaker.

Abstract: A system and method for event matching by analysis of text characteristics are presented. A document collection comprising documents is acquired. One or more document subsets of the document collection each comprising one or more documents potentially describing identical events are identified based on certain structured metadata fields of the documents. Salient text features are extracted from the documents in the document collection. An event similarity score for pairs of documents in the document collection is generated by comparing the text features extracted from the documents. A common event document list comprising sets of documents in the document collection whose event similarity scores with each other are above a similarity threshold is generated.

Abstract: A computational device having a user interface is disclosed, the user interface enables a user to securely enter data into the computational device. In particular, the user interface may include a user input portion and a user output portion. The user input portion may be partitioned into a number of input zones, each having a data value associated therewith that when engaged by a user causes the data value associated with the engaged input zone to be provided as input to the computational device.

Abstract: One aspect of the invention relates to a method of displaying, in a first area of the display, a current character string being input by a user; displaying, in a second area of the display distinct from the first area, a plurality of suggested replacement character strings; detecting an input from a user; in accordance with a determination that the input selects one of the plurality of suggested replacement character strings, replacing the current character string in the first area of the display with the selected one of the plurality of suggested replacement character strings; and in accordance with a determination that the input confirms the current charactering string, keeping the current character string in the first area on the display.

Abstract: Certain aspects of the present disclosure provide techniques for selecting a response to a self-support query. One example method generally includes receiving an audio stream query including spoken content from a user recorded by a mobile device and determining a set of paralinguistic features from the spoken content. The method further includes estimating an emotional state of the user based on the set of paralinguistic features and identifying subject matter of the spoken content in the audio stream query. The method further includes determining two or more query responses corresponding to the subject matter to present to the user and transmitting at least one query response to the mobile device.

Abstract: Techniques are described herein for enabling an automated assistant to adjust its behavior depending on a detected age range and/or “vocabulary level” of a user who is engaging with the automated assistant. In various implementations, data indicative of a user's utterance may be used to estimate one or more of the user's age range and/or vocabulary level. The estimated age range/vocabulary level may be used to influence various aspects of a data processing pipeline employed by an automated assistant. In various implementations, aspects of the data processing pipeline that may be influenced by the user's age range/vocabulary level may include one or more of automated assistant invocation, speech-to-text (“STT”) processing, intent matching, intent resolution (or fulfillment), natural language generation, and/or text-to-speech (“TTS”) processing. In some implementations, one or more tolerance thresholds associated with one or more of these aspects, such as grammatical tolerances, vocabularic tolerances, etc.

Abstract: A targeted summary of textual content tuned to a target audience vocabulary is generated in a digital medium environment. A word generation model obtains textual content, and generates a targeted summary of the textual content. During the generation of the targeted summary, the words of the targeted summary generated by the word generation model are tuned to the target audience vocabulary using a linguistic preference model. The linguistic preference model is trained, using machine learning on target audience training data corresponding to a corpus of text of the target audience vocabulary, to learn word preferences of the target audience vocabulary between similar words (e.g., synonyms). After each word is generated using the word generation model and the linguistic preference model, feedback regarding the generated word is provided back to the word generation model. The feedback is utilized by the word generation model to generate subsequent words of the summary.

Abstract: A system for rapid deployment and configuration of a virtual agent to a hosted cloud platform is provided. A virtual agent builder may convert a dialog corpus into a dialog model that includes parameters that cause a cognitive service engine to provide natural language processing for the virtual agent according to the dialog corpus. Depending on the natural language processing capabilities of the cognitive engine service, the dialog model may be included in the virtual agent or communicated to the cognitive service engine. The virtual agent, or individual components of the virtual agent, may be generated and/or reconfigured in real time using predetermined logic that is selected based on virtual agent configuration parameters. The virtual agent configuration parameters may be received from a graphical user interface that reduces the complexity of deploying and/or managing the virtual agent.

Abstract: A system for text summarization includes an encoder for encoding input tokens of a document and a decoder for emitting summary tokens which summarize the document based on the encoded input tokens. At each iteration the decoder generates attention scores between a current hidden state of the decoder and previous hidden states of the decoder, generates a current decoder context from the attention scores and the previous hidden states of the decoder, and selects a next summary token based on the current decoder context and a current encoder context of the encoder. The attention scores penalize candidate summary tokens having high attention scores in previous iterations. In some embodiments, the attention scores include an attention score for each of the previous hidden states of the decoder. In some embodiments, the selection of the next summary token prevents emission of repeated summary phrases in a summary of the document.