Abstract: A user requests explanation of a term. In response, a definition is provided. The user can indicate that the user does not understand a new term included in the definition. In response, explanation information is customized based on analysis of the initial term and the new term, and then the explanation information is provided to the user.

Abstract: An example operation may include one or more of transferring a copy of a plurality of revised translation data sets to be added to an IVR application into a grid structure, each revised translation data set comprising a prompt name in a first field, an IVR prompt in a second field, a translation of the IVR prompt into a different language in a third field, and a timestamp in a fourth field, executing, via a processor, an accuracy validation on the plurality of revised translation data sets, wherein, for each revised translation data set, the processor identifies whether a respective translation in a different language in a third field is an accurate translation of a respective IVR prompt in a second field based on attributes of the respective translation and the respective IVR prompt, and displaying results of the accuracy validation via a user interface.

Abstract: Systems and methods are described for providing subtitles for a media content item. Subtitles are obtained, using control circuitry, for the media content item. Control circuitry determines whether a character component of the subtitles should be replaced by an image component. In response to determining that the character component of the subtitles should be replaced by an image component, control circuitry selects, from memory, an image component corresponding to the character component. Control circuitry replaces the character component of the subtitles by the image component to generate modified subtitles.

Abstract: Methods and systems for converting an input content item into an output content item to enhance comprehension of the message by an interlocutor, based on contexts. For example, the conversion may occur in any message service: when an interlocutor writes a message in English (or any other language), he or she might include a regional dialect (purposively or not), such as a piece of slang, that the other interlocutors may not understand, although they all generally write and understand English. In such circumstances, the regional dialect is identified and replaced with either a more globalized word or with another linguistic regionalism that is understandable for the intended interlocutor.

Abstract: The present disclosure discloses a method for training a reading comprehension model, and relates to a field of natural language processing and deep learning technologies. The detailed implementing solution includes: respectively inputting a first training sample of the reference field into a reference reading comprehension model of a reference field and a target reading comprehension model of a target field, to obtain first output data output by the reference reading comprehension model and second output data output by the target reading comprehension model; and performing a first training process on the target reading comprehension model based on a difference between the first output data and the second output data.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and method for replacing text in a message thread. The program and method provide for receiving an indication of user input provided by a first user, the user input comprising a text-based term for updating a message thread between the first user and a second user; determining that the text-based term is included within a set of predefined terms, each predefined term within the set of predefined terms having corresponding replacement content for including in the message thread, the replacement content having been specified by the first or second user with respect to messages exchanged between the first and second user; and providing, in response to the determining and based on the set of predefined terms, the replacement content corresponding to the text-based term within the message thread.

Abstract: Implementations are described herein for adapting existing source code snippets to new contexts. In various implementations, a command may be detected to incorporate an existing source code snippet into destination source code. An embedding may be generated based on the existing source code snippet, e.g., by processing the existing source code snippet using an encoder. The destination source code may be processed to identify one or more decoder constraints. Subject to the one or more decoder constraints, the embedding may be processed using a decoder to generate a new version of the existing source code snippet that is adapted to the destination source code.

Abstract: A multi-layer language translator operating in conjunction with a syntax-based model, coupled with machine learning and artificial intelligence, performs language translations from a source language text to text expressed in a target language. A relevancy-based “chunking” module breaks a source text into smaller units and applies a part-of-speech tag to some or all of the units. A hierarchy-based structuring module determines grammatical structure of the source text based, at least in part, on the applied part-of-speech tags. The hierarchy-based structuring module recursively combines grammatically linked units into one or more phrases, and applies to the phrases higher-level tags. A syntax-based translating module translates the units and/or phrases into the target language, and based on syntax differences between the source and target languages, reconfigures the translated text, as needed, such that the translated text is expressed in the target language using target language syntax rules and conventions.

Abstract: Proposed are a machine translation apparatus and a machine translation method for displaying a translation result through a user interface. The machine translation method may include: display an initial machine translation result for a first translation target sentence; correcting the initial machine translation result according to a manipulation result of a user on the user interface unit, and displaying the corrected machine translation result; and analyzing a difference between the corrected machine translation result and the initial machine translation result, and reflecting the analysis result to perform machine translation on a second translation target sentence. The machine translation apparatus and the method can be used to efficiently acquire a high-quality translation within a short time while minimizing time, cost and effort of a user, which used to be required for a conventional machine translation process.

Abstract: A processor may identify an anomaly in one or more communications. A processor may monitor the one or more communications for an utterance. A processor may perform natural language processing (NLP) on the utterance. A processor may generate an understanding of the utterance using natural language understanding (NLU). A processor may detect the anomaly from the understanding of the utterance. A processor may execute a response, responsive to detecting the anomaly.

Abstract: An approach for generating synthetic treebanks to be used in training a parser in a production system is provided. A processor receives a request to generate one or more synthetic treebanks from a production system, wherein the request indicates a language for the one or more synthetic treebanks. A processor retrieves at least one corpus of text in which the requested language is present. A processor provides the at least one corpus to a transformer enhanced parser neural network model. A processor generates at least one synthetic treebank associated with a string of text from the at least one corpus of text in which the requested language is present. A processor sends the at least one synthetic treebank to the production system, wherein the production system trains a parser utilized by the production system with the at least one synthetic treebank.

Abstract: Electronic device includes display, microphone, and processor configured to activate voice input function based on user input, display graphic representation for indicating that the voice input function is activated, provide, on the display, a text display area for displaying text inputted by a plurality of user input methods and a keyboard input interface for receiving a user keyboard input, the plurality of user input methods including user keyboard input method and user voice input method, receive, via the keyboard input interface, the user keyboard input corresponding to a first text, display the first text in the text display area based on receiving the user keyboard input, receive user voice input corresponding to a second text while the keyboard input interface is provided and the voice input function is activated, and display the second text next to the first text in the text display area based on the user voice input.

Abstract: A method for incorporating an augmented voice communication into a communication routing configuration of a contact center system according to an embodiment includes selecting a vocal avatar, wherein the vocal avatar includes phonetic characteristics having first values, receiving a text communication and input user parameters from an input user, generating the augmented voice communication based on the text communication and the input user parameters, wherein the augmented voice communication includes phonetic characteristics having second values, wherein the first values of the phonetic characteristics of the vocal avatar are different from the second values of the phonetic characteristics of the augmented voice communication, and incorporating the augmented voice communication into the communication routing configuration of the contact center system.

Abstract: A computing machine receives an input comprising unstructured text. The computing machine identifies, within the unstructured text, one or more entities using a named entity recognition (NER) engine in a trained machine learning model. The trained machine learning model embeds tokens from the text into a vector space and uses generated embeddings to identify one or more tokens as being associated with the one or more entities. The computing machine determines, using the trained machine learning model that identifies the one or more entities and based on the embedded tokens, an assertion applied, within the text, to at least one entity. The assertion is represented as a vector in a multi-dimensional space. Each dimension corresponds to a part of the assertion. The trained machine learning model is a span-level model that both identifies the one or more entities and determines the assertion based on candidate spans of tokens.

Abstract: A computer-implemented method for providing an input suggestion for a user is disclosed. The computer-implemented method may include identifying an intended recipient of an electronic message input by the user; identifying a location associated with the user and a time associated with the electronic message input by the user; determining the input suggestion for the user based on an input profile of the intended recipient, the location, and the time; and outputting the input suggestion via a user device associated with the user.

Abstract: The disclosure relates to system and method for processing multilingual user inputs using a Single Natural Language Processing (SNLP) model. The method includes receiving a user input in a source language and translating the user input to generate a plurality of translated user inputs in an intermediate language. The method includes using the SNLP model configured only using the intermediate language to generate a plurality of sets of intermediate input vectors in the intermediate language. The method includes processing the plurality of sets of intermediate input vectors in the intermediate language using at least one of a plurality of predefined mechanisms to identify a predetermined response. The method includes translating the predetermined response to generate a translated response that is rendered to the user.

Abstract: Techniques for determining a degree to which a document can be generated using a natural language generation (NLG) system, the NLG system being configured to generate natural language text. The techniques include using at least one computer hardware processor to perform: obtaining a document including text segments; determining a degree to which at least some of the text segments can be generated using the NLG system; generating a report indicating the degree to which the at least some of the text segments can be generated using the NLG system; and outputting the report.

Abstract: A building system including one or more memory devices configured to store instructions that, when executed by one or more processors, cause the one or more processors to receive training data including acronym strings and tag strings, train a sequence to sequence neural network based on the training data, receive an acronym string for labeling, the acronym string comprising a particular plurality of acronyms, and generate a tag string for the acronym string with the sequence to sequence neural network, wherein the sequence to sequence neural network outputs a tag of the tag string for one acronym of the particular plurality of acronyms based on the one acronym and contextual information of the acronym string, wherein the contextual information includes other acronyms of the particular plurality of acronyms.

Abstract: Systems and methods for an enhanced ultrasound biofeedback therapy for an improved speech remediation treatment for an individual include transmitting a plurality of ultrasound (US) waves toward a tongue of the individual; receiving a plurality of reflected US waves; converting the plurality of reflected US waves into a plurality of US signals to transmit to an ultrasound machine; and generating one or more enhanced images of the tongue at least partially based on the US signals in real-time, the enhanced images including identified Regions of Interest (ROIs) along tongue sub-parts comprising the tongue root, the tongue dorsum, and the tongue blade and respective ROI points identified therein. An interactive visual story is generated and updated in real-time with a tongue-mapping trajectory of the individual on a display based on the enhanced one or more images to determine a successful or unsuccessful sound production.

Abstract: A method includes receiving a dataset that includes a plurality of input texts. Each input text from the plurality of texts is associated with a content category from a plurality of content categories based on a comparison between that input text and an intended meaning that is common for each comparison. For each model in a plurality of models, and for each content category from the plurality of content categories, that model is executed on each input text from the plurality of input texts to generate an average similarity/dissimilarity score for that content category. At least one model from the plurality of models is selected, based on the average similarity score for each content category from the plurality of content categories for each model in the plurality of models, to determine whether an input text is similar/dissimilar to the intended meaning.

Abstract: Embodiments are disclosed for automated evaluation of compatibility of a data structure with a user device. An example method includes receiving, by communications circuitry, a set of user device characteristics regarding the user device, and retrieving, by the personalization circuitry, a set of data structure characteristics regarding the data structure. The example method further includes calculating, by the personalization circuitry, a set of characteristic-level compatibility scores, and generating, by the personalization circuitry and based on the set of characteristic-level compatibility scores, a compatibility score for the data structure and the user device. Subsequently, the example method includes generating, by an aggregator and using the generated compatibility score, an indication of relative compatibility of the data structure for the user device, and causing transmission, by communications circuitry, of a control signal to the user device based on the indication of relative compatibility.

Abstract: Techniques are described for invoking and switching between chatbots of a chatbot system. In some embodiments, the chatbot system is capable of routing an utterance received while a user is already interacting with a first chatbot in the chatbot system. For instance, the chatbot system may identify a second chatbot based on determining that (i) such an utterance is an invalid input to the first chatbot or (ii) that the first chatbot is attempting to route the utterance to a destination associated with the first chatbot. Identifying the second chatbot can involve computing, using a predictive model, separate confidence scores for the first chatbot and the second chatbot, and then determining that a confidence score for the second chatbot satisfies one or more confidence score thresholds. The utterance is then routed to the second chatbot based on the identifying of the second chatbot.

Abstract: The present disclosure relates to a response analysis system that employs a small-data training dataset to train a neural network that accurately performs domain-agnostic opinion mining. For example, in one or more embodiments, the response analysis system trains a response classification neural network using part of speech information (e.g., syntactic information) to learn and apply response classification labels for opinion text responses. In particular, the response analysis system employs part of speech information patterns without regard to word patterns to determine whether words in a text response correspond to an opinion, the target of the opinion, or neither. In addition, the trained response classification neural network has a significantly reduced learned parameter space, which decreases processing, memory requirements, and overall complexity.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing sequence modeling tasks using insertions. One of the methods includes receiving a system input that includes one or more source elements from a source sequence and zero or more target elements from a target sequence, wherein each source element is selected from a vocabulary of source elements and wherein each target element is selected from a vocabulary of target elements; generating a partial concatenated sequence that includes the one or more source elements from the source sequence and the zero or more target elements from the target sequence, wherein the source and target elements arranged in the partial concatenated sequence according to a combined order; and generating a final concatenated sequence that includes a finalized source sequence and a finalized target sequence, wherein the finalized target sequence includes one or more target elements.

Abstract: Systems and methods for content aggregation creation are disclosed herein. The system can include memory having a content database and an aggregation database. The system can include a user device having a first network interface and a first I/O subsystem. The system can include a server that can: provide content to the user device via a first electrical signal; receive a selection of a portion of the provided content from the user device via a second electrical signal; automatically extract sentences from the selected portion of the provided content via a natural language processor; automatically generate a parse tree for one of the automatically extracted sentences; identify noun phrases from the part of speech tags within the parse tree; place content associated with one of the noun phrase in a content aggregation; and output the content aggregation to the user device.

Abstract: A computer-implemented method of encoding a word for use in a method of text analysis comprises receiving input text to be analysed, the input text comprising a first word which is not represented in a vocabulary set stored on a storage. The vocabulary set comprises a plurality of words and an associated word embedding vector for each word in the set. The method comprises identifying the first word as a word which is not represented in the vocabulary set and determining one or more sub-words within the first word with which to encode the first word. Each of the one or more sub-words corresponds with a word represented in the vocabulary set and having an embedding vector in the vocabulary set. The method comprises determining an encoding for the first word based on the one or more sub-words.

Abstract: A system includes a memory and at least one processor to receive text from a client computing device, the text received one character at a time, as each character of the text is received, determine a recommendation in real-time to be added to the text based on at least one of a list of rules, word embedding, an n-gram model, and a co-occurrence model, the recommendation comprising at least one of a word, a list of hashtags, a quotation, and a list of emojis, and send the recommendation to the client computing device.

Abstract: Provided are an artificial intelligence (AI) system that mimics cognitive functions, such as recognition and determination, of the human brain using a machine learning algorithm such as deep learning and an application thereof. A method of providing feedback information in response to a user input including determining a user's intention, determining a variation in a number of candidates for an operation to be determined to correspond to the intention based on information input by the user, generating feedback information based on the determined variation, and providing the generated feedback information to the user is provided.

Abstract: A user may respond to a request of another user by entering text, such as a customer service representative responding to a customer. As the user enters text, a suggested completion of the text may be suggested to the user so that the user may select the suggested completion instead of continuing to enter text. Previous messages between the two users and other information may be used to determine an appropriate suggested completion to the entered text. A neural network language model and a search graph may be used to select a suggested completion from a search graph of possible suggested completions.

Abstract: A method, computer system, and a computer program product for estimating the probability of invoking information technology (IT) disaster recovery at a location based on an incident risk is provided. The present invention may include receiving a piece of data associated with an incident at the location. The present invention may also include estimating a similarity value associated with the incident based on a plurality of past incidents from a knowledge base. The present invention may then include receiving a plurality of mined data based on the location. The present invention may further include predicting the incident risk to the location based on the received plurality of mined data and the estimated similarity value to the plurality of past incidents.

Abstract: A phrase that includes a trigger word that modifies a meaning within the phrase is received. The trigger word is identified. The words of the phrase that are modified by the trigger word are identified by analyzing features of the phrase that link the trigger word to other words. The phrase is interpreted by modifying the second subset of words according to the modification of the trigger word.

Abstract: System and method to analyze and predict impact of textual data are provided. The system also includes a processing subsystem configured to select textual data from a plurality of data sets stored in a memory, to extract data from external sources using crawling, to identify at least one context of the textual data using one or more identification methods. The processing subsystem includes an NLP module configured to match the textual data with NLP frameworks using a mapping method based on a plurality of parameters, to apply feature engineering and transformation on the textual data to extract a plurality of features from the plurality of data sets and to analyze matched textual data of the textual using at least one analysis method. The processing subsystem also includes a predictive module configured to predict one or more future values of the analyzed textual data using the one or more predictive methods.

Abstract: A paraphrase sentence generation method and apparatus relating to the research field of natural language processing include generating m second sentences based on a first sentence and a paraphrase generation model, determining a matching degree between each of the m second sentences and the first sentence based on a paraphrase matching model, and determining n second sentences from the m second sentences based on matching degrees among the m second sentences and the first sentence, where the paraphrase generation model is obtained through reinforcement learning-based training based on a reward of the paraphrase matching model.

Abstract: A hybrid entity recognition system and accompanying method identify composite entities based on machine learning. An input sentence is received and is preprocessed to remove extraneous information, perform spelling correction, and perform grammar correction to generate a cleaned input sentence. A POS tagger tags parts of speech of the cleaned input sentence. A rules based entity recognizer module identifies first level entities in the cleaned input sentence. The cleaned input sentence is converted and translated into numeric vectors. Basic and composite entities are extracted from the cleaned input sentence using the numeric vectors.

Abstract: A non-transitory computer-readable recording medium stores instructions executable by a controller of an information processing apparatus. The instructions cause the controller to perform operations. The operations include: displaying an edit screen, the edit screen being configured to receive a translation instruction, the edit screen including a text area and a print area, the print area being configured to place therein a target text string to be printed; upon receiving on the edit screen an operation for inputting the target text string, displaying the target text string in a first language in the text area; upon receiving on the edit screen the translation instruction for translating the target text string displayed in the text area from the first language into a second language, translating the target text string to obtain a translation data piece representing a translated text string in the second language.

Abstract: The present invention may be a method, a system, and/or a computer program product. An embodiment of the present invention provides a method for paraphrasing, on a client computer, text in a webpage, the method comprising the following: transferring a request for a webpage including a plurality of passages of text to a server; receiving the webpage from the server in response to the request; judging whether or not the received webpage has text which is a subject of paraphrase; in a case where the judgment is positive, paraphrasing the text; and displaying, on a display, the webpage including the paraphrased text. Another embodiment of the present invention provides a method for updating on a server, text in a webpage, the method comprising the following: receiving, from each of the devices, a set of URLs of a webpage, a location path of text which is a subject of paraphrase in the webpage, and paraphrased text; and replacing text in the webpage with text among the received text.

Abstract: Methods and apparatus for automated processing of natural language text is described. The text can be preprocessed to produce language-space data that includes descriptive data elements for words. Source code that includes linguistic expressions, and that may be written in a programming language that is user-friendly to linguists, can be compiled to produce finite-state transducers and bi-machine transducers that may be applied directly to the language-space data by a language-processing virtual machine. The language-processing virtual machine can select and execute code segments identified in the finite-state and/or bi-machine transducers to disambiguate meanings of words in the text.

Abstract: Provided are a method and apparatus for classifying a sentence into a class by using a deep neural network. The method includes respectively training first and second sentences by using first and second neural networks, obtaining a contrastive loss based on first and second feature vectors generated as output data of the training, and information about whether classes to which the first and second sentences belong are the same, and repeating the training in such a manner that the contrastive loss has a maximum value.

Abstract: Methods, apparatus and systems for recognizing sign language movements using multiple input and output modalities. One example method includes capturing a movement associated with the sign language using a set of visual sensing devices, the set of visual sensing devices comprising multiple apertures oriented with respect to the subject to receive optical signals corresponding to the movement from multiple angles, generating digital information corresponding to the movement based on the optical signals from the multiple angles, collecting depth information corresponding to the movement in one or more planes perpendicular to an image plane captured by the set of visual sensing devices, producing a reduced set of digital information by removing at least some of the digital information based on the depth information, generating a composite digital representation by aligning at least a portion of the reduced set of digital information, and recognizing the movement based on the composite digital representation.

Abstract: A learning device includes one or more processors. The processors input, to an input layer of a neural network including hidden layers defined for respective first arrangement patterns indicating arrangement of one or more words, and output layers connected with some of hidden layers, one or more first morphemes conforming to any of first arrangement patterns, among morphemes included in a document, and learn the neural network to minimize a difference between one or more second morphemes conforming to any of second arrangement patterns indicating arrangement of one or more words, among morphemes included in the document, and output morphemes from the neural network for the input first morphemes. The processors output an embedding vector of the first morphemes that is obtained based on a weight of the learned neural network.

Abstract: A knowledge base is collaboratively developed by receiving language input from at least one editor, featurizing it into language elements, extracting predicate sets that are missing predicate arguments, querying editors for input regarding the missing arguments, and updating the knowledge base with suitable predicate arguments and other language elements provided by the editors.

Abstract: A method may include generating, based a context-free grammar, a sample forming a corpus. The context-free grammar may include production rules for replacing a first nonterminal symbol with a second nonterminal symbol and/or a terminal symbol. The sample may be generated by rewriting recursively a first text string to form a second text string associated with the sample. The first text string may be rewritten by applying the production rules to replace nonterminal symbols included in the first text string until no nonterminal symbols remain in the first text string. A machine learning model may be trained, based on the corpus, to process a natural language. Related methods and articles of manufacture are also disclosed.

Abstract: A question-and-answer system directed to a specific domain optimally utilizes reference documents that are semantically complete for that domain. Semantic completeness of a document is assessed using quality control questions (provided by subject matter experts) applied to the Q&A system followed by analysis of the proposed answers. That analysis is carried out using a cogency module having a feedforward neural network which receives metadata features of the document such as document ownership, document priority, and document type. A domain-optimized corpus for the Q&A system is built by so assessing multiple documents in a document collection, and adding each reference document that is reported as being semantically complete to the domain-optimized corpus. Thereafter, the deep learning question-and-answer system can receive a natural language query from a user, find a responsive answer in the documents while applying the domain-optimized corpus, and provide that answer to the user.

Abstract: A method, an apparatus, a computer device and a readable medium for knowledge hierarchical extraction of a text are disclosed. The method comprises: performing word segmentation on a designated text to obtain a word list, the word list including at least one word arranged in a sequence in the designated text; analyzing part-of-speech of each word in the word list in the designated text, to obtain a part-of-speech list corresponding to the word list; predicting a SPO triple included in the designated text according to the word list, the part-of-speech list and a pre-trained knowledge hierarchical extraction model. By the technical solutions, the SPO triple included in any designated text however loose its organization and structure is may be accurately extracted based on the pre-trained knowledge hierarchical extraction model. Compared to the prior art, the efficiency and accuracy of knowledge hierarchical extraction may be effectively improved.

Abstract: Disclosed are an emotion classification information-based text-to-speech (TTS) method and device. The emotion classification information-based TTS method according to an embodiment of the present invention may, when emotion classification information is set in a received message, transmit metadata corresponding to the set emotion classification information to a speech synthesis engine and, when no emotion classification information is set in the received message, generate new emotion classification information through semantic analysis and context analysis of sentences in the received message and transmit the metadata to the speech synthesis engine. The speech synthesis engine may perform speech synthesis by carrying emotion classification information based on the transmitted metadata.

Abstract: A method for detecting deviations between an event log and a process model includes converting the process model into a probability process model, the probability process model comprising multiple nodes in multiple hierarchies and probability distribution associated with the multiple nodes, a leaf node among the multiple nodes corresponding to an activity in the process model; detecting differences between at least one event sequence contained in the event log and the probability process model according to a correspondence relationship; and identifying the differences as the deviations in response to the differences exceeding a predefined threshold; wherein the correspondence relationship describes a correspondence relationship between an event in one event sequence of the at least one event sequence and a leaf node in the probability process model.

Abstract: Training a machine learning model such as a neural network, which can automatically extract a hypernym from unstructured data, is disclosed. A preliminary candidate list of hyponym-hypernym pairs can be parsed from the corpus. A preliminary super-term—sub-term glossary can be generated from the corpus, the preliminary super-term—sub-term glossary containing one or more super-term—sub-term pairs. A super-term—sub-term pair can be filtered from the preliminary super-term—sub-term glossary, responsive to detecting that the super-term—sub-term pair is not a candidate for hyponym-hypernym pair, to generate a final super-term—sub-term glossary. The preliminary candidate list of hyponym-hypernym pairs and the final super-term—sub-term glossary can be combined to generate a final list of hyponym-hypernym pairs. An artificial neural network can be trained using the final list of hyponym-hypernym pairs as a training data set, the artificial neural network trained to identify a hypernym given new text data.

Abstract: A design application is configured to perform a system-level optimization of a collection of system components. The design application iteratively executes a multi-objective solver to optimize structural and functional relationships between the system components in order to meet global design criteria and generate a system design. The design application initializes the design process by extracting from a knowledge base system templates having taxonomic, structural, or functional attributes relevant to the system design. The design application generates the knowledge base by mining taxonomic, structural, and functional relationships from a corpus of engineering texts.

Abstract: An electronic device and a method for controlling the electronic device thereof are provided. The electronic device includes a memory storing instructions, and a processor configured to control the electronic device by executing the instructions stored in the memory, and the processor is configured to, based on a user's speech being input, acquire a first sentence in a first language corresponding to the user's speech through a speech recognition model corresponding to a language of the user's speech, acquire a second sentence in a second language corresponding to the first sentence in the first language through a machine translation model trained to translate a plurality of languages into the predefined second language, and acquire a control instruction of the electronic device corresponding to the acquired second sentence or acquire a response to the second sentence through a natural language understanding model trained based on the second language.

Abstract: Systems and methods are provided to combine data from various internal data sources and external data sources to generate and maintain frequently asked questions and knowledge bases. By doing so, the collective knowledge of a company and customers' questions around it are aggregated and served in a way that increases the availability and relevancy of such knowledge for both self-help channels and computing agents (e.g., customer service representatives (CSRs)).