Abstract: A computer-implemented method is provided to perform text classification with a neural network system. The method includes providing a computing device to receive input datasets including user input question text and feed the datasets to the neural network system. The neural network system includes one or more neural networks configured to extract and concatenate character-based features, word-based features from the question datasets and clickstream embeddings of clickstream data to form a representation vector indicative of the question text and user behavior. A representation vector is fed into fully connected layers of a feed-forward network. The feed-forward network is configured to predict a first class and a second class associated with respective user input questions based on the representation vector.

Abstract: Aspects of the present disclosure relate to identifying semantic relationships. Natural language content is received. A part of speech is determined for respective terms within the natural language content. A semantic type is determined for each of two or more terms within the natural language content. A parse tree representation containing a plurality of nodes is then generated based on the natural language content, each of the plurality of nodes corresponding to at least one term within the natural language content, wherein visual characteristics of respective nodes of the plurality of nodes within the parse tree representation depend on the part of speech and semantic type of the respective terms. A bounding box identifying a semantic relationship is then generated around a set of nodes on the parse tree representation, the set of nodes including the two or more terms.

Abstract: Methods, systems, and computer program products for extracting meaning representation from text are provided herein.

Abstract: A method for applying image encoding recognition in the execution of natural language processing (NLP) tasks, comprising the processing steps as follows. A sentence from a textual source is extracted by an NLP-based feature extractor. A word vector is generated in response to the sentence by the NLP-based feature extractor. The word vector is converted into a feature vector {right arrow over (b)} by the NLP-based feature extractor, in which the feature vector {right arrow over (b)} satisfies {right arrow over (b)}?m and the parameter m is a positive integer. The feature vector is transformed into an image set having a plurality of two-dimensional images by a transformer. The image set is fed to a neural network to execute image recognition by a processor, so as to analyze the sentence.

Abstract: In a method for the recognition of an object by means of a radar sensor system, a primary radar signal is transmitted into an observation space, a secondary radar signal reflected by the object is received, a Micro-Doppler spectrogram of the secondary radar signal is generated, and at least one periodicity quantity relating to an at least essentially periodic motion of a part of the object is determined based on the Micro-Doppler spectrogram. The determining of the at least one periodicity quantity includes the following steps: (i) determining the course of at least one periodic signal component corresponding to an at least essentially periodic pattern of the Micro-Doppler spectrogram, (ii) fitting a smoothed curve to the periodic signal component, (iii) determining the positions of a plurality of peaks and/or valleys of the smoothed curve, and (iv) determining the periodicity quantity based on the determined positions of peaks and/or valleys.

Abstract: Embodiments of the invention describe a computer-implemented method that includes receiving a query that includes a query sequence having query characters grouped into query words. A segment of program code is retrieved from a database for evaluation. The program code includes a program code sequence including program code characters grouped into program code words. The query sequence, the query word, the program code sequence, and the program code word are each converted to sequence and word representations. Query sequence-level features, query word-level features, program code sequence-level features, and program code word-level features are extracted from the sequence and word representation. Similarity between the query and the segment of program code is determined by applying a similarity metric technique to the query sequence-level features, the query word-level features, the program code sequence-level features, and the program code word-level features.

Abstract: Systems, methods, and non-transitory computer-readable media can determine one or more graphical overlays to be applied to at least one object represented in a media content item; determine that a depth of the object as represented in one or more frames of the media content item satisfies a first threshold depth; and augment a representation of the object based at least in part on a first graphical overlay that corresponds to the first threshold depth.

Abstract: An artificial intelligence server for determining a deployment area of a robot includes a memory and a processor. The memory is configured to store density data for a control area. The processor is configured to obtain a plurality of current context keywords corresponding to a current time point, determine at least one related keyword among the obtained plurality of current context keywords using the density data, and determine the deployment area of the robot based on density data corresponding to the determined related keyword.

Abstract: A method of determining an operational difficulty of a process described in a document including text includes generating text data corresponding to the text of the document, and generating a word vector output by processing the text data through a plurality of word vectors, the plurality of word vectors based on a domain-specific text collection and a general-language text collection. The method further includes generating a statistical information output by processing the text data through a plurality of statistical information vectors, the plurality of statistical information vectors based on the domain-specific text collection and the general-language text collection, and generating a gated recurring unit (GRU) output by processing (i) the word vector output, (ii) the statistical information output, (iii) word-level data based on the text data, (iv) sentence-level data based on the text data, and (v) paragraph-level data based on the text data through at least one GRU.

Abstract: A computer-implemented method, according to one embodiment, includes: sending one or more instructions to a web crawler to identify presentation videos on the internet and capture video data therefrom. In response, video data which corresponds to various presentation videos on the internet is received from the web crawler. The video data is used to define influence factors, such that different combinations of the influence factors represent different conditions of a presenter in the presentation videos. The video data is also used to define labels, where different combinations of the labels represent different conditions of one or more audience members in the presentation videos. Furthermore, structured data is generated by correlating certain presenter conditions with certain audience conditions, and the structured data is stored in memory.

Abstract: Approaches for determining a response for an agent in an undirected dialogue are provided. The approaches include a dialogue generating framework comprising an encoder neural network, a decoder neural network, and a language model neural network. The dialogue generating framework generates a sketch sentence response with at least one slot. The sketch sentence response is generated word by word and takes into account the undirected dialogue and agent traits of the agent making the response. The dialogue generating framework generates sentence responses by filling the slot with words from the agent traits. The dialogue generating framework ranks the sentence responses according to perplexity by passing the sentence responses through a language model and selects a final response which is a sentence response that has a lowest perplexity.

Abstract: A method and device for correcting an error in a text are provided. The method includes: preprocessing the text to obtain at least one segment of the text; generating a plurality of candidate segments for the segment; scoring the plurality of candidate segments with a tree model, to obtain respective first scoring results of the plurality of candidate segments; scoring the plurality of candidate segments with a deep neural network model, to obtain respective second scoring results of the plurality of candidate segments; for each candidate segment, calculating a scoring of the candidate segment based on the first scoring result and the second scoring result of the candidate segment; ranking the plurality of candidate segments according to the scorings of the candidate segments, to obtain a ranking result; and correcting the error in the text according to the ranking result.

Abstract: An electronic message including text generated by a first user can be identified and at least a second user can be identified as a recipient. At least one n-gram contained in the text of the electronic message can be identified by performing natural language processing on the text. A first user profile of the first user and a second user profile of the second user can be accessed. Based on the first user profile and the second user profile, at least one user context of the first user, not shared with the second user, relating to the computer-understandable meaning of the at least one n-gram can be determined. The electronic message as presented to the second user can include the at least one user context of the first user, not shared with the second user, relating to the computer-understandable meaning of the at least one n-gram.

Abstract: Embodiments of the present invention provides methods, computer program products, and a system for providing a shipping and billing address for online product purchases based on a fingerprint of a user. Embodiments of the present invention can be used to request a live scan of a fingerprint, identify a stored address based on the fingerprint, and complete a shipping and billing address section for an online purchase using the stored address. Embodiments of the present invention can be used to collect a fingerprint from a user, match the fingerprint to a database of fingerprints, and acquire a stored address mapped to the fingerprint. Embodiments of the present invention can be used quickly provide a shipping and billing address for an online purchase based on a double-tap gesture made by a user on an electronic device.

Abstract: One embodiment of the present invention provides a method comprising receiving a text corpus, and generating a first list of triples based on the text corpus. Each triple of the first list comprises a first term representing a candidate hyponym, a second term representing a candidate hypernym, and a frequency value indicative of a number of times a hypernymy relation is observed between the candidate hyponym and the candidate hypernym in the text corpus. The method further comprises training a neural network for hypernym induction based on the first list. The trained neural network is a strict partial order network (SPON) model.

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 analysis by utilizing joint topic-sentiment (JST) modeling.

Abstract: In some examples, matrix based bot implementation may include obtaining, for a plurality of bots that are used to respond to a query, a matrix that includes entries including a plurality of scenarios, a plurality of questions corresponding to the plurality of scenarios, and a plurality of responses. Each response may correspond to a specified question. A plurality of scripts may be generated based on an analysis of the matrix. Each script may include at least one question followed by at least one response, and further followed by at least one scenario. For each script, a closest pre-existing script may be identified based on a comparison of the script to pre-existing scripts. For each script, a modification to the matrix may be generated based on a difference in the script from the closest pre-existing script. The bots may be utilized to respond to the query based on the modified matrix.

Abstract: Local detail enhancement (LDE) is an imagery contrast enhancement method applied to visible and uncooled long wave imagery. It enhances local spatial detail through the use of a median based high/band pass filter. The generated detail channel is blended with a histogram-equalized version of the image, creating an image that contains both local detail as well as retaining some amount of global intensity. Retaining global intensity coherency allows for easier target acquisition when compared to fully local forms of contrast enhancement.

Abstract: Some implementations of the disclosure are directed to retrieving a structured description; using a model trained on a plurality of structured descriptions to generate a numeric representation of the retrieved description; searching the retrieved description for a plurality of keywords in a keyword list to generate one or more values corresponding to a presence of the plurality of searched keywords; combining the numeric representation of the structured description with the generated one or more values to create a combination; using the combination to compute a most likely classification of the description from a plurality of classifications; and returning the most likely classification.

Abstract: A display control apparatus according to the present invention includes: an axis detection unit configured to detect, based on an image, a rotation axis about which a celestial body included in the image as an object rotates in response to the rotation of the earth; and a control unit configured to perform control such that a partial area of the image is displayed as a display area, and rotation display is performed by changing the display area while changing an angle corresponding to the display area around a position corresponding to the rotation axis detected by the axis detection unit.