Abstract: A specific target-oriented social media tweet sentiment analysis method includes: preprocessing social media tweet data to obtain a target text and a specific target; passing the target text and the specific target through an embedding layer to obtain target text word vectors and obtain a specific target word vector, respectively; passing the target text word vectors through a self-attention structure to obtain a self-attention result; combining the self-attention result with the specific target word vector and passing through a cross-attention structure to obtain cross-attention results; concatenating the cross-attention results to obtain an attention representation matrix; and passing the attention representation matrix through a pooling layer, a fully connected layer and a softmax layer to obtain a sentiment tendency of the specific target.

Abstract: Apparatus and methods to decipher and analyze hidden/figurative meanings in communications using contextual analysis are provided. The apparatus and methods may include generating an initial list of slang words and phrases and their corresponding hidden/figurative meanings, searching the Internet for new slang words and phrases, determining the corresponding hidden/figurative meanings of the new slang words and phrases, and contextually analyzing a set of communications for hidden/figurative meaning. The apparatus and methods may include generating an alert if a relevant hidden/figurative meaning is found in the set of communications.

Abstract: Systems, devices, and methods of the present invention involve discourse trees. In some aspects, a system creates a discourse tree by identifying elementary discourse units in text. The discourse tree includes nodes, each nonterminal node representing a rhetorical relationship between two elementary discourse units and each terminal node associated with an elementary discourse unit. The system identifies, in a reference sentence of the discourse tree, a rhetorical relation of type elaboration or joint. The system selects a candidate sentence having a highest syntactic generalization score of a set of syntactic generalization scores. The system identifies a semantic relation corresponding to the candidate sentence. The semantic relation corresponds to a word in the candidate sentence and defines a role in the candidate sentence.

Abstract: In an approach for discourse-level text optimization, a processor receives an initial text in a first language. A processor applies one or more operators to modify the initial text. A processor evaluates the modified text using a scoring function. A processor determines whether a score generated from the scoring function on the modified text is above a predefined threshold. In response to determining the score is above the predefined threshold, a processor outputs the modified text.

Abstract: A translation method is provided, including: encoding to-be-processed text information to obtain a source vector representation sequence, the to-be-processed text information belonging to a first language; obtaining a source context vector corresponding to a first instance according to the source vector representation sequence, the source context vector indicating to-be-processed source content in the to-be-processed text information at the first instance; determining a translation vector according to the source vector representation sequence and the source context vector; and decoding the translation vector and the source context vector, to obtain target information of the first instance, the target information belonging to a second language.

Abstract: The present disclosure provides an event extraction method, an event extraction device and an electronic device, and it relates to the field of computer data processing, in particular to the field of knowledge graph. The event extraction method includes: acquiring text information; determining a plurality of pieces of question information ranked in a sequential order in accordance with the text information; and inputting vector information for each piece of question information into an extraction model in accordance with the sequential order to acquire extraction information for each piece of question information.

Abstract: Some embodiments provide a program that retrieves a set of notifications describing failures that occurred on a set of monitored devices. The program further determines a set of topics based on the set of notifications. The program also determines failure modes associated with the set of topic from a plurality of failure modes defined for the set of monitored devices. The program further determines failure modes associated with the set of notifications based on the set of topics and the failure modes associated with the set of topics. The program also receives a particular notification that includes a particular set of words describing a failure that occurred on a particular monitored device in the set of monitored devices. The program further determines a failure mode associated with the particular notification based on the particular set of words and the determined failure modes associated with the set of notifications.

Abstract: Embodiments relate to a system, program product, and method for employing deep learning techniques to fuse data across modalities. A multi-modal data set is received, including a first data set having a first modality and a second data set having a second modality, with the second modality being different from the first modality. The first and second data sets are processed, including encoding the first data set into one or more first vectors, and encoding the second data set into one or more second vectors. The processed multi-modal data set is analyzed, and the encoded features from the first and second modalities are iteratively and asynchronously fused. The fused modalities include combined vectors from the first and second data sets representing correlated temporal behavior. The fused vectors are then returned as output data.

Abstract: A translation model training method for a computer device includes obtaining a training sample set, the training sample set including a plurality of training samples. Each training sample is a training sample pair having a training input sample in a first language and a training output sample in a second language. The method also includes determining a disturbance sample set corresponding to each training sample in the training sample set, the disturbance sample set comprising at least one disturbance sample, and a semantic similarity between the disturbance sample and the corresponding training sample being greater than a first preset value; and training an initial translation model by using the plurality of training samples and the disturbance sample set corresponding to each training sample to obtain a target translation model, such that the training output sample remains same for the disturbance sample and the corresponding training sample.

Abstract: To make it possible to accurately generate a word vector even if vocabulary of a word vector data set is not limited. In a vector generating device 10 that generates vectors representing an input sentence P, when generating a series of the vectors representing the input sentence P based on vectors corresponding to words included in the input sentence P, a definition-sentence-considered-context encode unit 280 generates, based on a dictionary DB 230 storing sets of headwords y and definition sentences Dy, which are sentences defining the headwords y, concerning a word, which is the headword stored in the dictionary DB, among the words included in the input sentence P, the series of the vectors representing the input sentence P using the definition sentence Dy of the headwords y.

Abstract: An embodiment of the present invention is directed to combining natural language processing with constrained grammar defined pattern matching to advantageously allow a system to translate natural language questions into any number of underlying technologies. By using a unique intermediate parse tree representation, the disclosed embodiments are able to instantiate a corresponding data store adapter for each given query, which may be for a relational database or a no-SQL database, for example. The ability to abstract underlying storage technology advantageously allows the management of disparate database systems, which is not possible using existing methods and technology.

Abstract: Systems, devices, and methods of the present invention detect deceptive or fake content in text. In an example, a computer system generates, from text a discourse tree that represents rhetorical relationships between fragments of the text. The computer system generates a communicative discourse tree from the discourse tree. The computer system identifies a number of non-trivial rhetorical relations associated with the nonterminal nodes in the communicated discourse tree and, for each terminal edge having a communicative action, a level of nesting of the communicative action. The computer system derives, from the number of non-trivial rhetorical relations and the levels of nesting of the identified communicative actions, a complexity score that is indicative of a level of deception in the text.

Abstract: A request paraphrasing system 120 allowing a dialogue system to flexibly address to requests in various different manners of expression includes: a pre-processing unit 130 converting a user input 56 to a word vector sequence; and a neural paraphrasing model 94 trained in advance by machine learning to receive the word vector sequence as an input and paraphrasing a request represented by the word vector sequence to a request having a higher probability of obtaining an answer from a question-answering device 122 than the request before paraphrasing. As pre-processing, whether the user input 56 is a request or not may be determined and it may be paraphrased only when it is determined to be a request. Further, a classification model 98 may classify the input request to determine to which request class it belongs, and the classification may be input as one feature to neural paraphrasing model 94.

Abstract: Methods, apparatus, systems and articles of manufacture to generate regex and detect data similarity are disclosed. An example apparatus includes a token graph generator to generate a token graph including nodes based on a cluster of strings corresponding to a group of messages that are known to be spam; a pivot engine to identify pivot nodes in the cluster of strings; a pivot applicator to tag corresponding ones of the nodes of the token graph as the pivot nodes; and a regex converter to generate the anti-spam signature based on: (a) the tagged nodes and (b) at least one of the node of the token graph that is not tagged as a pivot node.

Abstract: This application relates to a machine translation method performed at a computer device. The method includes: obtaining an original source text and a reconstructed source text; performing semantic encoding on the original source text, to obtain a source vector sequence; sequentially decoding the source vector sequence to obtain target vectors by performing decoding on the source vector sequence at a current time according to a word vector of a candidate target word determined at a previous time, determining a candidate target word at the current time according to a target vector at the current time, and forming a target vector sequence accordingly; performing reconstruction assessment on the source vector sequence and the target vector sequence using the reconstructed source text, to obtain reconstruction scores corresponding to the candidate target words; and generating a target text according to the reconstruction scores and the candidate target words.

Abstract: Disclosed is a method for error detection, performed by one or more processors of a computing device according to an example embodiment of the present disclosure. The method includes evaluating an error rate for a sentence to be evaluated, in a first language unit. the method includes evaluating an error rate in a second language unit which is smaller than the first language unit, based on the first language unit error.

Abstract: A call translation system and a method for operating the management system in a controlled environment is disclosed. The call translation system includes a calling device and a call translation server. The calling device receives authorization from the call translation server to conduct call sessions within the controlled environment. The calling device further receives a call session application from the call translation server that enables the calling device to initiate and establish call sessions through the call translation server. The call session application allows a user of the calling device to select outside parties to add to the call session.

Abstract: Provided are a model training method for neural machine translation that enhances an encoder using a monolingual corpus of a target language and improves the accuracy of the entire translator, and a machine translation system for performing the model training method. The machine translation system 1000 uses a monolingual corpus of the target language to obtain multiple pieces of pseudo source language data, thus allowing for obtaining a large amount of pseudo parallel corpus data having diversity. Further, the machine translation system 1000 uses both the pseudo parallel corpus data having diversity, which has been obtained in large quantities, and the base parallel corpus data in a small quantity but with high accuracy, with the applied learning rates changed accordingly, to perform the learning process (training process) for the machine translation model. This allows the machine translation system 1000 to obtain a learned model (machine translation model) with very high accuracy.

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

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