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.

Abstract: Systems and methods for performing inference for word or wordpiece tokenization are disclosed using a left-to-right longest-match-first greedy process. In some examples, the vocabulary may be organized into a trie structure in which each node includes a precomputed token or token ID and a fail link, so that the tokenizer can parse the trie in a single pass to generate a list of only those tokens or token IDs that correspond to the longest matching vocabulary entries in the sample string, without the need for backtracking. In some examples, the vocabulary may be organized into a trie in which each node has a fail link, and any node that would share token(s) or token_ID(s) of a preceding node is instead given a prev_match link that points back to a chain of nodes with those token(s) or token_ID(s).

Abstract: A video translation method includes: converting speech in a video to be translated into text; displaying the text and first time information, second time information, and a reference translation of the text; in response to an operation by a user on the text or the reference translation, displaying an editing area supporting the user inputting a translation; following input by the user, providing a translation suggestion from the reference translation; when a confirmation operation by the user for the translation suggestion is detected, using the translation suggestion as a translation result and displaying the same; when a non-confirmation operation by the user for the translation suggestion is detected, receiving a translation inputted by the user which is different from the translation suggestion, using the inputted translation as a translation result and displaying the same, and updating the reference translation in a translation area according to the inputted translation.

Abstract: Certain aspects of the present disclosure provide techniques for training and using a machine learning model to extract relevant textual content for custom fields in a software application from freeform text samples. An example method generally includes generating, via a natural language processing pipeline, a training data set from a data set of freeform text samples and field entries for a plurality of custom fields defined in a software application. A first machine learning model is trained to identify custom fields for which relevant data is included in freeform text. A second machine learning model is trained to extract content from the freeform text into one or more custom fields of the plurality of custom fields defined in the software application and identified by the first machine learning model as custom fields for which relevant data is included in the freeform text.

Abstract: Systems, devices, and methods of the present invention validate argumentation in text. In an example, an application forms a communicative discourse tree from a subset of text by matching each fragment of the subset that has a verb to a verb signature. The application identifies that the subset includes an argument by applying a classification model trained to detect argumentation to the communicative discourse tree. The application further creates a logic system based on a claim of the argument, a domain definition clause associated with a domain of the text, a set of defeasible rules based on the communicative discourse tree, and a set of facts from one or more of the communicative actions of the communicative discourse tree. The application evaluates a consistency of the argument with respect to itself and with respect to the domain definition clauses by solving the logic system, thereby validating a claim associated with the argument.

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.

Abstract: Methods and systems are presented for providing automated online chat assistance in multiple languages. A query in a first language is received via a chat robot from a user device. The query is machine-translated into a second language and transmitted to an artificial intelligence system that includes a dialog tree configured in the second language. The artificial intelligence system determines a response in the second language to the query by locating a node corresponding to an intent based on the query in the dialog tree. The node includes a node ID and response text in the second language. The artificial intelligence system transmits the second-language response including the node ID to the chat robot. The second-language response is intercepted, and first-language response text corresponding to the second-language response text is determined based on the node ID. The second-language response text is then provided to the user device by the chat robot.

Abstract: There is a need for more effective and efficient document summarization. This need can be addressed by, for example, techniques for contextual summarization using semantic intelligence. In one example, a method includes identifying a plurality of senses associated with a plurality of words in a document; for each word-sense pair, determining a word-sense probability score; determining, based at least in part on each word-sense probability score for a word-sense pair, one or more context buckets for the document and one or more sense buckets for the document; determining, based at least in part on the one or more context buckets for the document and the one or more sense buckets for the document, the contextual summarization of the document; and performing one or more document processing actions based at least in part on the contextual summarization.

Abstract: One embodiment of the present disclosure sets forth a technique for generating translation suggestions. The technique includes receiving a sequence of source-language subtitle events associated with a content item, where each source-language subtitle event includes a different textual string representing a corresponding portion of the content item, generating a unit of translatable text based on a textual string included in at least one source-language subtitle event from the sequence, translating, via software executing on a machine, the unit of translatable text into target-language text, generating, based on the target-language text, at least one target-language subtitle event associated with a portion of the content item corresponding to the at least one source-language subtitle event, and generating, for display, a subtitle presentation template that includes the at least one target-language subtitle event.

Abstract: Described herein are embodiments for end-to-end reinforcement learning based coreference resolution models to directly optimize coreference evaluation metrics. Embodiments of a reinforced policy gradient model are disclosed to incorporate reward associated with a sequence of coreference linking actions. Furthermore, maximum entropy regularization may be used for adequate exploration to prevent a model embodiment from prematurely converging to a bad local optimum. Experiments on datasets compared with state-of-the-art methods verified the effectiveness of embodiments.

Abstract: Disclosed are a labeling method and apparatus for named entity recognition of a legal instrument. The method includes steps: step S1: acquiring a legal text, and transforming the legal text into an index table; step S2: outputting a sentence feature encoding result; step S3: performing training and prediction; step S4: obtaining a set; step S5: obtaining a multi-head score transfer matrix; step S6: obtaining a score transfer matrix corresponding to the legal text; step S7: determining a recognized nested entity; and S8: constructing an entity labeling template by using the recognized nested entity. According to the present disclosure, a user tries to complete recognition of nested entity labeling by changing an input of the BERT model, and a multi-head selection matrix labeling thought of the present disclosure is used to relieve the difficulty in recognizing a long text and a nested entity in an NER task to a larger extent.

Abstract: Disclosed is an artificial intelligence server. The artificial intelligence server includes a communicator in communication with at least one electronic device and a processor for receiving input data from a specific electronic device, applying personalized information corresponding to the specific electronic device to a recognition model, inputting the input data into the recognition model to which the personalized information is applied to obtain a final result value, and transmitting the final result value to the specific electronic device.

Abstract: A dialog change service builds a directed graph of nodes, each described by code for a conversational agent stored in source control, the code comprising one or more dialog-based features. The dialog change service, responsive to receiving a request for a dialog change to a particular node of the conversational agent, evaluates the directed graph to identify an additional selection of nodes that require a similar changes as the dialog change based on textual and structural content. The dialog change service updates the code for the particular node and the additional selection of nodes to propagate the dialog change in the conversational agent stored in source control.

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: Systems, devices, and methods of the present disclosure use discourse analysis and other techniques to form questions and answers from text. The questions and answers can be used for different applications, including providing a virtual dialogue or generating training data for machine-learning models. For example, a dialogue application generates a discourse tree that represents text and identifies a question from a satellite elementary discourse unit of the discourse tree. The dialogue application annotates the text by inserting the generated question and labeling the satellite elementary discourse unit as an answer.

Abstract: A document translation method includes: displaying a source text display region, a translated text region, and an editing region, wherein textual content in a document to be translated is displayed in the source text display region, and reference translated text for the textual content is displayed in the translated text region; and providing a translated text recommendation from the reference translated text according to input from a user within the editing region. The method further includes: displaying the translation recommendation in the editing area as a translation result, if a confirmation operation for the translation recommendation is detected; and receiving a translation inputted by the user that is different from the translation recommendation and displaying the translation inputted by the user in the editing area as the translation result, if a non-confirmation operation for the translation recommendation is detected.

Abstract: A computing system including one or more processors configured to receive an audio input. The one or more processors may generate a text transcription of the audio input at a sequence-to-sequence speech recognition model, which may assign a respective plurality of external-model text tokens to a plurality of frames included in the audio input. Each external-model text token may have an external-model alignment within the audio input. Based on the audio input, the one or more processors may generate a plurality of hidden states. Based on the plurality of hidden states, the one or more processors may generate a plurality of output text tokens. Each output text token may have a corresponding output alignment within the audio input. For each output text token, a latency between the output alignment and the external-model alignment may be below a predetermined latency threshold. The one or more processors may output the text transcription.

Abstract: A computer based system and method for assigning queries to topics and/or visualizing or analyzing query coverage may include, using a computer processor, searching, using a set of queries, over a set of text documents, to produce for each query a set of search results for the query. Each search result may include a subset of text from a text document of the set of text documents. For each query, a query vector may be calculated based on the set of search results for the query, and for each of a set of topics describing the set of text documents, a topic vector may be calculated. A report or visualization may be generated including the set of queries and the set of topics using the topic vectors and the query vectors.

Abstract: Disclosed are a computer implemented method, system and platform for improving the readability and/or coherency of a conversation transcript, which include the applying of a speech disfluency detection model to identify speech disfluencies in a text transcript and to provide a corrected and/or annotated version of the conversation transcript indicating the edits made vis-à-vis the inputted text transcript.

Abstract: An electronic device is provided. The electronic device includes a memory configured to store a speech translation model and at least one processor electronically connected with the memory. The at least one processor is configured to train the speech translation model based on first information related to conversion between a speech in a first language and a text corresponding to the speech in the first language, and second information related to conversion between a text in the first language and a text in a second language corresponding to the text in the first language, and the speech translation model is trained to convert a speech in the first language into a text in the second language and output the text.