Abstract: The present disclosure is directed to systems and methods for performing reading comprehension with machine learning. More specifically, the present disclosure is directed to a Neural Symbolic Reader (example implementations of which may be referred to as NeRd), which includes a reader to encode the passage and question, and a programmer to generate a program for multi-step reasoning. By using operators like span selection, the program can be executed over a natural language text passage to generate an answer to a natural language text question. NeRd is domain-agnostic such that the same neural architecture works for different domains. Further, NeRd is compositional such that complex programs can be generated by compositionally applying the symbolic operators.

Abstract: Obtain, at a computing device, a segment of computer code. With a classification module of a machine learning system executing on the computing device, determine a required annotation category for the segment of computer code. With an annotation generation module of the machine learning system executing on the computing device, generate a natural language annotation of the segment of computer code based on the segment of computer code and the required annotation category. Provide the natural language annotation to a user interface for display adjacent the segment of computer code.

Abstract: Techniques for implementing a streaming remote procedure call (RPC) mechanism using distributed processing components of a system are described. A first processing component sends a connect message to a second processing component. Thereafter, the first processing component sends different instances of data to the second processing component as the different instances of data are determined by the first processing component. The second processing component performs at least some processes as the second processing component receives the different instances of data. After the first processing component sends all relevant data to the second processing component, the first processing component sends a commit message to the second processing component. Based at least in part on receiving the commit message, the second processing component determines finishes its processing, and sends result data to the first processing component.

Abstract: Systems and methods for natural language processing are described. One or more embodiments of the present disclosure receive a document comprising a plurality of words organized into a plurality of sentences, the words comprising an event trigger word and an argument candidate word, generate word representation vectors for the words, generate a plurality of document structures including a semantic structure for the document based on the word representation vectors, a syntax structure representing dependency relationships between the words, and a discourse structure representing discourse information of the document based on the plurality of sentences, generate a relationship representation vector based on the document structures, and predict a relationship between the event trigger word and the argument candidate word based on the relationship representation vector.

Abstract: A system and method are disclosed that enable rapid and cost-effective human-in-the-loop synthesis of domain-specific textual training data for a deep learning model. The data augmentation process incorporates a sentence generator, a sentence classifier, and weak-supervision by a domain expert that is ‘in the loop.’ Generally, both the sentence generator and the sentence classifier are implemented as machine learning models. The sentence generator generates new sentences based on manually labeled sentences and the sentence classifier generates labels for the newly generated sentences. The new sentences are corrected or verified by a domain expert and then used to retrain one or both of the sentence generator and the sentence classifier.

Abstract: A system for knowledge graph construction. The system includes a computing device. The computing device has a processor and a storage device storing computer executable code. The computer executable code, when executed at the processor, is configured to: define entities and relations of the knowledge graph; provide documents having sentences; convert the sentences into fix length sentence embeddings and regard the sentence embeddings as primary capsule layers; use a set transformer to learn entity capsules and relation capsules from the primary capsule layers; for each triple, project head and tail entities from entity space to the specific relation space, and determine the relation exists when the sum of the projected head entity vector and the relation vector substantially equals to the projected tail entity vector; and construct the knowledge graph using the head entity, the tail entity, and the determined relation.

Abstract: A method comprises obtaining, by a computing system, first audio data representing one or more initial utterances during an interactive voice session with an interactive voice system; generating, by the computing system, based on the first audio data, a prediction regarding whether a subsequent utterance of a user during the interactive voice session will contain sensitive information, the subsequent utterance following the one or more initial utterances in time; obtaining, by the computing system, second audio data representing the subsequent utterance; determining, by the computing system, based on the prediction, whether to transmit the second audio data; and based on a determination not to transmit the second audio data: replacing, by the computing system, the second audio data with third audio data that is based on a voice of the user; and transmitting, by the computing system, the third audio data.

Abstract: A current observation expressed in natural language is received. Entities in the current observation are extracted. A relevant historical observation is retrieved, which has at least one of the entities in common with the current observation. The current observation and the relevant historical observation are combined as observations. The observations and a template list specifying a list of verb phrases to be filled-in with at least some of the entities are input to a neural network, which can output the template list of the verb phrases filled-in with said at least some of the entities. The neural network can include attention mechanism. A reward associated with the neural network's output can be received and fed back to the neural network for retraining the neural network.

Abstract: The present disclosure provides a novel sentence-level representation learning method Conditional Masked Language Modeling (CMLM) for training on large scale unlabeled corpora. CMLM outperforms the previous state-of-the-art English sentence embedding models, including those trained with (semi-)supervised signals. For multilingual representations learning, it is shown that co-training CMLM with bitext retrieval and cross-lingual natural language inference (NL) fine-tuning achieves state-of-the-art performance. It is also shown that multilingual representations have the same language bias and principal component removal (PCR) can eliminate the bias by separating language identity information from semantics.

Abstract: A portable radio may include a radio frequency (RF) transmitter, an RF receiver, and an audio input transducer. A controller may store command messages and speech messages, implement a stand-alone, speech recognition and text-to-speech (TTS) function for the stored command messages and stored speech messages. The controller may also control at least one of an RF transmitter and RF receiver of a remote radio based upon an input command matching one of the stored command messages using the audio input transducer and the stand-alone speech recognition and TTS function, and convert a speech message matching one of the stored speech messages into a text message. The RF transmitter may send the text message to the remote receiver.

Abstract: Systems and methods of the present disclosure are directed to a method for predicting semantic similarity between documents. The method can include obtaining a first document and a second document. The method can include parsing the first document into a plurality of first textual blocks and the second document into a plurality of second textual blocks. The method can include processing each of the plurality of first textual blocks and the second textual blocks with a machine-learned semantic document encoding model to obtain a first document encoding and a second document encoding. The method can include determining a similarity metric descriptive of a semantic similarity between the first document and the second document based on the first document encoding and the second document encoding.

Abstract: A computer receives a multimedia data, where the multimedia data comprises a plurality of frames. The computer converts the multimedia data into a signal wave having a plurality of frequencies and a plurality of amplitudes. The computer determines a frame from the plurality of frames having a pronoun. The computer identifies a topic of the frame. The computer searches for a frame in a media repository having a highest correlation coefficient with the topic of the frame, where the frame from the media repository comprises a bag of objects and resolves the anaphora disambiguation by substituting the pronoun with an object from the bag of objects.

Abstract: Disclosed is a machine learning-based media success prediction through plot summaries According to an embodiment, a method comprises performing preprocessing on text data including a plot summary, calculating a sentiment score from the preprocessed text data using a first model, generating first input data using the calculated sentiment score, generating second input data from the preprocessed data using a second model, and determining a candidate class of content corresponding to the plot summary by applying the first input data and the second input data to a pre-trained third model. The candidate class includes a first class indicating success and a second class indicating failure.

Abstract: A system for automating a process using robotic process automation code includes a memory device for storing program code, and at least one processor device operatively coupled to the memory device. The at least one processor device is configured to execute program code stored on the memory device to process, based on a contextual dictionary, a process description document associated with a process to be automated by a robotic process automation system, automatically generate robotic process automation code based on the processing, and execute the robotic process automation code for automating the process.