Abstract: Disclosed herein are optical transceivers with multi-laser modules, as well as related optoelectronic assemblies and methods. In some embodiments, an optical transceiver may include: a first laser and a second laser; an optical output path, wherein an output of the first laser is coupled to the optical output path; and switching circuitry to decouple the output of the first laser from the optical output path and to couple an output of the second laser to the optical output path.

Abstract: A system and method for mind-body relaxation may include a plurality of vibration modules, a light-providing member, a controller, a relaxation substrate, a pillow member, a graphical user interface (GUI), and network connection circuitry.

Abstract: The present disclosure describes systems and methods for dialog processing and information retrieval. Embodiments of the present disclosure provide a dialog system (e.g., a task-oriented dialog system) with adaptive recurrent hopping and dual context encoding to receive and understand a natural language query from a user, manage dialog based on natural language conversation, and generate natural language responses. For example, a memory network can employ a memory recurrent neural net layer and a decision meta network (e.g., a subnet) to determine an adaptive number of memory hops for obtaining readouts from a knowledge base. Further, in some embodiments, a memory network uses a dual context encoder to encode information from original context and canonical context using parallel encoding layers.

Abstract: Embodiments disclosed herein include optoelectronic systems and methods of forming such systems. In an embodiment the optoelectronic system comprises a board, and a carrier attached to the board. In an embodiment, a first die is on the carrier. In an embodiment, the first die is a photonics die, and a surface of the first die is covered by an optically transparent layer.

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: The present invention provides a noise modeling method to improve the speech recognition quality to help the recognition system perform better in real-life environments. With this method, we not only add noise to the training audio signal to simulate different environments, but we also add noise labels to the speech transcripts. Since then, the recognition model will perform better in different environments and increase the accuracy of the recognition model.

Abstract: Certain embodiments involve a method for generating a search result. The method includes processing devices performing operations including receiving a query having a text input by a joint embedding model trained to generate an image result. Training the joint embedding model includes accessing a set of images and textual information. Training further includes encoding the images into image feature vectors based on spatial features. Further, training includes encoding the textual information into textual feature vectors based on semantic information. Training further includes generating a set of image-text pairs based on matches between image feature vectors and textual feature vectors. Further, training includes generating a visual grounding dataset based on spatial information. Training further includes generating a set of visual-semantic joint embeddings by grounding the image-text pairs with the visual grounding dataset.

Abstract: The present disclosure provides a memory-based neural network for question answering. Embodiments of the disclosure identify meta-evidence nodes in an embedding space, where the meta-evidence nodes represent salient features of a training set. Each element of the training set may include a questions appended to a ground truth answer. The training set may also include questions with wrong answers that are indicated as such. In some examples, a neural Turing machine (NTM) reads a dataset and summarizes the dataset into a few meta-evidence nodes. A subsequent question may be appended to multiple candidate answers to form an input phrase, which may also be embedded in the embedding space. Then, corresponding weights may be identified for each of the meta-evidence nodes. The embedded input phrase and the weighted meta-evidence nodes may be used to identify the most appropriate answer.

Abstract: An integrated circuit assembly includes a support (e.g., package substrate or circuit board) and a semiconductor die including a device. The semiconductor die is mounted to the support with the device facing the support. The device can be, for example, a quantum well laser device or a photonics device. A layer of decoupling material is on the device. An underfill material is between the semiconductor die and the support, where the decoupling material is between the device and the underfill material. The decoupling layer decouples stress from transferring from the underfill material into the device. For example, the decoupling material forms only weak bonds with the underfill material and/or a passivation layer on the device, in an embodiment. Weak bonds include non-covalent bonds and non-ionic bonds, for example. The decoupling material can be, for instance, a PTFE film, a poly(p-xylylene) film, a fluorocarbon, or a compound lacking free hydroxyl groups.

Abstract: A computer-implemented method is disclosed for determining one or more characteristics of a dialog between a computer system and user. The method may comprise receiving a system utterance comprising one or more tokens defining one or more words generated by the computer system; receiving a user utterance comprising one or more tokens defining one or more words uttered by a user in response to the system utterance, the system utterance and the user utterance forming a dialog context; receiving one or more utterance candidates comprising one or more tokens; for each utterance candidate, generating an input sequence combining the one or more tokens of each of the system utterance, the user utterance, and the utterance candidate; and for each utterance candidate, evaluating the generated input sequence with a model to determine a probability that the utterance candidate is relevant to the dialog context.

Abstract: A method for controlling an automated vehicle. In a first method part, the instantaneous surroundings of the automated vehicle are detected using an on-board surroundings sensor system. A localization of the automated vehicle takes place based on a comparison of the data of the surroundings sensor system to a previously provided HD localization map. A map-based surroundings model is generated, in a second method part representing a normal mode, and is used for planning the behavior and the trajectory of the automated vehicle. In a third method part representing a safety mode, carried out in parallel to or as an alternative to the first method part, the instantaneous surroundings of the automated vehicle are detected using the on-board surroundings sensor system. Based on the data ascertained in the process, a map-less surroundings model is generated and used for planning the behavior and the trajectory of the automated vehicle.

Abstract: Methods and apparatus to reduce stress on lasers in optical transceivers are disclosed. An apparatus comprising a printed circuit board (PCB) having a first side and a second side opposite the first side; and a first stiffener attached to the first side of the PCB; and a photonic integrated circuit (PIC) attached to the first stiffener. The first stiffener is between the PIC and the PCB. The apparatus also includes a second stiffener attached to the second side of the PCB.

Abstract: A microelectronic device includes a stack structure including a vertically alternating sequence of conductive structures and insulating structures arranged in tiers, a dielectric-filled opening vertically extending into the stack structure and defined between two internal sidewalls of the stack structure, a stadium structure within the stack structure and comprising steps defined by horizontal ends of at least some of the tiers, a first ledge extending upward from a first uppermost step of the steps of the stadium structure and interfacing with a first internal sidewall of the two internal sidewalls of the stack structure, and a second ledge extending upward from a second, opposite uppermost step of the steps of the stadium structure and interfacing with a second, opposite internal sidewall of the two internal sidewalls.

Abstract: A neutral to alkaline chemical mechanical composition for polishing tungsten includes, as initial components: water; an oxidizing agent selected from an iodate compound, a periodate compound and mixtures thereof; colloidal silica abrasive particles including a nitrogen-containing compound; optionally, a pH adjusting agent; and, optionally, a biocide. The chemical mechanical polishing method includes providing a chemical mechanical polishing pad, having a polishing surface; creating dynamic contact at an interface between the polishing pad and the substrate; and dispensing the neutral to alkaline chemical mechanical polishing composition onto the polishing surface at or near the interface between the polishing pad and the substrate; wherein some of the tungsten is polished away from the substrate and, further, to at least inhibit static etch of the tungsten.

Abstract: Microelectronic devices include a lower deck and an upper deck, each comprising a stack structure with a vertically alternating sequence of insulative structures and conductive structures arranged in tiers. A lower array of pillars extends through the stack structure of the lower deck, and an upper array of pillars extends through the stack structure of the upper deck. Along an interface between the lower deck and the upper deck, the pillars of the lower array align with the pillars of the upper array. At least at elevations comprising bases of the pillars, a pillar density of the pillars of the lower array differs from a pillar density of the pillars of the upper array, “pillar density” being a number of pillars per unit of horizontal area of the respective array. Related methods and electronic systems are also disclosed.

Abstract: The present invention provides a method for speech separation and recognition. The present invention overcomes the disadvantages of the existing techniques by providing automatic speech recognition and separation that helps managers see what their service agents and customers are saying. From there, quickly and objectively knowing the wishes and concerns of customers as well as whether their service agents can give accurate and correct advice. In addition, the system is constantly updated based on the semi-supervised training mechanism, which means that the system can self-learn from actual data during operation, thereby helping to improve the system's accuracy.

Abstract: Systems and methods for parsing natural language sentences using an artificial neural network (ANN) are described. Embodiments of the described systems and methods may generate a plurality of word representation matrices for an input sentence, wherein each of the word representation matrices is based on an input matrix of word vectors, a query vector, a matrix of key vectors, and a matrix of value vectors, and wherein a number of the word representation matrices is based on a number of syntactic categories, compress each of the plurality of word representation matrices to produce a plurality of compressed word representation matrices, concatenate the plurality of compressed word representation matrices to produce an output matrix of word vectors, and identify at least one word from the input sentence corresponding to a syntactic category based on the output matrix of word vectors.

Abstract: This disclosure describes one or more implementations of a text sequence labeling system that accurately and efficiently utilize a joint-learning self-distillation approach to improve text sequence labeling machine-learning models. For example, in various implementations, the text sequence labeling system trains a text sequence labeling machine-learning teacher model to generate text sequence labels. The text sequence labeling system then creates and trains a text sequence labeling machine-learning student model utilizing the training and the output of the teacher model. Upon the student model achieving improved results over the teacher model, the text sequence labeling system re-initializes the teacher model with the learned model parameters of the student model and repeats the above joint-learning self-distillation framework. The text sequence labeling system then utilizes a trained text sequence labeling model to generate text sequence labels from input documents.

Abstract: This disclosure describes one or more implementations of systems, non-transitory computer-readable media, and methods that extract multiple attributes from an object portrayed in a digital image utilizing a multi-attribute contrastive classification neural network. For example, the disclosed systems utilize a multi-attribute contrastive classification neural network that includes an embedding neural network, a localizer neural network, a multi-attention neural network, and a classifier neural network. In some cases, the disclosed systems train the multi-attribute contrastive classification neural network utilizing a multi-attribute, supervised-contrastive loss. In some embodiments, the disclosed systems generate negative attribute training labels for labeled digital images utilizing positive attribute labels that correspond to the labeled digital images.

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.