Abstract: An operation method for a memory device is provided. The memory device includes a two-terminal selector and a resistance variable storage element coupled to the two-terminal selector. The method includes providing a voltage pulse to the memory device. A voltage applied across the two-terminal selector during a falling part of the voltage pulse falls below a holding voltage of the two-terminal selector. A voltage falling rate of the falling part at which the voltage applied across the two-terminal selector reaches the holding voltage is raised for reducing threshold voltage drift of the two-terminal selector.

Abstract: A power supply unit supplies power to a load, and the power supply unit includes a power factor corrector, a DC conversion module, and an isolated conversion module. The power factor corrector is plugged into a first main circuit board and converts an AC power into a DC power. The DC conversion module is plugged into the first main circuit board and converts the DC power into a main power. The isolated conversion module includes a bus capacitor, the bus capacitor is coupled to the DC conversion module through a first power copper bar, and coupled to the power factor corrector through a second power copper bar. The first power copper bar and the second power copper bar are arranged on a side opposite to the first main circuit board, and are arranged in parallel with the first main circuit board.

Abstract: Embodiments described herein provide a multi-modal search-and-summarize tool for message platforms. Specifically, the multi-modal search-and-summarize tool may monitor conversational content of different formats, e.g., text, image, video, etc., and use multi-modal summarization models to generate a summary of the conversation channel. The summarization may be conducted via a search-and-summarize process in response to a specific user query, e.g., a user may enter “what did John and Josh say about the presentation tomorrow?” The multi-modal summarization model would first search for relevant conversation messages between user John and user Josh, identify communication files of different format (e.g., text messages, emojis, multimedia attachments, etc.), and then input the communication files to respective text or image encoders to generate a summary of the communication content.

Abstract: A semiconductor die package includes an inductor-capacitor (LC) semiconductor die that is directly bonded with a logic semiconductor die. The LC semiconductor die includes inductors and capacitors that are integrated into a single die. The inductors and capacitors of the LC semiconductor die may be electrically connected with transistors and other logic components on the logic semiconductor die to form a voltage regulator circuit of the semiconductor die package. The integration of passive components (e.g., the inductors and capacitors) of the voltage regulator circuit into a single semiconductor die reduces signal propagation distances in the voltage regulator circuit, which may increase the operating efficiency of the voltage regulator circuit, may reduce the formfactor for the semiconductor die package, may reduce parasitic capacitance and/or may reduce parasitic inductance in the voltage regulator circuit (thereby improving the performance of the voltage regulator circuit), among other examples.

Abstract: A physical analysis method, a sample for physical analysis and a preparing method thereof are provided. The preparing method of the sample for physical analysis includes: providing a sample to be inspected; and forming a contrast enhancement layer on a surface of the sample to be inspected. The contrast enhancement layer includes a plurality of first material layers and a plurality of second material layers stacked upon one another. The first material layer and the second material layer are made of different materials. Each one of the first and second material layers has a thickness that does not exceed 0.1 nm. In an image captured by an electron microscope, a difference between an average grayscale value of a surface layer image of the sample to be inspected and an average grayscale value of an image of the contrast enhancement layer is at least 50.

Abstract: The present invention discloses a vessel tracking and monitoring system and operating method thereof. Specifically, the vessel tracking and monitoring system comprises at least one camera, a processing module and a storage module. On the other hand, the processing module may keep the water object which is detected and recognized by the at least one camera in the center area of a monitoring screen. Therefore, the present invention may track and recognize the type of the at least one water object, assisting areas such as ports in managing and tracking water object arrivals and departures under various environmental conditions.

Abstract: Embodiments described herein provide system of a neural network based news reading tool. The system includes a communication interface receiving one or more text passages from data sources. The system also includes a memory storing a discord question neural model that generates a discord question according to the text passages. The system further includes processors executing processor-executable instructions to perform operations that include determining, by the discord question neural model, respective locations within the one or more text passages for inserting the discord question; receiving, via the communication interface from a client component, an indication that a user device is accessing a first text passage from a first data source; and sending, via the communication interface, the discord question, and a first location corresponding to the first text passage to the user device thereby causing the client component to generate and display a reading interface widget.

Abstract: A semiconductor device according to embodiments of the present disclosure includes a first die including a first bonding layer and a second die including a second hybrid bonding layer. The first bonding layer includes a first dielectric layer and a first metal coil embedded in the first dielectric layer. The second bonding layer includes a second dielectric layer and a second metal coil embedded in the second dielectric layer. The second hybrid bonding layer is bonded to the first hybrid bonding layer such that the first dielectric layer is bonded to the second dielectric layer and the first metal coil is bonded to the second metal coil.

Abstract: An antenna module includes a first antenna radiator including a feeding terminal, a second antenna radiator, a first ground radiator, a second ground radiator and a capacitive element. The second antenna radiator is disposed on one side of the first antenna radiator, and a first gap is formed between a main portion of the second antenna radiator and the first antenna radiator. The first ground radiator is disposed on another side of the first antenna radiator, and a second gap is formed between the first antenna radiator and the first antenna radiator. The second ground radiator is disposed between the second antenna radiator and the first ground radiator, and a third gap is formed between the second ground radiator and a first branch of the second antenna radiator. The capacitive element is disposed on the third gap and connects the second antenna radiator and the second ground radiator.

Abstract: Embodiments described herein provide a method for text summarization. The method includes receiving a training dataset having at least an uncompressed text, a compressed text, and one or more information entities accompanying the compressed text. The method also includes generating, using a perturber model, a perturbed text with the one or more information entities being inserted into the compressed text. The method further includes training the perturber model based on a first training objective, and generating, using the trained perturber model, a perturbed summary in response to an input of a reference summary. The method further includes generating, via an editor model, a predicted summary by removing information from the perturbed summary conditioned on a source document of the reference summary, and training the editor model based on a second training objective.

Abstract: Embodiments described herein provide a document summarization framework that employs an ensemble of summarization models, each of which is a modified version of a base summarization model to control hallucination. For example, a base summarization model may first be trained on a full training data set. The trained base summarization model is then fine-tuned using a first filtered subset of the training data which contains noisy data, resulting in an “anti-expert” model. The parameters of the anti-expert model are subtracted from the parameters of the trained base model to produce a final summarization model which yields robust factual performance.

Abstract: A system uses conversation engines to process natural language requests and conduct automatic conversations with users. The system generates responses to users in an online conversation. The system ranks generated user responses for the online conversation. The system generates a context vector based on a sequence of utterances of the conversation and generates response vectors for generated user responses. The system ranks the user responses based on a comparison of the context vectors and user response vectors. The system uses a machine learning based model that uses a pretrained neural network that supports multiple languages. The system determines a context of an utterance based on utterances in the conversation. The system generates responses and ranks them based on the context. The ranked responses are used to respond to the user.

Abstract: A method for showing objects in an augmented reality environment includes the steps of an Augmented Reality (AR) device obtaining spatial information and object identification (ID) from an anchor device. The AR device obtains parameters of the objects from a cloud system. The parameters of an object include the image of the object, the audio of the object, and a first spatial relationship between the object and an anchor device. The AR device obtains a second spatial relationship between the AR device and the anchor device. A third spatial relationship between the object and the AR device can be obtained according to the first spatial relationship and the second spatial relationship. The image of the object and the audio of the object is displayed or projected in the AR device according to the third spatial relationship.

Abstract: Embodiments described herein provide methods and systems for training task-oriented dialogue (TOD) language models. In some embodiments, a TOD language model may receive a TOD dataset including a plurality of dialogues and a model input sequence may be generated from the dialogues using a first token prefixed to each user utterance and a second token prefixed to each system response of the dialogues. In some embodiments, the first token or the second token may be randomly replaced with a mask token to generate a masked training sequence and a masked language modeling (MLM) loss may be computed using the masked training sequence. In some embodiments, the TOD language model may be updated based on the MLM loss.

Abstract: Embodiments described herein provide a method of evaluating a natural language processing model. The method includes receiving an evaluation dataset that may include a plurality of unit tests, the unit tests having: an input context, and a first candidate and a second candidate that are generated in response to the input context, where the first test candidate is associated with a first quality notation, and the second candidate is associated with a second quality notation. The method includes determining, via a model, a first likelihood of generating the first candidate and a second likelihood of generating the second candidate in response to the input context. The method also includes determining whether the first likelihood being greater than the second likelihood. The method also includes determining whether the first model passed the unit test, where the first quality notation indicates a higher quality candidate and the second quality notation indicate a lower quality candidate.

Abstract: Embodiments described herein provide methods and systems for presenting a document and generating a human-AI summary. A system provides a user with a selection of an amount of time to spend reading the document, or a list of questions from which the user may select which questions they would like answered by reading the document. The system highlights sections of the document according to the user selection. Implicit and explicit user data such as dwell times, user highlights, and user notes, are collected while displaying the document. A human-AI summary is generated based on the document and the user data.

Abstract: Embodiments described herein provide methods and systems for presenting a document and generating a human-AI summary. A system provides a user with a selection of an amount of time to spend reading the document, or a list of questions from which the user may select which questions they would like answered by reading the document. The system highlights sections of the document according to the user selection. Implicit and explicit user data such as dwell times, user highlights, and user notes, are collected while displaying the document. A human-AI summary is generated based on the document and the user data.

Abstract: Embodiments described herein provide systems and methods for an Explicit Memory Tracker (EMT) that tracks each rule sentence to perform decision making and to generate follow-up clarifying questions. Specifically, the EMT first segments the regulation text into several rule sentences and allocates the segmented rule sentences into memory modules, and then feeds information regarding the user scenario and dialogue history into the EMT sequentially to update each memory module separately. At each dialogue turn, the EMT makes a decision among based on current memory status of the memory modules whether further clarification is needed to come up with an answer to a user question. The EMT determines that further clarification is needed by identifying an underspecified rule sentence span by modulating token-level span distributions with sentence-level selection scores. The EMT extracts the underspecified rule sentence span and rephrases the underspecified rule sentence span to generate a follow-up question.

Abstract: Embodiments described herein propose an approach for unsupervised structure extraction in task-oriented dialogues. Specifically, a Slot Boundary Detection (SBD) module is adopted, for which utterances from training domains are tagged with the conventional BIO schema but without the slot names. A transformer-based classifier is trained to detect the boundary of potential slot tokens in the test domain. Next, while the state number is usually unknown, it is more reasonable to assume the slot number is given when analyzing a dialogue system. The detected tokens are clustered into the number of slot of groups. Finally, the dialogue state is represented with a vector recording the modification times of every slot. The slot values are then tracked through each dialogue session in the corpus and label utterances with their dialogue states accordingly. The semantic structure is portrayed by computing the transition frequencies among the unique states.

Abstract: Database systems and methods are provided for assigning structural metadata to records and creating automations using the structural metadata. One method of assigning structural metadata to a record associated with a conversation involves obtaining a plurality of utterances associated with the conversation, the plurality of utterances including at least a first set of utterances by a first actor and a second set of utterances corresponding to a second actor, obtaining a summarization of semantic content of the conversation based at least in part on an initial subset of the plurality of utterances using a summarization model, identifying, from among the first set of utterances corresponding to the first actor, a representative utterance that is closest to the summarization of the semantic content of the conversation, and automatically updating the record associated with the conversation at a database system to include metadata identifying the representative utterance by the first actor.