Abstract: Techniques regarding identifying candidate knowledge graph subgraphs in a question answering over knowledge graph task are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a question answering over knowledge graph component that encodes graph structure information of a knowledge graph subgraph and a question graph into neural network embeddings.

Abstract: A method for recommending a product, includes: providing product information having a product description, a main image, and a plurality of alternate images; for each alternate image: performing saliency segmentation to obtain a segment and a background, defining a segment bounding box enclosing the segment, extracting image feature from the segment bounding box, extracting textual feature from the product description, extracting main image feature from the main image, matching the image feature of the segment bounding box to the textual feature and the main image feature, and determining the alternate image as a qualified alternate image if the image feature of the segment bounding box matches the textual feature and the main image feature; and when a number of the qualified alternate image equals to or is greater than a threshold number, recommending the product to customers.

Abstract: An adversarial robustness testing method, system, and computer program product include testing, via an accelerator, a robustness of a black-box system under different access settings, where the testing includes tearing down the robustness testing to a subtask of a predetermined size.

Abstract: This application discloses a program compilation method including: obtaining a first program, where the first program includes a plurality of layers of loop statements, a loop condition of each layer of loop statement in the plurality of layers of loop statements includes a variable and a value interval of the variable, and a loop body of the plurality of layers of loop statements includes at least one conditional statement; processing a value interval of a first variable in a first loop statement included in the plurality of layers of loop statements, to obtain a second loop statement; and compiling the first program based on at least one loop statement to obtain a compilation result of the first program.

Abstract: Computer-implemented techniques for unsupervised event extraction are provided. In one instance, a computer implemented method can include parsing, by a system operatively coupled to a processor, unstructured text comprising event information to identify candidate event components. The computer implemented method can further include employing, by the system, one or more unsupervised machine learning techniques to generate structured event information defining events represented in the unstructured text based on the candidate event components.

Abstract: A method (and structure and computer product) of machine translation for processing input questions includes receiving, in a processor on a computer, an input question presented in a natural language. The input question is preprocessed to find one or more condition values for possible Structured Query Language (SQL) queries. One or more possible SQL queries are enumerated based on the one or more found condition values and a paraphrasing model is used to rank the enumerated SQL queries. The highest ranked SQL query is executed against a relational database to search for a response to the input question.

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: An adversarial robustness testing method, system, and computer program product include testing, via an accelerator, a robustness of a black-box system under different access settings, where the testing includes tearing down the robustness testing to a subtask of a predetermined size.

Abstract: Techniques that facilitate graph similarity analytics are provided. In one example, a system includes an information component and a similarity component. The information component generates a first information index indicative of a first entropy measure for a first graph-structured dataset associated with a machine learning system. The information component also generates a second information index indicative of a second entropy measure for a second graph-structured dataset associated with the machine learning system. The similarity component determines similarity between the first graph-structured dataset and the second graph-structured dataset based on a graph similarity computation associated with the first information index and the second information index.

Abstract: A system may include a memory and a processor in communication with the memory. The processor may be configured to perform operations. The operations may include training a neural network and predicting structural feature sets with the neural network. The operations may include producing predicted structures with the neural network using the structural feature sets, converting the predicted structures into predicted graphs with predicted edges, and comparing predicted graphs to training graphs and predicted edges to training edges to obtain a comparison. The operations may include training a model with the comparison, constructing a graph with the neural network using a node feature set, and reducing missing edges in the graph with the model.

Abstract: An adversarial robustness testing method, system, and computer program product include testing a robustness of a black-box system under different access settings via an accelerator.

Abstract: Embodiments of the present invention provide a computer-implemented method for performing unsupervised feature representation learning for text data. The method generates reference text data having a set of random text sequences, in which each text sequence of set of random text sequences is of a random length and comprises a number of random words, and in which each random length is sampled from a minimum length to a maximum length. The random words of each text sequence in the set are drawn from a distribution. The method generates a feature matrix for raw text data based at least in part on a set of computed distances between the set of random text sequences and the raw text data. The method provides the feature matrix as an input to one or more machine learning models.

Abstract: For a passage text and a corresponding answer text, perform a word-level soft alignment to obtain contextualized passage embeddings and contextualized answer embeddings, and a hidden level soft alignment on the contextualized passage embeddings and the contextualized answer embeddings to obtain a passage embedding matrix. Construct a passage graph of the passage text based on the passage embedding matrix, and apply a bidirectional gated graph neural network to the passage graph until a final state embedding is determined, during which intermediate node embeddings are fused from both incoming and outgoing edges. Obtain a graph-level embedding from the final state embedding, and decode the final state embedding to generate an output sequence word-by-word. Train a machine learning model to generate at least one question corresponding to the passage text and the answer text, by evaluating the output sequence with a hybrid evaluator combining cross-entropy evaluation and reinforcement learning evaluation.

Abstract: A computer-implemented method for calculating a similarity between a pair of graph-structured objects by learning-based techniques. The operations include computing the node embeddings of a pair of graph-structured objects of two computer graphs utilizing a hierarchical graph matching network (HGMN). A first component of the HGMN performs graph matching of global-level graph interactions of the two computer graphs. A second component of the HGMN performs graph matching of cross-level node-graph interactions of the two computer graphs. There is an aggregating of features learned from the graph matching of the global-level graph interactions and the cross-level node-graph interactions. At least one of a graph-graph classification or a graph-graph regression is performed utilizing the learned features of the two computer graphs.

Abstract: An approach for a non-factoid question answering framework across tasks and domains may be provided. The approach may include training a multi-task joint learning model in a general domain. The approach may also include initializing the multi-task joint learning model in a specific target domain. The approach may include tuning the joint learning model in the target domain. The approach may include determining which task of the multiple tasks is more difficult for the multi-task joint learning model to learn. The approach may also include dynamically adjusting the weights of the multi-task joint learning model, allowing the model to concentrate on learning the more difficult learning task.

Abstract: Generate, from a logical formula, a directed acyclic graph having a plurality of nodes and a plurality of edges. Assign an initial embedding to each mode and edge, to one of a plurality of layers. Compute a plurality of initial node states by using feed-forward networks, and construct cross-dependent embeddings between conjecture node embeddings and premise node embeddings. Topologically sort the DAG with the initial embeddings and node states. Beginning from a lowest rank, compute layer-by-layer embedding updates for each of the plurality of layers until a root is reached. Assign the embedding update for the root node as a final embedding for the DAG. Provide the final embedding for the DAG as input to a machine learning system, and carry out the automatic theorem proving with same.

Abstract: Task-dependent analysis of various types of data graphs is provided, based at least on generation of a random graph based on node embeddings corresponding to a data graph, and a graph feature matrix corresponding to the data graph based on a distance between the random graph and the data graph.

Abstract: Techniques regarding code retrieval tasks are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a code retrieval component that can execute a code retrieval machine learning task by computing an amount of similarity between neural network embeddings of graph representations of a query text and at least a portion of a computer program code.

Abstract: A method for recommending a product, includes: providing product information having a product description, a main image, and a plurality of alternate images; for each alternate image: performing saliency segmentation to obtain a segment and a background, defining a segment bounding box enclosing the segment, extracting image feature from the segment bounding box, extracting textual feature from the product description, extracting main image feature from the main image, matching the image feature of the segment bounding box to the textual feature and the main image feature, and determining the alternate image as a qualified alternate image if the image feature of the segment bounding box matches the textual feature and the main image feature; and when a number of the qualified alternate image equals to or is greater than a threshold number, recommending the product to customers.