Abstract: Described herein is a mechanism to identify user intent in requests submitted to a system such as a digital assistant or question-answer systems. Embodiments utilize a match methodology instead of a classification methodology. Features derived from a subgraph retrieved from a knowledge base based on the request are concatenated with pretrained word embeddings for both the request and a candidate predicate. The concatenated inputs for both the request and predicate are encoded using two independent LSTM networks and then a matching score is calculated using a match LSTM network. The result is identified based on the matching scores for a plurality of candidate predicates. The pretrained word embeddings allow for knowledge transfer since pretrained word embeddings in one intent domain can apply to another intent domain without retraining.

Abstract: A method of disambiguating user queries in a multi-turn dialogue including a set of user utterances. The method includes using a predefined language model to recognize an ambiguous entity in an unresolved user utterance from the multi-turn dialogue, and using the predefined language model to recognize entity constraints of the ambiguous entity. The method further includes, in a computer-accessible conversation history of the multi-turn dialogue, searching a set of previously-resolved entities for a candidate entity having entity properties with a highest confidence correspondence to the entity constraints of the ambiguous entity. The unresolved user utterance is rewritten as a rewritten utterance that replaces the ambiguous entity with the candidate entity. The rewritten utterance is output to one or more query answering machines.

Abstract: A computer processing pipeline is automatically computer monitored. The computer processing pipeline includes a plurality of ordered computer stages. At least one computer stage is configured to receive an input data set and perform one or more computer processing operations on the input data set to produce an output data set. The output data set is provided as input to another computer stage of the computer processing pipeline. A historical expected schedule is automatically computer generated for compliant execution of the at least one computer stage. The output data set is automatically computer sampled at a designated time dictated by the historical expected schedule. The sampled output data set is automatically computer tested for compliance with one or more detection rules. An anomaly alert that identifies one or more anomalies is automatically computer issued based on non-compliance of the output data set with the one or more detection rules.

Abstract: A method of disambiguating user queries in a multi-turn dialogue including a set of user utterances. The method includes using a predefined language model to recognize an ambiguous entity in an unresolved user utterance from the multi-turn dialogue, and using the predefined language model to recognize entity constraints of the ambiguous entity. The method further includes, in a computer-accessible conversation history of the multi-turn dialogue, searching a set of previously-resolved entities for a candidate entity having entity properties with a highest confidence correspondence to the entity constraints of the ambiguous entity. The unresolved user utterance is rewritten as a rewritten utterance that replaces the ambiguous entity with the candidate entity. The rewritten utterance is output to one or more query answering machines.

Abstract: Described herein is a mechanism to identify user intent in requests submitted to a system such as a digital assistant or question-answer systems. Embodiments utilize a match methodology instead of a classification methodology. Features derived from a subgraph retrieved from a knowledge base based on the request are concatenated with pretrained word embeddings for both the request and a candidate predicate. The concatenated inputs for both the request and predicate are encoded using two independent LSTM networks and then a matching score is calculated using a match LSTM network. The result is identified based on the matching scores for a plurality of candidate predicates. The pretrained word embeddings allow for knowledge transfer since pretrained word embeddings in one intent domain can apply to another intent domain without retraining.

Abstract: A computer processing pipeline is automatically computer monitored. The computer processing pipeline includes a plurality of ordered computer stages. At least one computer stage is configured to receive an input data set and perform one or more computer processing operations on the input data set to produce an output data set. The output data set is provided as input to another computer stage of the computer processing pipeline. A historical expected schedule is automatically computer generated for compliant execution of the at least one computer stage. The output data set is automatically computer sampled at a designated time dictated by the historical expected schedule. The sampled output data set is automatically computer tested for compliance with one or more detection rules. An anomaly alert that identifies one or more anomalies is automatically computer issued based on non-compliance of the output data set with the one or more detection rules.