Abstract: A computer-implemented method for determining an answer to a question in a multi-party conversation includes receiving a multi-party conversation having multiple nodes of unstructured natural language. Each node is parsed into a plurality of elements. Each element of the plurality of elements that comprises a question is identified. A conversation node list is constructed that identifies relationships between the nodes. At least one answer to the question is produced based on the conversation node list.

Abstract: A one-time passphrase is transmitted from an authentication system to a personal communication device of a user. The one-time passphrase includes common but incongruous words. The user is prompted to verbalize the one-time passphrase to a processor-implemented, conversational user interface. Utterances from the user are received by a conversational user interface, and the utterances are communicated from the conversational user interface to the authentication system via a trusted communication channel. The authentication system determines, using speech recognition, presence or non-presence of the one-time passphrase within the received utterances. The authentication system authenticates the user in response to detecting presence of the one-time passphrase within the received utterances.

Abstract: One or more documents are received. Each document of the one or more documents is partitioned into segments using stylistic cues from a textual format of each document. Each of the segments is mapped to a respective embedding based on one or more language models. A dependency graph is computed based on the embeddings. A rooted, ordered tree is produced based on the dependency graph. The rooted, ordered tree represents a hierarchical structure of each document.

Abstract: An apparatus (100) that automatically generates suggested responses to an incoming natural language communication includes: a classifier (170) that has been trained to predict one or more style attributes exhibited by natural language communications; a generative natural language model (180) that has been trained to generate responses to natural language communications; and at least one processor which executes computer program code from at least one memory, wherein the at least one memory and the computer program code are configured, with the at least one processor, to cause the apparatus to perform defined operations.

Abstract: A computer-implemented method for determining an answer to a question in a multi-party conversation includes receiving a multi-party conversation having multiple nodes of unstructured natural language. Each node is parsed into a plurality of elements. Each element of the plurality of elements that comprises a question is identified. A conversation node list is constructed that identifies relationships between the nodes. At least one answer to the question is produced based on the conversation node list.