Oracle International Corporation

Loglogic, Inc.

Groupon, Inc.

Tibco Software Inc.

Boris Galitsky

Sherif Botros

Vishal Vishnoi

Andrey Ozerov

Jian L Zhen

Anfernee Xu

Minjun Liu

Eugene William McKenna

Techniques are disclosed for improved autonomous agents that can provide a recommendation in a non-intrusive, conversational manner. In an aspect, a method determines a first sentiment score for a first utterance and a second sentiment score for a second utterance, each sentiment score indicating an emotion indicated by the respective utterance. The method further identifies that a difference between the first sentiment score and the second sentiment score is greater than a threshold. The method further extracts a noun phrase from the second utterance. The method identifies a text fragment that includes an entity that corresponds to the noun phrase. The method identifies that the text fragment addresses a claim of the second utterance. The method forms a third utterance that includes the a recommendation related to the second utterance and adds the third utterance to the sequence of utterances after the second utterance.

Generating recommendations by using communicative discourse trees of conversations

Systems, devices, and methods discussed herein are directed to generating an answer to an input query using machine reading comprehension techniques and a lattice of supported decision trees. A supported decision tree can be generated from the various decision chains (e.g., a sequence of elements comprising a premise and a decision connected by rhetorical relationships), where the nodes of the decision tree are identified from the plurality of decision chains and ordered based on a set of predefined priority rules. A lattice may include nodes that individually correspond to a respective supported decision tree. Nodes of the lattice may be identified for an input query. The passages corresponding to those nodes may be obtained and an answer for the query may be generated from the obtained passages using machine reading comprehension techniques. The generated answer may be provided in response to the query.

Answer generation using machine reading comprehension and supported decision trees

Techniques are disclosed for generating defeating textual replies. A computer-implemented method generates a first communicative discourse tree from an utterance and as second communicative discourse tree from a candidate answer derived from a search of keywords in the utterance. The method translates the first communicative discourse tree into a first logical formula from and the second communicative discourse tree into a second logical formula. The method determines that the first logical formula is a negation of the second logical formula. The method further provides the candidate answer to a user device responsive to the determining.

Chatbot providing a defeating reply

Methods for generating and utilizing a multi-modal discourse tree (MMDT) are provided herein. An extended discourse tree (EDT) may be generated (e.g., from a discourse tree (DT) or a communicative DT (CDT)) from a corpus of text. Data records (e.g., records contained numerical data) may be linked to the extended discourse tree to generate a multi-modal discourse tree. The multi-modal discourse tree may link any suitable text/records from disparate sources. For example, entities identified from elementary discourse units of the EDT may be matched to an entity of a data record. Causal links may be identified between EDTs and/or data records. Rhetorical relationships can be identified for each entity/causal link match to incorporate the data records with the EDT to generate a MMDT. The MMDT may be used to classify subsequent input, to generate answers to subsequent questions, to navigate the corpus of text and/or data records, or the like.

Techniques for generating multi-modal discourse trees

An autonomous agent receives a user query comprising the complex question. The agent can obtain, from a corpus of unstructured texts, an answer candidate text corresponding to the user query and comprising text from which the answer is subsequently identified. The agent may generate first linguistic data corresponding to the user query and second linguistic data corresponding to the answer candidate text. Each instance of linguistic data may comprise a combination of respective syntactic data, semantic data, and discourse data generated from the user query and/or answer candidate text. Both instances of linguistic data may be provided to a machine-learning model that has been previously trained to output an answer identified from an instance of unstructured text (e.g., the answer candidate text). The model may output the answer identified from the answer candidate text, which in turn may be provided in response to the user query.

Relying on discourse analysis to answer complex questions by neural machine reading comprehension

Methods for correcting raw text generated by deep learning techniques is disclosed. The methods may be performed by systems/computing devices described herein. Raw text previously generated by the deep learning techniques may be obtained. A search query can be generated from a raw text sentence of the raw text. The search query is executed against a knowledge base or a corpus of text to obtain a set of search results, the set of search results comprising a plurality of candidate true sentences that can potentially be utilized to correct one or more entities or phrases of the raw text sentence. A candidate true sentence is selected from the plurality and used to correct the raw text sentence. For example, at least one entity or phrase of the candidate true sentence can be used to replace a corresponding entity or phrase of the raw text sentence.

Correcting content generated by deep learning

Systems, devices, and methods of the present invention involve discourse trees. In an example, a method involves generating a discourse tree. The method includes identifying, from the discourse tree, a central entity that is associated with a rhetorical relation of type elaboration and corresponds to a topic node that identifies a central entity of the text. The method includes determining a subset of elementary discourse units of the discourse tree that are associated with the central entity. The method includes forming generalized phrases from the subset of elementary discourse units. The method includes forming tuples from the generalized phrases, where a tuple is an ordered set of words in normal form. The method involves responsive to successfully converting an elementary discourse unit associated with an identified tuple into a logical representation, updating the ontology with an entity from the identified tuple.

Relying on discourse trees to build ontologies

Systems, devices, and methods of the present invention are related to determining a document classification. For example, a document classification application generates a set of discourse trees, each discourse tree corresponding to a sentence of a document and including a rhetorical relationship that relates two elementary discourse units. The document classification application creates one or more communicative discourse trees from the discourse trees by matching each elementary discourse unit in a discourse tree that has a verb to a verb signature. The document classification application combines the first communicative discourse tree and the second communicative discourse tree into a parse thicket and applies a classification model to the parse thicket in order to determine whether the document is public or private.

Data loss prevention system for cloud security based on document discourse analysis

Disclosed systems, devices, and methods improve dialogue management through the use of dialogue discourse trees (DDTs). To determine whether a candidate response (CR) is appropriate in the dialogue, the CR can be added to other utterances that have been previously provided in a dialogue between two parties and a dialogue discourse tree (DDT) can be generated from the result. The DDT includes nodes corresponding to elementary discourse units (EDUs) representing text fragments of the utterances and the CR. The DDT may include nodes that indicate rhetorical relationships between EDUs. In some embodiments, the DDT comprises a node representing at least one dialogue-specific rhetorical relationship between two utterances. The DDT for the CR can be provided to a machine-learning model that has been trained to identify whether the rhetorical flow is maintained between the utterances of the DDT. If so, the CR can be provided in response to the request.

Techniques for maintaining rhetorical flow

Systems, devices, and methods discussed herein provide improved autonomous agent applications that are configured to generate a diagnosis for input symptoms from labels (e.g., diseases, illnesses, and/or conditions) associated with previously-known cases. Extended discourse trees may be generated that identify multiple discourse trees corresponding to various fragment granularities (e.g., document, paragraph, sentence, phrase, word, etc.) of previously-known cases as well as rhetorical relations between those discourse trees. New symptoms can be provided (e.g., via the autonomous agent) as input. The input can be parsed to identify various fragments of the input and rhetorical relations between the fragments. These fragments can be matched to fragments of previously-known cases by matching nodes of the extended discourse tree. If the rhetorical relations between the input fragments match the rhetorical relations indicated in the extended discourse tree of a previously-known cases, the input may be classified with the same label as those previously-known cases.

Multi case-based reasoning by syntactic-semantic alignment and discourse analysis

Systems, devices, and methods discussed herein provide improved autonomous agent applications that are configured to generate automated answers to a question using summarized logical forms (SLFs). A myriad of techniques may be utilized to generate one or more summarized logical forms for an answer, where the summarized logical form(s) identifies the main entities/informative portions of the answer. Instead of indexing the whole of the answer as in conventional methods, an answer can be indexed using the summarized logical forms. A subsequent query may be converted to logical form to generate a query representation which can be compared to one or more SLFs of a set of answers. If an SLF of an answer matches the query representation, the answer may be provided in response to the question. By indexing the answer with its informative portions, the speed and accuracy of identifying the answer is improved.

Summarized logical forms based on abstract meaning representation and discourse trees

Techniques are disclosed for detecting distributed incompetence in text of a conversation using communicative discourse trees and then inserting an automatic response from an autonomous agent (chatbot) or other entity. For example, a computing system generates a communicative discourse tree from utterances from multiple agents to a user. The computing system obtains a prediction of whether the text includes distributed incompetence by applying a trained predictive model to the communicative discourse tree. Based on the detection, the computing system generates an updated response to a user device.

Using communicative discourse trees to detect distributed incompetence

Systems, devices, and methods of the present invention detect rhetoric agreement between texts. In an example, a rhetoric agreement application accesses a multi-part initial query and generates a question communicative discourse tree that represents rhetorical relationships between fragments of the query. The application identifies a sub-communication discourse tree from the question communicative discourse tree. The application generates a candidate answer communicative discourse tree for each candidate answer of a set of candidate answers. The application computes a level of complementarity between the sub-discourse tree and each candidate answer discourse tree by applying a classification model to the sub-communication discourse tree and candidate answer communicative discourse trees. The application selects an answer from the candidate answers based on the computed complementarity, thereby building a dialogue structure of an interactive session.

Building dialogue structure by using communicative discourse trees

Systems, devices, and methods of the present invention involve discourse trees. In some aspects, a system creates a discourse tree by identifying elementary discourse units in text. The discourse tree includes nodes, each nonterminal node representing a rhetorical relationship between two elementary discourse units and each terminal node associated with an elementary discourse unit. The system identifies, in a reference sentence of the discourse tree, a rhetorical relation of type elaboration or joint. The system selects a candidate sentence having a highest syntactic generalization score of a set of syntactic generalization scores. The system identifies a semantic relation corresponding to the candidate sentence. The semantic relation corresponds to a word in the candidate sentence and defines a role in the candidate sentence. The system replaces, in the discourse tree, the rhetorical relation with an updated rhetorical relation that corresponds to the semantic relation, thereby creating an updated discourse tree.

Growing community of inventors

San Jose, CA, United States of America

Boris Galitsky