US 11,537,645 B2Granted

Building dialogue structure by using communicative discourse trees

AssigneeOracle International Corporation

InventorBoris Galitsky

Life of this patent

Estimating the term…

Loading patent…

Abstract

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-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-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.

Claims16

Dependent claims

A method for managing a session of dialogue with an autonomous agent, the method comprising:

generating, from a question sentence comprising text, a question communicative discourse tree that represents rhetorical relationships between elementary discourse units in the text, at least one of the elementary discourse units comprising a verb and a plurality of words, wherein generating the question communicative discourse tree comprises:
generating, from the text, a discourse tree that represents rhetorical relationships between the elementary discourse units, wherein the discourse tree comprises nodes, each nonterminal node of the nodes representing a rhetorical relationship between two of the elementary discourse units, and each terminal node of the nodes is associated with one of the elementary discourse units;
accessing a plurality of verb signatures, wherein each verb signature comprises the verb of the respective elementary discourse unit and a sequence of thematic roles, wherein thematic roles describe a relationship between the verb and related words;
determining, for each verb signature of the plurality of verb signatures, a plurality of thematic roles of the respective signature that match a role of a word in the respective elementary discourse unit;
selecting a particular verb signature from the plurality of verb signatures based on the particular verb signature comprising a highest number of matches;
and
associating the particular verb signature with the respective elementary discourse unit;
identifying a question sub-communicative discourse tree from the question communicative discourse tree, wherein the question sub-communicative discourse tree comprises at least one of the elementary discourse units having a corresponding verb signature and represents a sub-question;
accessing a plurality of candidate answers, each candidate answer comprising a plurality of elementary discourse units;
generating, for each candidate answer of a plurality of candidate answers, a candidate answer communicative discourse tree that represents rhetorical relationships between elementary discourse units in the respective candidate answer;
for each candidate answer, computing a level of rhetorical agreement between the question sub-communicative discourse tree and the respective candidate answer communicative discourse tree, the computing comprising:
pairing the question sub-communicative discourse tree and the respective candidate answer discourse tree;
applying a classification model to the paired tree;
and
receiving, from the classification model, the computed level of rhetorical agreement;
selecting an answer from the candidate answers based on the computed level of rhetorical agreement;
and
providing the selected answer to a user device.

15 more elements

A system for managing a session of dialogue with an autonomous agent, the system comprising:

a non-transitory computer-readable medium storing computer-executable program instructions;
and
a processing device communicatively coupled to the non-transitory computer-readable medium for executing the computer-executable program instructions, wherein executing the computer-executable program instructions configures the processing device to perform operations comprising:
generating, from a question sentence comprising text, a question communicative discourse tree that represents rhetorical relationships between elementary discourse units in the text, at least one of the elementary discourse units comprising a verb and a plurality of words, wherein generating the question communicative discourse tree comprises:
generating, from the text, a discourse tree that represents rhetorical relationships between the elementary discourse units, wherein the discourse tree comprises nodes, each nonterminal node of the nodes representing a rhetorical relationship between two of the elementary discourse units, and each terminal node of the nodes is associated with one of the elementary discourse units;
accessing a plurality of verb signatures, wherein each verb signature comprises the verb of the respective elementary discourse unit and a sequence of thematic roles, wherein thematic roles describe a relationship between the verb and related words;
determining, for each verb signature of the plurality of verb signatures, a plurality of thematic roles of the respective signature that match a role of a word in the respective elementary discourse unit;
selecting a particular verb signature from the plurality of verb signatures based on the particular verb signature comprising a highest number of matches;
and
associating the particular verb signature with the respective elementary discourse unit;
identifying a question sub-communicative discourse tree from the question communicative discourse tree, wherein the question sub-communicative discourse tree comprises at least one of the elementary discourse units having a corresponding verb signature and represents a sub-question;
accessing a plurality of candidate answers, each candidate answer comprising a plurality of elementary discourse units;
generating, for each candidate answer of a plurality of candidate answers, a candidate answer communicative discourse tree that represents rhetorical relationships between elementary discourse units in the respective candidate answer;
for each candidate answer, computing a level of rhetorical agreement between the question sub-communicative discourse tree and the respective candidate answer communicative discourse tree, the computing comprising:
pairing the question sub-communicative discourse tree and the respective candidate answer discourse tree;
applying a classification model to the paired tree;
and
receiving, from the classification model, the computed level of rhetorical agreement;
selecting an answer from the candidate answers based on the computed level of rhetorical agreement;
and
providing the selected answer to a user device.

18 more elements

A non-transitory computer-readable storage medium storing computer-executable program instructions, wherein when executed by a processing device, the computer-executable program instructions cause the processing device to perform operations comprising:

generating, from a question sentence comprising text, a question communicative discourse tree that represents rhetorical relationships between elementary discourse units in the text, at least one of the elementary discourse units comprising a verb and a plurality of words, wherein generating the question communicative discourse tree comprises:
generating, from the text, a discourse tree that represents rhetorical relationships between the elementary discourse units, wherein the discourse tree comprises nodes, each nonterminal node of the nodes representing a rhetorical relationship between two of the elementary discourse units, and each terminal node of the nodes is associated with one of the elementary discourse units;
accessing a plurality of verb signatures, wherein each verb signature comprises the verb of the respective elementary discourse unit and a sequence of thematic roles, wherein thematic roles describe a relationship between the verb and related words;
determining, for each verb signature of the plurality of verb signatures, a plurality of thematic roles of the respective signature that match a role of a word in the respective elementary discourse unit;
selecting a particular verb signature from the plurality of verb signatures based on the particular verb signature comprising a highest number of matches;
and
associating the particular verb signature with the respective elementary discourse unit;
identifying a question sub-communicative discourse tree from the question communicative discourse tree, wherein the question sub-communicative discourse tree comprises at least one of the elementary discourse units having a corresponding verb signature and represents a sub-question;
accessing a plurality of candidate answers, each candidate answer comprising a plurality of elementary discourse units;
generating, for each candidate answer of a plurality of candidate answers, a candidate answer communicative discourse tree that represents rhetorical relationships between elementary discourse units in the respective candidate answer;
for each candidate answer, computing a level of rhetorical agreement between the question sub-communicative discourse tree and the respective candidate answer communicative discourse tree, the computing comprising:
pairing the question sub-communicative discourse tree and the respective candidate answer discourse tree;
applying a classification model to the paired tree;
and
receiving, from the classification model, the computed level of rhetorical agreement;
selecting an answer from the candidate answers based on the computed level of rhetorical agreement;
and
providing the selected answer to a user device.

15 more elements

Dependencies are inferred from the claim text.

Facts

Application: 16/240,232Filed 4 Jan 2019 · us provisional application
Priority: 30 Jan 2018
Published: US 2019/0236085 A11 Aug 2019
Granted: 27 Dec 2022
Term ends: Not estimatedThe source records don’t support an estimate.

Classification13 codes

G06F 16/3329
Query formulation: natural language query formulation
G06F 16/322
Indexing structures: trees
G06F 16/3349
Query processing: reuse of stored results of previous queries
G06F 18/24147
Based on distances to training or reference patterns: distances to closest patterns, e.g. nearest neighbour classification

Family

Application62/623,996Us provisional application · filed 30 Jan 2018
Application62/646,759Us provisional application · filed 22 Mar 2018
Application62/729,335Us provisional application · filed 10 Sep 2018
Application62/746,261Us provisional application · filed 16 Oct 2018
US 2019/0236085 A1Pre-grant publication · published 1 Aug 2019
US 11,537,645 B2This patent

From the US filing history. Foreign family members aren’t listed.