Constructing imaginary discourse trees to improve answering convergent questions

Patent metadata

Field	Value
Publication number	US-11782985-B2
Application number	US-202217690897-A
Country	US
Kind code	B2
Filing date	Mar 9, 2022
Priority date	May 9, 2018
Publication date	Oct 10, 2023
Grant date	Oct 10, 2023

Abstract

Systems and methods for improving question-answering recall for complex, multi-sentence, convergent questions. More specifically, an autonomous agent accesses an initial answer that partly answers a question received from a user device. The agent represents the question and the initial answer as discourse trees. From the discourse trees, the agent identifies entities in the question that are not addressed by the answer. The agent forms an additional discourse tree from an additional resource such as a corpus of text. The additional discourse tree rhetorically connects a non-addressed entity with the answer. The agent designates this discourse tree as an imaginary discourse tree. When combined with the initial answer discourse tree, the imaginary discourse tree is used to generate an improved answer relative to existing solutions.

First claim

What is claimed is:

1. A computer-implemented method comprising:
establishing, between a first entity of a first plurality of entities of a first discourse tree and a second entity of a second plurality of entities of a second discourse tree, a mapping that establishes a relevance of the second entity to the first entity, wherein a discourse tree represents rhetorical relationships between elementary discourse units;
responsive to determining that a third entity of the first plurality of entities is not addressed by any of the second plurality of entities, generating an imaginary discourse tree by combining an additional discourse tree with the second discourse tree;
determining, from the first discourse tree, a first communicative discourse tree, wherein a communicative discourse tree is a discourse tree having one or more verb signatures that each comprise a thematic role that indicates a role of a word in a corresponding elementary discourse unit;
determining, from the imaginary discourse tree, a second communicative discourse tree;
computing a level of rhetorical agreement between the first communicative discourse tree and the second communicative discourse tree by applying a predictive model to the first communicative discourse tree and the second communicative discourse tree; and
responsive to determining that the level of rhetorical agreement is above a threshold, outputting text corresponding to the imaginary discourse tree.

2. The method of claim 1 , wherein establishing a mapping comprises:
determining an entity relevance score for an additional entity of the second plurality of entities; and
responsive to determining that the entity relevance score is greater than a threshold, selecting the additional entity as the second entity.

3. The method of claim 1 , wherein the imaginary discourse tree comprises a node representing a rhetorical relationship, the method further comprising integrating the imaginary discourse tree into the second discourse tree by connecting the node to the second entity.

4. The method of claim 1 , wherein generating the imaginary discourse tree comprises:
calculating a relevancy score for each of a plurality of additional discourse trees by applying an additional predictive model to the first discourse tree and the respective additional discourse tree, wherein the relevancy score indicates a relevance of the first discourse tree to the respective additional discourse tree; and
selecting, from the plurality of additional discourse trees, an additional discourse tree with a highest relevancy score as the additional discourse tree.

5. The method of claim 1 , further comprising:
accessing a sentence comprising a plurality of elementary discourse units, wherein at least one elementary discourse unit comprises a verb and a plurality of words, each word comprising a role of the words within the elementary discourse unit; and
generating at least one of the first discourse tree, the second discourse tree, or the additional discourse tree, the generated trees representing rhetorical relationships between the plurality of elementary discourse units.

6. The method of claim 1 further comprising:
constructing at least one of the first communicative discourse tree or the second communicative discourse tree by matching each fragment that has a verb to a verb signature, wherein matching each fragment that has a verb to a verb signature comprises:
accessing a plurality of verb signatures, wherein each verb signature comprises the verb of the fragment 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 fragment;
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 fragment.

7. The method of claim 1 , wherein the applying comprises providing the first communicative discourse tree and the second communicative discourse tree to the predictive model and receiving, from the predictive model, the level of rhetorical agreement.

8. A 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:
establishing, between a first entity of a first plurality of entities of a first discourse tree and a second entity of a second plurality of entities of a second discourse tree, a mapping that establishes a relevance of the second entity to the first entity, wherein a discourse tree represents rhetorical relationships between elementary discourse units;
responsive to determining that a third entity of the first plurality of entities is not addressed by any of the second plurality of entities, generating an imaginary discourse tree by combining an additional discourse tree with the second discourse tree;
determining, from the first discourse tree, a first communicative discourse tree, wherein a communicative discourse tree is a discourse tree having one or more verb signatures that each comprise a thematic role that indicates a role of a word in a corresponding elementary discourse unit;
determining, from the imaginary discourse tree, a second communicative discourse tree;
computing a level of rhetorical agreement between the first communicative discourse tree and the second communicative discourse tree by applying a predictive model to the first communicative discourse tree and the second communicative discourse tree; and
responsive to determining that the level of rhetorical agreement is above a threshold, outputting text corresponding to the imaginary discourse tree.

9. The system of claim 8 , wherein establishing a mapping comprises:
determining an entity relevance score for an additional entity of the second plurality of entities; and
responsive to determining that the entity relevance score is greater than a threshold, selecting the additional entity as the second entity.

10. The system of claim 8 , wherein the imaginary discourse tree comprises a node representing a rhetorical relationship, the system further comprising integrating the imaginary discourse tree into the second discourse tree by connecting the node to the second entity.

11. The system of claim 8 , wherein generating the imaginary discourse tree comprises:
calculating a relevancy score for each of a plurality of additional discourse trees by applying an additional predictive model to the first discourse tree and the respective additional discourse tree, wherein the relevancy score indicates a relevance of the first discourse tree to the respective additional discourse tree; and
selecting, from the plurality of additional discourse trees, an additional discourse tree with a highest relevancy score as the additional discourse tree.

12. The system of claim 8 , wherein executing the computer-executable program instructions configures the processing device to perform operations comprising:
accessing a sentence comprising a plurality of elementary discourse units, wherein at least one elementary discourse unit comprises a verb and a plurality of words, each word comprising a role of the words within the elementary discourse unit; and
generating at least one of the first

Assignees

• Oracle Int Corp

Inventors

• Galitsky Boris

Classifications

• G06F16/3344

  using natural language analysis · CPC title

• G06F16/33295

  in dialogue systems · CPC title

• G06F40/35

  Discourse or dialogue representation · CPC title

• G06F40/295 Primary

  Named entity recognition · CPC title

• G06F16/90332 Primary

  Natural language query formulation or dialogue systems · CPC title