Knowledge Canvassing Using a Knowledge Graph and a Question and Answer System

Abstract

Mechanisms are provided for processing a knowledge canvassing request. The mechanisms receive a request specifying an entity of interest from an originator of the request and analyze the request to extract a feature of the request. The mechanisms determine whether the request is a targeted natural language question to be answered or a knowledge canvassing request, based on the extracted feature. In response to determining that the request is a knowledge canvassing request, the mechanisms process the request by identifying entities represented in a knowledge graph data structure as being related to the entity of interest. The mechanisms output results of the processing of the request to the originator of the request.

1 . A method, in a data processing system comprising a processor and a memory, for processing a knowledge canvassing request, the method comprising:
 receiving, by the data processing system, a request specifying at least one entity of interest from an originator of the request;   analyzing, by the data processing system, the request to extract one or more features of the request;   determining, by the data processing system, whether the request is a targeted natural language question to be answered by the data processing system or a knowledge canvassing request, based on the one or more extracted features;   in response to determining that the request is a knowledge canvassing request, processing, by the data processing system, the request by identifying entities represented in a knowledge graph data structure as being related to the at least one entity of interest; and   outputting, by the data processing system, results of the processing of the request to the originator of the request.   
     
     
         2 . The method of  claim 1 , wherein the data processing system comprises a factoid question and answer (QA) system pipeline and a knowledge canvassing pipeline, and wherein the method further comprises:
 in response to determining that the request is a targeted natural language question, routing, by the data processing system, the request to the factoid QA system pipeline which processes the request as a natural language question using natural language processing (NLP) mechanisms; and   in response to determining that the request is a knowledge canvassing request, routing, by the data processing system, the request to the knowledge canvassing pipeline which performs the processing of the request by identifying entities represented in the knowledge graph data structure as being related to the at least one entity of interest.   
     
     
         3 . The method of  claim 1 , wherein the knowledge graph data structure comprises a plurality of nodes representing different entities identified in a corpus of information ingested by the data processing system, and edges between nodes representing relationships between the entities corresponding to the nodes as identified by analyzing a context of references to the entities in the corpus of information. 
     
     
         4 . The method of  claim 3 , wherein processing the request by identifying entities represented in the knowledge graph data structure as being related to the at least one entity of interest comprises identifying at least one node in the knowledge graph corresponding to the at least one entity of interest and related entities connected to the at least one node by one or more edges in the knowledge graph data structure. 
     
     
         5 . The method of  claim 4 , wherein processing the request further comprises ranking the related entities by scoring each related entity in accordance with a relatedness metric associated with edges connecting the related entity to the at least one entity of interest, and wherein outputting results of the processing comprises outputting a ranked listing of the related entities based on the ranking of the related entities. 
     
     
         6 . The method of  claim 5 , wherein the relatedness metric is an inverse document frequency (IDF) metric representing a degree of rarity of the relationship between the related entity and the entity of interest in the corpus of information. 
     
     
         7 . The method of  claim 5 , wherein the ranking of the related entities is performed in accordance with a domain specific ranking criteria indicating a criteria that is of greater desirability in the context of the domain. 
     
     
         8 . The method of  claim 5 , further comprising receiving a user input selecting a related entity in the ranked listing of related entities to be a new entity of interest, and repeating the method with the new entity of interest being the entity of interest associated with a new request to identify related entities. 
     
     
         9 . The method of  claim 5 , wherein scoring each related entity comprises generating, for the related entity, a context independent score and a context dependent score, and calculating a score for the related entity based on a combination of the context independent score and the context dependent score. 
     
     
         10 . The method of  claim 1 , wherein outputting results of the processing of the request to the originator of the request comprises outputting results comprising a listing of one or more related entities and, for each related entity of the one or more related entities, a portion of at least one text passage from a corpus of information in which a relationship of the related entity with the entity of interest is referenced. 
     
     
         11 - 21 . (canceled)