System and method for generating dialogue graphs
A method, computer program product, and computing system for automatically generating a dialogue graph is executed on a computing device and includes receiving a plurality of conversation data. A plurality of utterance pairs from the plurality of conversation data may be clustered into a plurality of utterance pair clusters. A dialogue graph may be generated with a plurality of nodes representative of the plurality of utterance pair clusters.
1. A computer-implemented method for automatically generating a dialogue graph, executed on a computing device, comprising:
receiving, at the computing device, a plurality of conversation data;
clustering the plurality of conversation data into a plurality of topic clusters;
clustering a plurality of utterance pairs from the plurality of conversation data into a plurality of utterance pair clusters, wherein each utterance pair represents at least a portion of a single exchange between a plurality of participants associated with the conversation data, wherein clustering the plurality of utterance pairs from the plurality of conversation data into the plurality of utterance pair clusters includes:
for at least one topic cluster of the plurality of topic clusters, converting the plurality of utterance pairs into a plurality of feature vectors representative of the plurality of utterance pairs, and
comparing the plurality of feature vectors representative of the plurality of utterance pairs;
generating a dialogue graph with a plurality of nodes representative of the plurality of utterance pair clusters;
receiving one or more modifications to the dialogue graph, the one or more modifications including one or more of:
a selection of a plurality of nodes to merge, and
a selection of a node from the plurality of nodes to split into separate nodes representative of distinct utterance pairs clusters; and
performing the one or more modifications on the dialogue graph.
2. The computer-implemented method of claim 1 , wherein receiving the plurality of conversation data includes one or more of:
receiving a plurality of chat transcripts; and
converting one or more audio recordings of one or more conversations into one or more text-based representations of the one or more conversations.
3. The computer-implemented method of claim 1 , wherein clustering the plurality of conversational data into a plurality of topic clusters includes:
generating a plurality of feature vectors representative of the plurality of conversation data; and
comparing the plurality of feature vectors representative of the plurality of conversation data.
4. The computer-implemented method of claim 1 , further comprising:
generating one or more labels for at least one node of the plurality of nodes representative of the plurality of utterance pair clusters.
5. A computer program product residing on a non-transitory computer readable medium having a plurality of instructions stored thereon which, when executed by a processor, cause the processor to perform operations comprising:
receiving a plurality of conversation data;
clustering the plurality of conversation data into a plurality of topic clusters;
clustering a plurality of utterance pairs from the plurality of conversation data into a plurality of utterance pair clusters, wherein each utterance pair represents at least a portion of a single exchange between a plurality of participants associated with the conversation data, wherein clustering the plurality of utterance pairs from the plurality of conversation data into the plurality of utterance pair clusters includes:
for at least one topic cluster of the plurality of topic clusters, converting the plurality of utterance pairs into a plurality of feature vectors representative of the plurality of utterance pairs, and
comparing the plurality of feature vectors representative of the plurality of utterance pairs;
generating a dialogue graph with a plurality of nodes representative of the plurality of utterance pair clusters;
receiving one or more modifications to the dialogue graph, the one or more modifications including one or more of:
a selection of a plurality of nodes to merge, and
a selection of a node from the plurality of nodes to split into separate nodes representative of distinct utterance pairs clusters; and
performing the one or more modifications on the dialogue graph.
6. The computer program product of claim 5 , wherein receiving the plurality of conversation data includes one or more of:
receiving a plurality of chat transcripts; and
converting one or more audio recordings of one or more conversations into a text-based representation of the one or more conversations.
7. The computer program product of claim 5 , wherein clustering the plurality of conversational data into a plurality of topic clusters includes:
generating a plurality of feature vectors representative of the plurality of conversation data; and
comparing the plurality of feature vectors representative of the plurality of conversation data.
8. The computer program product of claim 5 , further comprising:
generating one or more labels for at least one node of the plurality of nodes representative of the plurality of utterance pair clusters.
9. A computing system including a processor and memory configured to perform operations comprising:
receiving a plurality of conversation data;
clustering the plurality of conversation data into a plurality of topic clusters;
clustering a plurality of utterance pairs from the plurality of conversation data into a plurality of utterance pair clusters, wherein each utterance pair represents at least a portion of a single exchange between a plurality of participants associated with the conversation data, wherein clustering the plurality of utterance pairs from the plurality of conversation data into the plurality of utterance pair clusters includes:
for at least one topic cluster of the plurality of topic clusters, converting the plurality of utterance pairs into a plurality of feature vectors representative of the plurality of utterance pairs, and
comparing the plurality of feature vectors representative of the plurality of utterance pairs;
generating a dialogue graph with a plurality of nodes representative of the plurality of utterance pair clusters;
receiving one or more modifications to the dialogue graph, the one or more modifications including one or more of:
a selection of a plurality of nodes to merge, and
a selection of a node from the plurality of nodes to split into separate nodes representative of distinct utterance pairs clusters; and
performing the one or more modifications on the dialogue graph.
10. The computing system of claim 9 , wherein receiving the plurality of conversation data includes one or more of:
receiving a plurality of chat transcripts; and
converting one or more audio recordings of one or more conversations into a text-based representation of the one or more conversations.
11. The computing system of claim 9 , wherein clustering the plurality of conversational data into a plurality of topic clusters includes:
generating a plurality of feature vectors representative of the plurality of conversation data; and
comparing the plurality of feature vectors representative of the plurality of conversation data.
12. The computing system of claim 9 , further comprising:
generating one or more labels for at least one node of the plurality of nodes representative of the plurality of utterance pair clusters.