Determining conversational structure from speech
Embodiments are directed to organizing conversations. Words may be provided from a conversation stream. Each word may be mapped to a graph model based on characteristics of each word. The graph model may be partitioned based on one or more attributes of a nodes and edges included in the graph model such that nodes associated with relationship strength that exceeds a threshold value may be grouped together. Sentence models may be generated based on sentences included in the conversation stream. Combined models may be generated based on the sentence models and the graph such that each sentence model may be associated with one or more partitions of the graph model. A conversation digest may be generated based on the combined model such that the conversation digest identifies one or more dominant portions of the conversation that include key subject matter.
1. A method for organizing conversations over a network using one or more network computers that include one or more processors that perform actions, comprising:
providing a graph model for a conversation based on one or more words provided by a conversation stream;
generating one or more sentence models based on the one or more words, wherein each sentence model provides one or more key phrases for each sentence;
generating a combined model that associates one or more partitions of the graph model and the one or more key phrases with one or more portions of the conversation stream;
employing the combined model to determine one or more dominance scores for the one or more portions of the conversation stream based on a strength of the correlation between the one or more key phrases and the one or more partitions of the graph model; and
determining one or more context switches in the conversation based on the one or more dominance scores, wherein the one or more context switches are employed to identify one or more of topics or sub-topics in the conversation.
2. The method of claim 1 , wherein the one or more words, further comprise:
associating each word with a node in the graph model and each edge in the graph model corresponds to one or more relationships between each word.
3. The method of claim 1 , further comprising:
corresponding each sentence model to a sentence in the conversation.
4. The method of claim 1 , wherein generation of the combined model further comprises:
correlating the one or more key phrases with the one or more partitions of the graph model.
5. The method of claim 1 , wherein determination of the one or more context switches, further comprises:
determining a transition from a portion of the conversation stream associated with a dominance score that exceeds a threshold value to another portion of the conversation stream associated with another dominance score that is below another threshold value that corresponds to each context switch.
6. The method of claim 1 , further comprising:
categorizing the one or more partitions into two or more types based on one or more of characteristics of each word that is included in a partition and each relationship between each word that is included in the partition.
7. The method of claim 1 , further comprising:
determining one or more phrasal scores for one or more portions of each sentence;
refining the one or more phrasal scores for each sentence based on a repetition of each word, a degree of each word, or a length of each sentence; and
employing the one or more refined phrasal scores to rank order one or more key words for the conversation.
8. A system for organizing conversation information over a network, comprising:
a network computer, comprising:
a memory that stores at least instructions; and
one or more processors that execute instructions that perform actions, including:
providing a graph model for a conversation based on one or more words provided by a conversation stream;
generating one or more sentence models based on the one or more words, wherein each sentence model provides one or more key phrases for each sentence;
generating a combined model that associates one or more partitions of the graph model and the one or more key phrases with one or more portions of the conversation stream;
employing the combined model to determine one or more dominance scores for the one or more portions of the conversation stream based on a strength of the correlation between the one or more key phrases and the one or more partitions of the graph model; and
determining one or more context switches in the conversation based on the one or more dominance scores, wherein the one or more context switches are employed to identify one or more of topics or sub-topics in the conversation; and
a client computer, comprising:
another memory that stores at least instructions; and
one or more processors that execute instructions that perform actions, including:
providing one or more of the conversation stream or the one or more words to the network computer.
9. The system of claim 8 , wherein the one or more words, further comprise:
associating each word with a node in the graph model and each edge in the graph model corresponds to one or more relationships between each word.
10. The system of claim 8 , further comprising:
corresponding each sentence model to a sentence in the conversation.
11. The system of claim 8 , wherein generation of the combined model further comprises:
correlating the one or more key phrases with the one or more partitions of the graph model.
12. The system of claim 8 , wherein determination of the one or more context switches, further comprises:
determining a transition from a portion of the conversation stream associated with a dominance score that exceeds a threshold value to another portion of the conversation stream associated with another dominance score that is below another threshold value that corresponds to each context switch.
13. The system of claim 8 , further comprising:
categorizing the one or more partitions into two or more types based on one or more of characteristics of each word that is included in a partition and each relationship between each word that is included in the partition.
14. The system of claim 8 , further comprising:
determining one or more phrasal scores for one or more portions of each sentence;
refining the one or more phrasal scores for each sentence based on a repetition of each word, a degree of each word, or a length of each sentence; and
employing the one or more refined phrasal scores to rank order one or more key words for the conversation.
15. A processor readable non-transitory storage media that includes instructions for organizing conversation information over a network, wherein execution of the instructions by one or more hardware processors performs actions, comprising:
providing a graph model for a conversation based on one or more words provided by a conversation stream;
generating one or more sentence models based on the one or more words, wherein each sentence model provides one or more key phrases for each sentence;
generating a combined model that associates one or more partitions of the graph model and the one or more key phrases with one or more portions of the conversation stream;
employing the combined model to determine one or more dominance scores for the one or more portions of the conversation stream based on a strength of the correlation between the one or more key phrases and the one or more partitions of the graph model; and
determining one or more context switches in the conversation based on the one or more dominance scores, wherein the one or more context switches are employed to identify one or more of topics or sub-topics in the conversation.
16. The processor readable non-transitory storage media of claim 15 , wherein the one or more words, further comprise:
associating each word with a node in the graph model and each edge in the graph model corresponds to one or more relationships between each word.
17. The processor readable non-transitory storage media of claim 15 , wherein determination of the one or more context switches, further comprises:
determining a transition from a portion of the conversation stream associated with a dominance score that exceeds a threshold value to another portion of the conversation stream associated with another dominance score that is below another threshold value that corresponds to each context switch.
18. The processor readable non-transitory storage media of claim 15 , further comprising:
categorizing the one or more partitions into two or more types based on one or more of characteristics of each word that is included in a partition and each relationship between each word that is included in the partition.
19. The processor readable non-transitory storage media of claim 15 , further comprising:
determining one or more phrasal scores for one or more portions of each sentence;
refining the one or more phrasal scores for each sentence based on a repetition of each word, a degree of each word, or a length of each sentence; and
employing the one or more refined phrasal scores to rank order one or more key words for the conversation.
20. The processor readable non-transitory storage media of claim 15 , further comprising:
corresponding each sentence model to a sentence in the conversation; and
correlating the one or more key phrases with the one or more partitions of the graph model.