System and method of providing a spoken dialog interface to a website
View Patent ↗Disclosed is a method for training a spoken dialog service component from website data. Spoken dialog service components typically include an automatic speech recognition module, a language understanding module, a dialog management module, a language generation module and a text-to-speech module. The method includes selecting anchor texts within a website based on a term density, weighting those anchor texts based on a percent of salient words to total words, and incorporating the weighted anchor texts into a live spoken dialog interface, the weights determining a level of incorporation into the live spoken dialog interface.
1. A method comprising:
selecting an anchor text in a website based on a term density;
weighting the anchor text with a weight based on a ratio of salient words to total words, to yield a weighted anchor text; and
incorporating the weighted anchor text into a live spoken dialog system, the spoken dialog system engaging in a spoken dialog with a user, wherein the weight determines a level of incorporation of the weighted anchor text into the live spoken dialog.
2. The method of claim 1 , further comprising extracting from the website a linguistic item wherein the level of incorporation is further based on the linguistic item.
3. The method of claim 2 , further comprising:
generating a website specific language model using the linguistic item and the weighted anchor text.
4. The method of claim 3 , further comprising:
integrating the website specific language model into the live spoken dialog.
5. The method of claim 2 , wherein the linguistic item comprises one of a named-entity, a nominal phrase, a verbal phrase, and an adjectival phrase.
6. The method of claim 1 , further comprising:
computing an alias comprising a best representative anchor text from a plurality of weighted anchor texts.
7. The method of claim 6 , wherein the best representative anchor text has a weight associated with a highest ratio of salient words to total words from the plurality of weighted anchor texts.
8. A system comprising:
a processor; and
a computer-readable storage medium having instructions stored which, when executed by the processor, result in the processor performing operations comprising:
selecting an anchor text in a website based on a term density;
weighting the anchor text with a weight based on a ratio of salient words to total words, to yield a weighted anchor text; and
incorporating the weighted anchor text into a live spoken dialog system, the spoken dialog system engaging in a spoken dialog with a user, wherein the weight determines a level of incorporation of the weighted anchor text into the live spoken dialog.
9. The system of claim 8 , the computer-readable storage medium having additional instructions stored which result in the operations further comprising extracting from the website a linguistic item wherein the level of incorporation is further based on the linguistic item.
10. The system of claim 9 , the computer-readable storage medium having further instructions stored which result in the operations further comprising:
generating a website specific language model using the linguistic item and the weighted anchor text.
11. The system of claim 10 , the computer-readable storage medium having yet additional instructions stored which result in the operations further comprising:
integrating the website specific language model into the live spoken dialog.
12. The system of claim 9 , wherein the linguistic item comprises one of a named-entity, a nominal phrase, a verbal phrase, and an adjectival phrase.
13. The system of claim 9 , the computer-readable storage medium having further instructions stored which result in the operations further comprising:
computing an alias comprising a best representative anchor text from a plurality of weighted anchor texts.
14. The system of claim 13 , wherein the best representative anchor text has a weight associated with a highest ratio of salient words to total words from the plurality of weighted anchor texts.
15. A computer-readable storage medium device having instructions stored which, when executed by a computing device, result in the computing device performing operations comprising:
selecting an anchor text in a website based on a term density;
weighting the anchor text with a weight based on a ratio of salient words to total words, to yield a weighted anchor text; and
incorporating the weighted anchor text into a live spoken dialog system, the spoken dialog system engaging in a spoken dialog with a user, wherein the weight determines a level of incorporation of the weighted anchor text into the live spoken dialog.
16. The computer-readable storage device of claim 15 , the computer-readable storage device having additional instructions stored which result in the operations further comprising extracting from the website a linguistic item wherein the level of incorporation is further based on the linguistic item.
17. The computer-readable storage device of claim 16 , the computer-readable storage device having further instructions stored which result in the operations further comprising:
generating a website specific language model using the linguistic item and the weighted anchor text.
18. The computer-readable storage device of claim 17 , the computer-readable storage device having yet additional instructions stored which result in the operations further comprising:
integrating the website specific language model into the live spoken dialog.
19. The computer-readable storage device of claim 16 , wherein the linguistic item comprises one of a named-entity, a nominal phrase, a verbal phrase, and an adjectival phrase.
20. The computer-readable storage device of claim 15 , the computer-readable storage device having further instructions stored which result in the operations further comprising:
computing an alias comprising a best representative anchor text from a plurality of weighted anchor texts.