Method and system for indexing and searching timed media information based upon relevance intervals
A method and system for indexing, searching, and retrieving information from timed media files based upon relevance intervals. The method and system for indexing, searching, and retrieving this information is based upon relevance intervals so that a portion of a timed media file is returned, which is selected specifically to be relevant to the given information representations, thereby eliminating the need for a manual determination of the relevance and avoiding missing relevant portions. The timed media includes streaming audio, streaming video, timed HTML, animations such as vector-based graphics, slide shows, other timed media, and combinations thereof.
1. A method comprising:
receiving, by a computing device, a media file;
parsing the media file to determine a grammatical structure of language contained in the media file; and
adding the language contained in the media file to an index.
2. The method of claim 1 , comprising:
dividing the language contained in the media file into sentences.
3. The method of claim 2 , comprising:
using a set of rules to determine a most likely sentence boundary for the dividing the language contained in the media file into the sentences.
4. The method of claim 3 , wherein the set of rules to determine the most likely sentence boundary for the dividing the language contained in the media file into the sentences comprise rules for determining sentence boundaries based upon one or more of word sequences, pauses, parts of speech, grammatical data, and prosodic cues.
5. The method of claim 3 , comprising:
determining a sentence number of a particular sentence in the media file by counting a number of sentences in the media file before the particular sentence.
6. The method of claim 1 , comprising:
determining a part of speech of the language contained in the media file.
7. The method of claim 1 , comprising:
determining a type of clause of which the language contained in the media file is a part.
8. The method of claim 1 , comprising:
determining a pronoun in the language contained in the media file; and
determining a reference to which the pronoun in the language contained in the media file refers.
9. The method of claim 8 , wherein the determining the reference to which the pronoun in the language contained in the media file refers comprises:
determining a group of potential antecedents for the pronoun in the language contained in the media file; and
filtering the group of potential antecedents for the pronoun based on whether the potential antecedents can represent one or more of a human, a group of humans, or a gendered non-human.
10. The method of claim 9 , wherein the determining the reference to which the pronoun in the language contained in the media file refers comprises:
filtering the group of potential antecedents for the pronoun based on one or more semantic constrains on the potential antecedents.
11. The method of claim 1 , comprising:
determining a synonym of the language contained in the media file.
12. The method of claim 1 , comprising:
determining an identification of a person who spoke the language contained in the media file.
13. The method of claim 1 , comprising:
determining a time code at which the language contained in the media file occurs in the media file.
14. The method of claim 1 , comprising:
detecting prosody of the language contained in the media file.
15. The method of claim 1 , comprising:
performing lemmatization of the language contained in the media file, the lemmatization comprising reducing words of the language contained in the media file to canonical form.
16. The method of claim 1 , comprising:
determining a centrality of a concept in a sentence formed by the language contained in the media file by examining the grammatical structure of the sentence formed by the language contained in the media file.
17. The method of claim 16 , wherein examining the grammatical structure of the sentence formed by the language contained in the media file comprises:
identifying phrases in the sentence;
identifying one or more verbs in the sentence; and
assigning a centrality weight to each word in the sentence.
18. A method comprising:
receiving, by a computing device, a media file;
receiving a text transcript for the media file;
synchronizing the text transcript with the media file; and
parsing the text transcript to determine a grammatical structure of language contained in the text transcript for the media file.
19. A method comprising:
receiving, by a computing device, a media file;
determining a centrality of a concept in a sentence formed by language contained in the media file by examining grammatical structure of a sentence formed by the language contained in the media file; and
adding the language contained in the media file to an index.
20. The method of claim 19 , comprising:
determining a corpus based on the centrality of the concept in the sentence formed by the language; and
customizing the index using the corpus to create a search index.