Generating snippets based on content features
Systems, methods, and computer storage media having computer-executable instructions embodied thereon that facilitate generation of snippets. In embodiments, text features within a keyword-sentence window are identified. The text features are utilized to determine break features that indicate favorability of breaking at a particular location of the keyword-sentence window. The break features are used to recognize features of partial snippets such that a snippet score to indicate the strength of the partial snippet can be calculated. Snippet scores associated with partial snippets are compared to select an optimal snippet, that is, the snippet having the highest snippet score.
1. One or more computer media devices having computer-executable instructions embodied thereon, that when executed, cause a computing device to perform a method for facilitating generation of snippets provided in association with search results, the method comprising:
referencing a keyword-sentence window comprising a sequence of tokens including one or more keywords that match one or more query terms;
identifying a part-of-speech for one or more tokens within the keyword-sentence window;
utilizing the part-of-speech corresponding with each of the one or more tokens to identify one or more text features associated with a span including two consecutive tokens, wherein at least one text feature comprises a bigram type that is a sequence of two parts-of-speech identifiers that correspond with the span of the two consecutive tokens, the one or more text features being used to generate at least one breaking indicator for at least one token that indicates an extent to which it is favorable to break the keyword-sentence window following the corresponding token, wherein the extent to which it is favorable to break the keyword-sentence window following the corresponding token is represented using a scale or rating technique;
generating a plurality of partial snippets comprising portions of the keyword-sentence window;
for each partial snippet, identifying a snippet feature that indicates a relative strength of truncating the keyword-sentence window in accordance with the corresponding partial snippet, wherein the snippet feature comprises a sum of breaking indicators associated with the partial snippet that each indicate an extent to which it is favorable to break the partial snippet at the corresponding break; and
using the snippet features to select a partial snippet from the plurality of partial snippets for display in association with a search result.
2. The media of claim 1 further comprising displaying the selected partial snippet in association with the search result.
3. The media of claim 1 , wherein the selected partial snippet comprises text that breaks at natural beginning and ending points.
4. The media of claim 1 , wherein the selected partial snippet characterizes a document in association with the search result such that desired information is not truncated from the keyword-sentence window.
5. The media of claim 1 , wherein the one or more text features further comprise a named entity.
6. The media of claim 5 , wherein the named entity is identified based on a pattern of part-of-speech identifiers.
7. The media of claim 1 further comprising identifying one or more additional text features based on tokens or spans within the keyword-sentence window.
8. The media of claim 1 , wherein the one or more text features being further used to generate at least one span indicator for at least one span that indicates whether the span is interesting or droppable.
9. A method for facilitating generation of snippets provided in association with search results, the method comprising:
identifying one or more text features for a plurality of spans within a keyword-sentence window, wherein at least one text feature comprises a named entity feature that is recognized when a span of two or more tokens has sequential parts-of-speech identifiers that match a predetermined sequence of part-of-speech identifiers;
determining one or more breaking indicators associated with one or more of the plurality of spans using the one or more text features, each of the one or more breaking indicators providing an indication of an extent comprising a numerical value for which a snippet boundary is favorable relative to a particular position within the keyword-sentence window;
generating a plurality of partial snippets comprising portions of the keyword-sentence window;
for each partial snippet, identifying a snippet feature that indicates a relative strength of truncating the keyword-sentence window in accordance with the corresponding partial snippet, wherein the snippet feature comprises a sum of breaking indicators associated with the partial snippet that each indicate an extent to which it is favorable to break the partial snippet at the corresponding break; and
using the snippet features to select a partial snippet from the plurality of partial snippets for display in association with a search result.
10. The method of claim 9 , further comprising determining one or more span indicators to indicate whether one or more spans within the one or more of the plurality of spans is interesting or droppable.
11. The method of claim 9 further comprising displaying the selected partial snippet in association with the search result.
12. One or more computer media devices having computer-executable instructions embodied thereon, that when executed, cause a computing device to perform a method for facilitating generation of snippets provided in association with search results, the method comprising:
identifying one or more text features associated with spans within a keyword-sentence window including at least one keyword that matches at least one query term, at least a portion of the one or more text features being identified based on a part-of-speech identifier associated with each of two or more consecutive tokens of the span;
determining one or more break features associated with the spans using the one or more text features, the one or more break features providing an indication of whether a snippet boundary is favorable relative to a particular position within the keyword-sentence window;
generating a plurality of partial snippets comprising portions of the keyword-sentence window;
for each partial snippet, identifying a snippet feature that indicates a relative strength of truncating the keyword-sentence window in accordance with the partial snippet, wherein the snippet feature comprises a sum of breaking indicators associated with the partial snippet that each indicate an extent to which it is favorable to break the partial snippet at the corresponding break;
determining a score for each of the plurality of partial snippets that indicates favorability of truncating the keyword-sentence window at snippet boundaries as indicated in the partial snippet, the score being based on the one or more snippet features; and
based on the scores, selecting a partial snippet from the plurality of partial snippets to display in association with a search result, the selected partial snippet designated as having optimal snippet boundaries.
13. The media of claim 12 further comprising displaying the selected partial snippet in association with a search result.
14. The media of claim 12 , wherein generating the plurality of partial snippets comprises expanding one or more previous partial snippets.