Ranking answers for on-line community questions
AssigneeOath Inc.
InventorsOleg Rokhlenko, David Carmel, Idan Szpektor, Adi Omari
Life of this patent
Estimating the term…
Abstract
Briefly, example methods, apparatuses, and/or articles of manufacture are disclosed that may be implemented, in whole or in part, using one or more computing devices to facilitate and/or support one or more operations and/or techniques for in part, to facilitate and/or support one or more operations and/or techniques for ranking answers for on-line community questions.
Claims21
A method, comprising:
- receiving, by one or more servers, a query from a client device;
- identifying, by the one or more servers, one or more candidate search results that are pertinent to the query, the one or more candidate search results including a set of community question answering (CQA) answers accessible over an electronic network;
- determining a CQA question that corresponds to the set of CQA answers;
- extracting, by the one or more servers, propositions from the set of CQA answers, each CQA answer of the set of CQA answers corresponding to at least one of the propositions, wherein the extracting comprises extracting a first proposition and a second proposition from a first CQA answer of the set of CQA answers;
- filtering, by the one or more servers, the propositions to generate filtered propositions based, at least in part, on a measure of relevance of the propositions to the CQA question corresponding to the set of CQA answers;
- measuring, by the one or more servers, similarity among the filtered propositions for the set of CQA answers identified as pertinent to the query based, at least in part, on one or more aspects identified in the filtered propositions for the set of CQA answers identified as pertinent to the query;
- ranking, by the one or more servers, the set of CQA answers based, at least in part, on the similarity, wherein the ranking comprises determining a first rank for the first CQA answer of the set of CQA answers based, at least in part, on a first similarity between the first proposition of the first CQA answer and a third proposition;
- and
- responsive to the query, providing, by the one or more servers, one or more search results including at least a portion of the set of CQA answers according to the ranking the set of CQA answers.
An apparatus comprising:
- at least one computing device, the at least one computing device including at least one processor and at least one memory;
- the at least one processor being configured to:
- process a query received from a client device;
- identify one or more candidate search results that are pertinent to the query, the one or more candidate search results including a set of community question answering (CQA) answers accessible over an electronic network;
- determine a CQA question that corresponds to the set of CQA answers;
- extract propositions from the set of CQA answers, each CQA answer of the set of CQA answers corresponding to at least one of the propositions, wherein the extracting comprises extracting a first proposition and a second proposition from a first CQA answer of the set of CQA answers;
- filter the propositions to generate filtered propositions based, at least in part, on a measure of relevance of the propositions to the CQA question that corresponds to the set of CQA answers;
- measure similarity among the filtered propositions for the set of CQA answers identified as pertinent to the query based, at least in part, on one or more aspects identified in the filtered propositions for the set of CQA answers identified as pertinent to the query;
- rank the set of CQA answers based, at least in part, on the similarity;
- and
- responsive to the query, provide one or more search results including at least a portion of the set of CQA answers according to the ranking.
A computer program product comprising one or more non-transitory computer-readable media having computer program instructions stored therein, the computer program instructions being configured such that, when executed by one or more computing devices, the computer program instructions cause the one or more computing devices to:
- process a query received from a client device;
- identify one or more candidate search results that are pertinent to the query, the one or more candidate search results including a set of community question answering (CQA) answers accessible over an electronic network;
- determine a CQA question that corresponds to the set of CQA answers;
- extract propositions from the set of CQA answers, each CQA answer of the set of CQA answers corresponding to at least one of the propositions, wherein the extracting comprises extracting a first proposition and a second proposition from a first CQA answer of the set of CQA answers;
- filter the propositions to generate filtered propositions based, at least in part, on a measure of relevance of the propositions to the CQA question that corresponds to the set of CQA answers;
- measure similarity among the filtered propositions for the set of CQA answers identified as pertinent to the query based, at least in part, on one or more aspects identified in the filtered propositions for the set of CQA answers identified as pertinent to the query;
- rank the set of CQA answers based, at least in part, on the similarity, wherein the ranking comprises determining a first rank for the first CQA answer of the set of CQA answers based, at least in part, on a first similarity between the first proposition of the first CQA answer and one or more propositions;
- and
- responsive to the query, provide one or more search results including at least a portion of the set of CQA answers according to the ranking the set of CQA answers.
Dependencies are inferred from the claim text.