US 2013/0232129 A1 · ROBUST DISCOVERY OF ENTITY SYNONYMS USING QUERY LOGS

Abstract

A similarity analysis framework is described herein which leverages two or more similarity analysis functions to generate synonyms for an entity reference string re. The functions are selected such that the synonyms that are generated by the framework satisfy a core set of synonym-related properties. The functions operate by leveraging query log data. One similarity analysis function takes into consideration the strength of similarity between a particular candidate string se and an entity reference string re even in the presence of sparse query log data, while another function takes into account the classes of se and re. The framework also provides indexing mechanisms that expedite its computations. The framework also provides a reduction module for converting long entity reference strings into shorter strings, where each shorter string (if found) contains a subset of the terms in its longer counterpart.

Claims20

Dependent claims

A method, performed by computing functionality, for generating at least one synonym for an entity reference string re, providing that said at least one synonym can be found, comprising:

providing the entity reference string re;
providing a set of candidate strings Se, comprising at least one candidate string se;
generating, using query log data, similarity score information for respective pairs of se and re using at least two similarity analysis modules;
and
determining, using the similarity score information, whether each se is a valid synonym of re, where a valid synonym satisfies a core set of synonym-related properties jointly provided by said at least two similarity analysis modules.

2 more elements

A pseudo-document similarity analysis system, implemented by computing functionality, comprising:

logic configured to determine, using query log data, a set of documents D that have been selected in response to submitting a query entity string re as a query;
and
logic configured to determine, using the query log data, a set of queries that have been submitted and which have resulted in the selection of any of the documents in the set of document D, the set of queries serving as a set of candidate strings Se;
logic configured to generate or receive a pseudo-document pdoc for each document d in the set of documents D, the pseudo-document containing a set of terms found in queries that that have been submitted and which have resulted in the selection of the document d;
logic configured to determine, for each candidate string se in Se, a number of pseudo-documents, if any, that contain all of the terms in se;
and
logic configured to generate a pseudo-document similarity score Scorepdsim(se→re) for se using said number, where Scorepdsim(se→re) describes a strength of relatedness of se to re.

4 more elements

Dependencies are inferred from the claim text.

Robust discovery of entity synonyms using query logs

Life of this patent

Robust discovery of entity synonyms using query logs

Life of this patent

Abstract

Claims20