Cross-lingual query suggestion
First Claim
1. A method for query suggestion performed by a processor executing computer-executable instructions stored on a memory device, the method comprising:
- for an input query in source language, identifying a query in target language from a query log of a search engine, the query in target language and the input query in source language having a cross-lingual similarity, the identifying the query in target language from the query log comprising;
providing a plurality of candidate queries in target language;
evaluating the plurality of candidate queries in target language at least partly by deducing a monolingual similarity between the input query in source language and a translation of a respective candidate query from target language to source language; and
ranking the plurality of candidate queries in target language using a cross-lingual query similarity score, the cross-lingual query similarity score being based on a plurality of features and a weight of each feature in calculating the cross-lingual query similarity score; and
suggesting the query in target language as a cross-lingual query at least partly based on click-through information of documents selected by users for the query in target language.
2 Assignments
0 Petitions
Accused Products
Abstract
Cross-lingual query suggestion (CLQS) aims to suggest relevant queries in a target language for a given query in a source language. The cross-lingual query suggestion is improved by exploiting the query logs in the target language. CLQS provides a method for learning and determining a similarity measure between two queries in different languages. The similarity measure is based on both translation information and monolingual similarity information, and in one embodiment uses both the query log itself and click-through information associated therewith. Monolingual and cross-lingual information such as word translation relations and word co-occurrence statistics may be used to estimate the cross-lingual query similarity with a discriminative model.
-
Citations
20 Claims
-
1. A method for query suggestion performed by a processor executing computer-executable instructions stored on a memory device, the method comprising:
-
for an input query in source language, identifying a query in target language from a query log of a search engine, the query in target language and the input query in source language having a cross-lingual similarity, the identifying the query in target language from the query log comprising; providing a plurality of candidate queries in target language; evaluating the plurality of candidate queries in target language at least partly by deducing a monolingual similarity between the input query in source language and a translation of a respective candidate query from target language to source language; and ranking the plurality of candidate queries in target language using a cross-lingual query similarity score, the cross-lingual query similarity score being based on a plurality of features and a weight of each feature in calculating the cross-lingual query similarity score; and suggesting the query in target language as a cross-lingual query at least partly based on click-through information of documents selected by users for the query in target language. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13)
-
-
14. A method for query suggestion performed by a processor executing computer-executable instructions stored on a memory device, the method comprising:
-
receiving an input query in source language; providing a plurality of candidate queries in target language, at least part of the plurality of candidate queries in target language being selected from a query log of a search engine; evaluating the plurality of candidate queries in target language at least partly by deducing a monolingual similarity between the input query in source language and a translation of a respective candidate query from target language to source language; ranking the plurality of candidate queries in target language using a cross-lingual query similarity score, the cross-lingual query similarity score being based on a plurality of features and a weight of each feature in calculating the cross-lingual query similarity score; and from top ranking candidate queries in target language, suggesting a query in target language as a cross-lingual query at least partly based on click-through information of documents selected by users for the plurality of candidate queries in target language. - View Dependent Claims (15, 16, 17, 18)
-
-
19. A method for query suggestion performed by a processor executing computer-executable instructions stored on a memory device, the method comprising:
for an input query in source language, identifying a query in target language from a query log of a search engine, the query in target language and the input query in source language having a cross-lingual similarity, the identifying the query in target language from the query log comprising; providing a plurality of candidate queries in target language; and ranking the plurality of candidate queries in target language using a cross-lingual query similarity score, the cross-lingual query similarity score of the input query in source language qe and the candidate query in target language qf being computed using an equation simCL(qf,qe)=w·
φ
(ƒ
(qf,qe)), simCL(qf, qe) being the cross-lingual query similarity score, f (qf, qe) being a feature vector, the feature vector f (qf, qe) including at least two of the feature functions selected from bilingual dictionary-based translation score, bidirectional translation score, frequency in Web mining snippets, and monolingual query suggestion-based feature, φ
being a mapping from an input feature space onto a kernel space, and w being a weight vector in the kernel space; and
suggesting the query in target language as a cross-lingual query.
-
20. A method for query suggestion performed by a processor executing computer-executable instructions stored on a memory device, the method comprising:
-
for an input query in source language, identifying a query in target language from a query log of a search engine, the query in target language and the input query in source language having a cross-lingual similarity, the identifying the query in target language from the query log comprising; providing a plurality of candidate queries in target language; evaluating the plurality of candidate queries in target language at least partly by deducing a monolingual similarity between the input query in source language and a translation of a respective candidate query from target language to source language; and ranking the plurality of candidate queries in target language using a cross-lingual query similarity score, the cross-lingual query similarity score of the input query in source language qe and the candidate query in target language qf being computed using an equation simCL(qf,qe)=w·
φ
(ƒ
(qf,qe)), simCL(qf, qe) being the cross-lingual query similarity score, ƒ
(qf, qe) being a feature vector, φ
being a mapping from an input feature space onto a kernel space, and w being a weight vector in the kernel space; andsuggesting the query in target language as a cross-lingual query at least partly based on click-through information of documents selected by users for the query in target language.
-
Specification