Hassan Sawaf

Techniques for the generation of dubbed audio for an audio/video are described. An exemplary approach is to receive a request to generate dubbed speech for an audio/visual file; and in response to the request to: extract speech segments from an audio track of the audio/visual file associated with identified speakers; translate the extracted speech segments into a target language; determine a machine learning model per identified speaker, the trained machine learning models to be used to… Show more

Techniques for the generation of dubbed audio for an audio/video are described. An exemplary approach is to receive a request to generate dubbed speech for an audio/visual file; and in response to the request to: extract speech segments from an audio track of the audio/visual file associated with identified speakers; translate the extracted speech segments into a target language; determine a machine learning model per identified speaker, the trained machine learning models to be used to generate a spoken version of the translated, extracted speech segments based on the identified speaker; generate, per translated, extracted speech segment, a spoken version of the translated, extracted speech segments using a trained machine learning model that corresponds to the identified speaker of the translated, extracted speech segment and prosody information for the extracted speech segments; and replace the extracted speech segments from the audio track of the audio/visual file with the spoken versions spoken version of the translated, extracted speech segments to generate a modified audio track. Show less

According to various embodiments, the Query Context Translation Engine identifies a topic of a search query history received during a current user session. The search query history in a first language. The Query Context Translation Engine identifies, in a translation table, target text that corresponds with a query in the search query history, the target text comprising at least one word. The Query Context Translation Engine obtains at least one search result based on a translation of the… Show more

According to various embodiments, the Query Context Translation Engine identifies a topic of a search query history received during a current user session. The search query history in a first language. The Query Context Translation Engine identifies, in a translation table, target text that corresponds with a query in the search query history, the target text comprising at least one word. The Query Context Translation Engine obtains at least one search result based on a translation of the target text in a second language. Show less

A method of forming parallel corpora comprises receiving sets of items in first language and second languages, each of the sets having one or more associated descriptions and metadata. The metadata is collected from the two sets of items and are aligned using the metadata. The aligned metadata are mapped from the first language to the second language for each of the sets. The descriptions of two items are fetched and the structural similarity of the descriptions is measured to assess whether… Show more

A method of forming parallel corpora comprises receiving sets of items in first language and second languages, each of the sets having one or more associated descriptions and metadata. The metadata is collected from the two sets of items and are aligned using the metadata. The aligned metadata are mapped from the first language to the second language for each of the sets. The descriptions of two items are fetched and the structural similarity of the descriptions is measured to assess whether two items are likely to be translations of each other. For mapped items with structurally similar descriptions, the mapped item descriptions are formed into respective sentences in first language and in the second language. The sentences are parallel corpora which may be used to translate an item from the first language to the second language, and also to train a machine translation system. Show less

A method of forming parallel corpora comprises receiving sets of items in first language and second languages, each of the sets having one or more associated descriptions and metadata. The metadata is collected from the two sets of items and are aligned using the metadata. The aligned metadata are mapped from the first language to the second language for each of the sets. The descriptions of two items are fetched and the structural similarity of the descriptions is measured to assess whether… Show more

A method of forming parallel corpora comprises receiving sets of items in first language and second languages, each of the sets having one or more associated descriptions and metadata. The metadata is collected from the two sets of items and are aligned using the metadata. The aligned metadata are mapped from the first language to the second language for each of the sets. The descriptions of two items are fetched and the structural similarity of the descriptions is measured to assess whether two items are likely to be translations of each other. For mapped items with structurally similar descriptions, the mapped item descriptions are formed into respective sentences in first language and in the second language. The sentences are parallel corpora which may be used to translate an item from the first language to the second language, and also to train a machine translation system. Show less

A method of propagating annotations of content items to a search query is disclosed. A strength of a correspondence between a search query and a title of a listing of an item on a network-based publication system is determined. The strength of the correspondence is based on an analysis of a set of actions by a set of users who submitted the search query. A set of annotations corresponding to the title is generated. The set of annotations is propagated to an additional search query such that the… Show more

A method of propagating annotations of content items to a search query is disclosed. A strength of a correspondence between a search query and a title of a listing of an item on a network-based publication system is determined. The strength of the correspondence is based on an analysis of a set of actions by a set of users who submitted the search query. A set of annotations corresponding to the title is generated. The set of annotations is propagated to an additional search query such that the set of annotations and the strength of the correspondence are used by a search engine to enhance search results corresponding to the additional search query. Show less

User-specific queries for items may be collected from a search engine in language A and corresponding behavioral data with respect to items returned for the queries, such as items viewed, watched, liked, clicked, and bought by the user may also be collected. Similar data may be gathered for user specific queries from a search engine in language B. For query pairs, each in a different language, the system may measure the similarity of their user behavioral data using language independent… Show more

User-specific queries for items may be collected from a search engine in language A and corresponding behavioral data with respect to items returned for the queries, such as items viewed, watched, liked, clicked, and bought by the user may also be collected. Similar data may be gathered for user specific queries from a search engine in language B. For query pairs, each in a different language, the system may measure the similarity of their user behavioral data using language independent features such as images, UPC codes, price, seller, category, and the like, and using translated features such as descriptors that comprise keywords that describe the item returned in response to the queries. Those pairs of queries in the two languages with high similarity of user behavior are statistically translations of each other. Show less

A user query for items is received in a first language and translated from the first language to a second language. A result set in the second language that meets the query is obtained and is translated into the first language for presentation to the user. User feedback is used to build an ontology for optimizing the translation from the first language to the second language based on query context and the feedback. Query context may include information determined by learning semantic… Show more

A user query for items is received in a first language and translated from the first language to a second language. A result set in the second language that meets the query is obtained and is translated into the first language for presentation to the user. User feedback is used to build an ontology for optimizing the translation from the first language to the second language based on query context and the feedback. Query context may include information determined by learning semantic relationships between keywords in the query. Optimizing may include building an ontology used by a machine translator to translate key words from the first language to the second language. The number of items in the result set are measured or information is abstracted from the feedback and correlated to ontological information of the result set. The system adapts to changes in meanings in the first language over time. Show less

Publication system, such as ecommerce system, machine translation translates a query in a first language to a second language to query an ecommerce database maintained in the second language and obtain a result set responsive to the query. Human feedback relating to the result set is detected. If the feedback is positive the system increases the probability that the translation is correct, if the feedback is negative the system decreases the probability that the translation is correct. For… Show more

Publication system, such as ecommerce system, machine translation translates a query in a first language to a second language to query an ecommerce database maintained in the second language and obtain a result set responsive to the query. Human feedback relating to the result set is detected. If the feedback is positive the system increases the probability that the translation is correct, if the feedback is negative the system decreases the probability that the translation is correct. For positive feedback, the system detects whether a clue is recognized in the query. If a clue is recognized the system increases the value of the clue for making the translation. The system detects the identity of the product in the query, accesses the product vendor website that is maintained in the query language, and detects information that is in the query language for use in the translation process. Show less

User interfaces receive a first plurality of user queries and result sets that are in a category, exhibit a constraint, and exhibit user behavior. Also received are a second plurality of user queries and result sets that that are in the category, exhibit the constraint, and exhibit user behavior. The second user queries and results are received either from a plurality of user interfaces coupled to a second system, or from the second system itself. Responsive to detecting that the first… Show more

User interfaces receive a first plurality of user queries and result sets that are in a category, exhibit a constraint, and exhibit user behavior. Also received are a second plurality of user queries and result sets that that are in the category, exhibit the constraint, and exhibit user behavior. The second user queries and results are received either from a plurality of user interfaces coupled to a second system, or from the second system itself. Responsive to detecting that the first plurality of user queries and result sets and the second plurality of user queries and result sets satisfy respective thresholds, a signal indicates that at least one of the first plurality of user queries and at least one of the second plurality of user queries are translations of each other. Show less

Information is provided a user of a mobile device. Media content is sensed by the mobile device and sent to an information processing server. The information processing server also obtains media content from another source and associates at least a portion of the obtained media content with a product or service offer. The sensed media content is correlated to the obtained media content such that an associated buy or service offer is selected. The buy or service offer is sent to the mobile… Show more

Information is provided a user of a mobile device. Media content is sensed by the mobile device and sent to an information processing server. The information processing server also obtains media content from another source and associates at least a portion of the obtained media content with a product or service offer. The sensed media content is correlated to the obtained media content such that an associated buy or service offer is selected. The buy or service offer is sent to the mobile device for display to the user. Show less

A system and method for hybrid machine translation approach is based on a statistical transfer approach using statistical and linguistic features. The system and method may be used to translate from one language into another. The system may include at least one database, a rule based translation module, a statistical translation module and a hybrid machine translation engine.

In a flow of computer actions, a computer system receives a request involving a machine translation. In performing the translation, or in using the translation in subsequent computer operations, the computer system takes into account known statistical relationships (310), obtained from previously accumulated click-through data, between a machine translation performed in a flow, the flow's portions preceding the translation, and success indicators pertaining to the flow's portion following the… Show more

In a flow of computer actions, a computer system receives a request involving a machine translation. In performing the translation, or in using the translation in subsequent computer operations, the computer system takes into account known statistical relationships (310), obtained from previously accumulated click-through data, between a machine translation performed in a flow, the flow's portions preceding the translation, and success indicators pertaining to the flow's portion following the translation. The statistical relationships are derived by data mining of the click-through data. Further, normal actions can be suspended to use a random option to accumulate the click-through data and/or perform statistical AB testing. Other features are also provided. Show less