Abstract: The present disclosure proposes a method, apparatus and computer program product for hierarchical representation learning of user interest. A historical content item sequence of a user may be obtained. A topic and a text of each historical content item in the historical content item sequence may be identified, to obtain a topic sequence and a text sequence corresponding to the historical content item sequence. A comprehensive topic representation may be generated based on the topic sequence. A comprehensive text representation may be generated based on the text sequence. A user interest representation of the user may be generated based on the comprehensive topic representation and the comprehensive text representation.

Abstract: The present disclosure proposes a method, apparatus and computer program product for sentence representation generation for cross-lingual retrieval. A target sentence may be obtained. An initial target sentence representation of the target sentence may be generated through an encoder, the encoder pretrained through a contrastive context prediction mechanism. A target sentence representation of the target sentence for cross-lingual retrieval may be generated based on the initial target sentence representation through cross-lingual calibration.

Abstract: The present disclosure provides method and apparatus for query conversion. A first query for a first graph database may be obtained. A syntax tree may be generated through parsing the first query. A query graph may be created based on the syntax tree. The query graph may be converted into a second query for a second graph database.

Abstract: The present disclosure proposes a method and apparatus for representation learning of cross-language texts. A source language text and a target language text may be obtained. An initial joint representation of the source language text and the target language text may be generated. Relations among a plurality of words in the source language text and the target language text may be identified. A joint representation of the source language text and the target language text may be generated based on the initial joint representation and the relations. The joint representation may be projected to at least a target language representation corresponding to the target language text.

Abstract: The present disclosure proposes a method and apparatus for multi-model joint denoising training. Multiple models may be obtained. A set of training samples may be denoised through the multiple models. The multiple models may be trained with the set of denoised training samples.

Abstract: The present disclosure proposes method and apparatus for query-based table visualization. A query may be obtained. At least one search result for the query may be obtained. A table may be extracted from the at least one search result. At least one chart corresponding to the table may be generated based on the query and the table.

Abstract: The present disclosure provides method and apparatus for query conversion. A first query for a first graph database may be obtained. A syntax tree may be generated through parsing the first query. A query graph may be created based on the syntax tree. The query graph may be converted into a second query for a second graph database.

Abstract: In embodiments of the present disclosure, there is provided an assertion-based question answering manner. After a question and the related passage are obtained, an assertion answer to the question is determined based on content of the passage, and the assertion answer has a predetermined structure and represents a complete semantic meaning. Then, the assertion answer to the question may be outputted to the user. In the embodiments of the present disclosure, the question and the relevant passage are used as input, and a semi-structured assertion answer is output. The assertion answer according to embodiments of the present disclosure can provide richer semantic content than the traditional short answer, and provide a more concise expression than the traditional long answer, thereby ensuring accuracy of the answer while improving the user experience.

Abstract: In embodiments of the present disclosure, there is provided an assertion-based question answering manner. After a question and the related passage are obtained, an assertion answer to the question is determined based on content of the passage, and the assertion answer has a predetermined structure and represents a complete semantic meaning. Then, the assertion answer to the question may be outputted to the user. In the embodiments of the present disclosure, the question and the relevant passage are used as input, and a semi-structured assertion answer is output. The assertion answer according to embodiments of the present disclosure can provide richer semantic content than the traditional short answer, and provide a more concise expression than the traditional long answer, thereby ensuring accuracy of the answer while improving the user experience.

Abstract: Techniques described herein describe a context-aware query suggestion process. Context of a current query may be calculated by analyzing a sequence of previous queries. Historical search data may be mined to generate groups of query suggestion candidates. Using the context of the current query, the current query may be matched with the groups of query suggestion candidates to find a matching query suggestion candidate, which may be provided to the user.

Abstract: Techniques described herein describe a context-aware query suggestion process. Context of a current query may be calculated by analyzing a sequence of previous queries. Historical search data may be mined to generate groups of query suggestion candidates. Using the context of the current query, the current query may be matched with the groups of query suggestion candidates to find a matching query suggestion candidate, which may be provided to the user.

Abstract: Architecture that mines intent of a query from search log data. For example, for a given query, the intent, the major URLs for the intent, and intent attributes, are found. The input is search log data and the output is a database that contains the intent of queries mined from the log data. Data mining techniques are employed to discover major intents of queries in the click-through log data of a search engine. For each query, its expanded queries are created and utilized, as well as co-clicks of the original query and expanded queries in the log data. For each query, clustering is performed on the co-click data of the query and expanded queries to find the major intents of the query.

Abstract: Query classification techniques attempt to classify user search queries in order to better understand user search intent. Understanding a user's search intent allows search engines to provide relevant content tailored to the user's interest. Unfortunately, current classification techniques do not take into account contextual information. Accordingly, as provided herein, a target query may be classified based upon contextual information. In particular, features may be extracted from contextual information and/or other sources. For example, features may be extracted from the target query, related queries, and/or invoked search results of the related queries. In this way, the target query may be classified based upon other queries performed by the user and/or search results of the queries the user found interesting. In addition, a CRF model may be utilized in classifying the target query by providing generalized parameters learned from labeled query sessions.

Abstract: A model generated from search log data predicts a hidden state based on a query to determine a context of the query, such as for providing re-ranked search results, query suggestions and/or URL recommendations.

Abstract: A suffix-tree index may be constructed from search engine search logs. This suffix-tree is scalable and suitable for use in a distributed computing environment. Data mining against the data may proceed with functions including a forward search, backward search, and/or query session retrieval.

Abstract: Techniques described herein describe a context-aware query suggestion process. Context of a current query may be calculated by analyzing a sequence of previous queries. Historical search data may be mined to generate groups of query suggestion candidates. Using the context of the current query, the current query may be matched with the groups of query suggestion candidates to find a matching query suggestion candidate, which may be provided to the user.