Abstract: A platform for generating query-answer pairs is described herein, wherein the platform is well-suited for generating query-answer pairs for a variety of topics. The platform comprises a topic-specific classifier that is configured to identify queries from a query log that are fact-seeking queries that belong to a topic. The platform further comprises a domain identifier component that identifies domains that are relevant to the topic, wherein the domains comprise pages. The platform further includes a passage extraction system that comprises a hierarchy of rankers, wherein the passage extraction system is configured to identify passages in the pages that belong to the domain that comprise answers to the fact-seeking queries that belong to the topic.

Abstract: A platform for generating query-answer pairs is described herein, wherein the platform is well-suited for generating query-answer pairs for a variety of topics. The platform comprises a topic-specific classifier that is configured to identify queries from a query log that are fact-seeking queries that belong to a topic. The platform further comprises a domain identifier component that identifies domains that are relevant to the topic, wherein the domains comprise pages. The platform further includes a passage extraction system that comprises a hierarchy of rankers, wherein the passage extraction system is configured to identify passages in the pages that belong to the domain that comprise answers to the fact-seeking queries that belong to the topic.

Abstract: Various technologies described herein pertain to use of path-constrained random walks for query expansion and/or query document matching. Clickthrough data from search logs is represented as a labeled and directed graph. Path-constrained random walks are executed over the graph based upon an input query. The graph includes a first set of nodes that represent queries included in the clickthrough data from search logs, a second set of nodes that represent documents included in the clickthrough data from the search logs, a third set of nodes that represent words from the queries and the documents, and edges between nodes that represent relationships between queries, documents, and words. The path-constrained random walks include traversals over edges of the graph between nodes. Further, a score for a relationship between a target node and a source node representative of the input query is computed based at least in part upon the path-constrained random walks.

Abstract: Various technologies described herein pertain to use of path-constrained random walks for query expansion and/or query document matching. Clickthrough data from search logs is represented as a labeled and directed graph. Path-constrained random walks are executed over the graph based upon an input query. The graph includes a first set of nodes that represent queries included in the clickthrough data from search logs, a second set of nodes that represent documents included in the clickthrough data from the search logs, a third set of nodes that represent words from the queries and the documents, and edges between nodes that represent relationships between queries, documents, and words. The path-constrained random walks include traversals over edges of the graph between nodes. Further, a score for a relationship between a target node and a source node representative of the input query is computed based at least in part upon the path-constrained random walks.

Abstract: A method for computer-assisted translation from a source language to a target language makes use of number of rules. Each rule forms an association between a representation of a sequence of source language tokens with a corresponding tree-based structure in the target language. The tree-based structure for each of at least some of the rules represents one or more asymmetrical relations within a number of target tokens associated with the tree-based structure and provides an association of the target tokens with the sequence of source language tokens of the rule. An input sequence of source tokens is decoded according to the rules to generate a representation of one or more output sequences of target language tokens. Decoding includes, for each of at least some sub-sequences of the input sequence of source tokens, determining a tree-based structure associated with the sub-sequence according a match to one of the plurality of rules.

Abstract: The invention relates to systems and methods for automatically translating documents from a first language to a second language. To carry out the translation of a document, elements of information are extracted from the document and are translated using one or more specialized translation processes. The remainder of the document is separately translated by a statistical translation process. The translated elements of information and the translated remainder are then merged into a final translated document.

Abstract: A method for computer-assisted translation from a source language to a target language makes use of number of rules. Each rule forms an association between a representation of a sequence of source language tokens with a corresponding tree-based structure in the target language. The tree-based structure for each of at least some of the rules represents one or more asymmetrical relations within a number of target tokens associated with the tree-based structure and provides an association of the target tokens with the sequence of source language tokens of the rule. An input sequence of source tokens is decoded according to the rules to generate a representation of one or more output sequences of target language tokens. Decoding includes, for each of at least some sub-sequences of the input sequence of source tokens, determining a tree-based structure associated with the sub-sequence according a match to one of the plurality of rules.

Abstract: The invention relates to systems and methods for automatically translating documents from a first language to a second language. To carry out the translation of a document, elements of information are extracted from the document and are translated using one or more specialized translation processes. The remainder of the document is separately translated by a statistical translation process. The translated elements of information and the translated remainder are then merged into a final translated document.