Abstract: The present disclosure relates to systems and methods for identifying webpage key points for a webpage. The systems and methods present the webpage key points in a side pane of a browser adjacent to the webpage.

Abstract: Systems, methods, and computer-executable instructions for synthesizing facts from multiple sources. A user search string associated with a topic is received. Queries associated with the user search string are generated. Website content is queried, using the plurality of queries associated with the user search string, to generate results. The results are ranked based on a first feature. The results are filtered based on the first feature to generate intermediate results. The intermediate results are ranked based on a second feature. The second feature is most costly to calculate than the first feature. The filtered intermedia results are filtered based on the second feature to generate final results. Distinct facts from the final results are determined. The distinct facts include content from different URLs. The distinct facts associated with the topic are returned.

Abstract: The present disclosure relates to systems and methods for automatically identifying additional content for a webpage. The systems and methods may create a side pane placed next to a webpage to supplement the webpage in a browser. The side pane may provide additional information or additional content to help users consume the webpage. The additional content may provide webpage insights and help the users further explore the webpage.

Abstract: The present disclosure relates to systems and methods for automatically identifying additional content for a webpage. The systems and methods may create a side pane placed next to a webpage to supplement the webpage in a browser. The side pane may provide additional information or additional content to help users consume the webpage. The additional content may provide webpage insights and help the users further explore the webpage.

Abstract: Described herein is a mechanism to identify user intent in requests submitted to a system such as a digital assistant or question-answer systems. Embodiments utilize a match methodology instead of a classification methodology. Features derived from a subgraph retrieved from a knowledge base based on the request are concatenated with pretrained word embeddings for both the request and a candidate predicate. The concatenated inputs for both the request and predicate are encoded using two independent LSTM networks and then a matching score is calculated using a match LSTM network. The result is identified based on the matching scores for a plurality of candidate predicates. The pretrained word embeddings allow for knowledge transfer since pretrained word embeddings in one intent domain can apply to another intent domain without retraining.

Abstract: The present disclosure relates to systems and methods for automatically identifying additional content for a webpage. The systems and methods may create a side pane placed next to a webpage to supplement the webpage in a browser. The side pane may provide additional information or additional content to help users consume the webpage. The additional content may provide webpage insights and help the users further explore the webpage.

Abstract: The technology described herein makes improved use of limited screen space on a search results page by determining whether to present a question-and-answer experience and/or an entity details experience. This determination effects the amount of information presented and the format in which it is presented. In general, the question-and-answer experience provides less information and is more targeted to a question and query terms other than the entity. In contrast, the entity details experience provides more information about the entity that is not tailored to the query beyond the entity being included in the query. In one aspect, the determination of whether to show a question-and-answer experience and/or an entity details experience is based, at least in part, on an entity-details intent classification score (“intent classification score”) generated by a machine classification system. The classification score may be processed in combination with other criteria to make a final determination.

Abstract: The technology described herein makes improved use of limited screen space on a search results page by determining whether to present a question-and-answer experience and/or an entity details experience. This determination effects the amount of information presented and the format in which it is presented. In general, the question-and-answer experience provides less information and is more targeted to a question and query terms other than the entity. In contrast, the entity details experience provides more information about the entity that is not tailored to the query beyond the entity being included in the query. In one aspect, the determination of whether to show a question-and-answer experience and/or an entity details experience is based, at least in part, on an entity-details intent classification score (“intent classification score”) generated by a machine classification system. The classification score may be processed in combination with other criteria to make a final determination.

Abstract: A method of disambiguating user queries in a multi-turn dialogue include a set of user utterances includes using a predefined language model to recognize an ambiguous entity in an unresolved user utterance from the multi-turn dialogue. The method further includes outputting a clarifying question about the ambiguous entity, and receiving a clarifying user utterance. The method further includes identifying a disambiguating entity in the clarifying user utterance. The method further includes rewriting the unresolved user utterance as a rewritten utterance that replaces the ambiguous entity with the disambiguating entity, and outputting the rewritten utterance to one or more query answering machines.

Abstract: A method of disambiguating user queries in a multi-turn dialogue including a set of user utterances. The method includes using a predefined language model to recognize an ambiguous entity in an unresolved user utterance from the multi-turn dialogue, and using the predefined language model to recognize entity constraints of the ambiguous entity. The method further includes, in a computer-accessible conversation history of the multi-turn dialogue, searching a set of previously-resolved entities for a candidate entity having entity properties with a highest confidence correspondence to the entity constraints of the ambiguous entity. The unresolved user utterance is rewritten as a rewritten utterance that replaces the ambiguous entity with the candidate entity. The rewritten utterance is output to one or more query answering machines.

Abstract: A method for determining whether to dynamically suppress a candidate query answer designated for inclusion in search results includes instantiating a plurality of filtering rules for assessing suppression of a candidate query answer. The filtering rules include one or both of a pattern rule and a site rule. The method further comprises receiving a query, and, after receiving the query, retrieving one or more candidate query answers previously associated with the query. The method further comprises, for each candidate query answer, dynamically suppressing the candidate query answer from a curated position having enhanced prominence within search results relative to a plurality of other result entries, if either or both of a pattern rule and a site rule match the query. The method further includes returning search results including up to one candidate query answer in the curated position, responsive to a candidate query answer not being dynamically suppressed.

Abstract: The technology described herein makes improved use of limited screen space on a search results page by determining whether to present a question-and-answer experience and/or an entity details experience. This determination effects the amount of information presented and the format in which it is presented. In general, the question-and-answer experience provides less information and is more targeted to a question and query terms other than the entity. In contrast, the entity details experience provides more information about the entity that is not tailored to the query beyond the entity being included in the query. In one aspect, the determination of whether to show a question-and-answer experience and/or an entity details experience is based, at least in part, on an entity-details intent classification score (“intent classification score”) generated by a machine classification system. The classification score may be processed in combination with other criteria to make a final determination.

Abstract: A method of disambiguating user queries in a multi-turn dialogue including a set of user utterances. The method includes using a predefined language model to recognize an ambiguous entity in an unresolved user utterance from the multi-turn dialogue, and using the predefined language model to recognize entity constraints of the ambiguous entity. The method further includes, in a computer-accessible conversation history of the multi-turn dialogue, searching a set of previously-resolved entities for a candidate entity having entity properties with a highest confidence correspondence to the entity constraints of the ambiguous entity. The unresolved user utterance is rewritten as a rewritten utterance that replaces the ambiguous entity with the candidate entity. The rewritten utterance is output to one or more query answering machines.

Abstract: A method of disambiguating user queries in a multi-turn dialogue include a set of user utterances includes using a predefined language model to recognize an ambiguous entity in an unresolved user utterance from the multi-turn dialogue. The method further includes outputting a clarifying question about the ambiguous entity, and receiving a clarifying user utterance. The method further includes identifying a disambiguating entity in the clarifying user utterance. The method further includes rewriting the unresolved user utterance as a rewritten utterance that replaces the ambiguous entity with the disambiguating entity, and outputting the rewritten utterance to one or more query answering machines.

Abstract: Described herein is a mechanism to identify user intent in requests submitted to a system such as a digital assistant or question-answer systems. Embodiments utilize a match methodology instead of a classification methodology. Features derived from a subgraph retrieved from a knowledge base based on the request are concatenated with pretrained word embeddings for both the request and a candidate predicate. The concatenated inputs for both the request and predicate are encoded using two independent LSTM networks and then a matching score is calculated using a match LSTM network. The result is identified based on the matching scores for a plurality of candidate predicates. The pretrained word embeddings allow for knowledge transfer since pretrained word embeddings in one intent domain can apply to another intent domain without retraining.

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 method for determining whether to dynamically suppress a candidate query answer designated for inclusion in search results includes instantiating a plurality of filtering rules for assessing suppression of a candidate query answer. The filtering rules include one or both of a pattern rule and a site rule. The method further comprises receiving a query, and, after receiving the query, retrieving one or more candidate query answers previously associated with the query. The method further comprises, for each candidate query answer, dynamically suppressing the candidate query answer from a curated position having enhanced prominence within search results relative to a plurality of other result entries, if either or both of a pattern rule and a site rule match the query. The method further includes returning search results including up to one candidate query answer in the curated position, responsive to a candidate query answer not being dynamically suppressed.

Abstract: Systems, methods, and computer-executable instructions for synthesizing facts from multiple sources. A user search string associated with a topic is received. Queries associated with the user search string are generated. Website content is queried, using the plurality of queries associated with the user search string, to generate results. The results are ranked based on a first feature. The results are filtered based on the first feature to generate intermediate results. The intermediate results are ranked based on a second feature. The second feature is most costly to calculate than the first feature. The filtered intermedia results are filtered based on the second feature to generate final results. Distinct facts from the final results are determined. The distinct facts include content from different URLs. The distinct facts associated with the topic are returned.

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: Described herein are technologies relating to parsing at least one document to return a snippet that includes information that answers a question set forth in a query. A ranked list of search results is generated based upon the query, and a document represented by a search result in the ranked list of search results is retrieved from a search engine cache or a web server that hosts the document. The document is parsed, and snippets in the document are extracted and ranked. At least a most highly-ranked snippet is returned to a client computing device as including an answer to the question set forth in the query.