Abstract: The present disclosure is directed to systems and methods that include and/or leverage one or more machine-learned language models that generate intermediate textual analysis (e.g., including usage of structural tools such as APIs) in service of contextual text generation. For example, a computing system can obtain a contextual text string that includes one or more contextual text tokens. The computing system can process the contextual text string with the machine-learned language model to generate one or more intermediate text strings that include one or more intermediate text tokens. The computing system can process the one or more intermediate text strings with the machine-learned language model to generate an output text string comprising one or more output text tokens. The one or more intermediate text strings can include textual analysis of the contextual text string that supports the output text string.

Abstract: The present disclosure is directed to systems and methods that include and/or leverage one or more machine-learned language models that generate intermediate textual analysis (e.g., including usage of structural tools such as APIs) in service of contextual text generation. For example, a computing system can obtain a contextual text string that includes one or more contextual text tokens. The computing system can process the contextual text string with the machine-learned language model to generate one or more intermediate text strings that include one or more intermediate text tokens. The computing system can process the one or more intermediate text strings with the machine-learned language model to generate an output text string comprising one or more output text tokens. The one or more intermediate text strings can include textual analysis of the contextual text string that supports the output text string.

Abstract: The present disclosure is directed to systems and methods that include and/or leverage one or more machine-learned language models that generate intermediate textual analysis (e.g., including usage of structural tools such as APIs) in service of contextual text generation. For example, a computing system can obtain a contextual text string that includes one or more contextual text tokens. The computing system can process the contextual text string with the machine-learned language model to generate one or more intermediate text strings that include one or more intermediate text tokens. The computing system can process the one or more intermediate text strings with the machine-learned language model to generate an output text string comprising one or more output text tokens. The one or more intermediate text strings can include textual analysis of the contextual text string that supports the output text string.

Abstract: The present disclosure is directed to systems and methods that include and/or leverage one or more machine-learned language models that generate intermediate textual analysis (e.g., including usage of structural tools such as APIs) in service of contextual text generation. For example, a computing system can obtain a contextual text string that includes one or more contextual text tokens. The computing system can process the contextual text string with the machine-learned language model to generate one or more intermediate text strings that include one or more intermediate text tokens. The computing system can process the one or more intermediate text strings with the machine-learned language model to generate an output text string comprising one or more output text tokens. The one or more intermediate text strings can include textual analysis of the contextual text string that supports the output text string.

Abstract: Different ad selection techniques may be evaluated and compared by (i) combining ads generated using at least two different techniques and (ii) determining performance statistics of these combined (e.g., interleaved) advertising serves over time. The relative performance of the different techniques can then be determined. These principles can also be used to gauge different ad scoring techniques. These principles can also be used to gauge different ad rendering techniques.

Abstract: A system ranks documents based, at least in part, on a ranking model. The ranking model may be generated to predict the likelihood that a document will be selected. The system may receive a search query and identify documents relating to the search query. The system may then rank the documents based, at least in part, on the ranking model and form search results for the search query from the ranked documents.

Abstract: A system for generating a model is provided. The system generates, or selects, candidate conditions and generates, or otherwise obtains, statistics regarding the candidate conditions. The system also forms rules based, at least in part, on the statistics and the candidate conditions and selectively adds the rules to the model.

Abstract: A computer-implemented method for determining whether a target text-string is correctly spelled is provided. The target text-string is compared to a corpus to determine a set of contexts which each include an occurrence of the target text-string. Using heuristics, each context of the set is characterized based on occurrences in the corpus of the target text-string and a reference text-string. Contexts are characterized as including a correct spelling of the target text-string, an incorrect spelling of the reference text-string, or including an indeterminate usage of the target text-string. A likelihood that the target text-string is a misspelling of the reference text-string is computed as a function of the quantity of contexts including a correct spelling of the target text-string and the quantity of contexts including an incorrect spelling of a reference text-string. In one application, the target text-string is received in a search query, the search executed following a spell-check.

Abstract: A computer-implemented method for determining whether a target text-string is correctly spelled is provided. The target text-string is compared to a corpus to determine a set of contexts which each include an occurrence of the target text-string. Using heuristics, each context of the set is characterized based on occurrences in the corpus of the target text-string and a reference text-string. Contexts are characterized as including a correct spelling of the target text-string, an incorrect spelling of the reference text-string, or including an indeterminate usage of the target text-string. A likelihood that the target text-string is a misspelling of the reference text-string is computed as a function of the quantity of contexts including a correct spelling of the target text-string and the quantity of contexts including an incorrect spelling of a reference text-string. In one application, the target text-string is received in a search query, the search executed following a spell-check.

Abstract: A system may track statistics for a number of features using an approximate counting technique by: subjecting each feature to multiple, different hash functions to generate multiple, different hash values, where each of the hash values may identify a particular location in a memory, and storing statistics for each feature at the particular locations identified by the hash values. The system may generate rules for a model based on the tracked statistics.

Abstract: Keyword suggestions that are category-aware (and field-proven) may be used to help advertisers better target the serving of their ads, and may reduce unused ad spot inventory. The advertiser can enter ad information, such as a creative, a landing Webpage, other keywords, etc. for example. A keyword facility may use this entered ad information as seed information to infer one or more categories. It may then request that the advertiser confirm or deny some basic feedback information (e.g., categories, Webpage information, etc.). For example, an advertiser may be provided with candidate categories and may be asked to confirm (e.g., using checkboxes) which of the categories are relevant to their ad. Keywords may be determined using at least the categories. The determined keywords may be provided to the advertiser as suggested keywords, or may automatically populate ad serving constraint information as targeting keywords.

Abstract: Keyword suggestions that are category-aware (and field-proven) may be used to help advertisers better target the serving of their ads, and may reduce unused ad spot inventory. The advertiser can enter ad information, such as a creative, a landing Webpage, other keywords, etc. for example. A keyword facility may use this entered ad information as seed information to infer one or more categories. It may then request that the advertiser confirm or deny some basic feedback information (e.g., categories, Webpage information, etc.). For example, an advertiser may be provided with candidate categories and may be asked to confirm (e.g., using checkboxes) which of the categories are relevant to their ad. Keywords may be determined using at least the categories. The determined keywords may be provided to the advertiser as suggested keywords, or may automatically populate ad serving constraint information as targeting keywords.

Abstract: A system for generating a model is provided. The system generates, or selects, candidate conditions and generates, or otherwise obtains, statistics regarding the candidate conditions. The system also forms rules based, at least in part, on the statistics and the candidate conditions and selectively adds the rules to the model.

Abstract: A system may track statistics for a number of features using an approximate counting technique by: subjecting each feature to multiple, different hash functions to generate multiple, different hash values, where each of the hash values may identify a particular location in a memory, and storing statistics for each feature at the particular locations identified by the hash values. The system may generate rules for a model based on the tracked statistics.

Abstract: A system for generating a model is provided. The system generates, or selects, candidate conditions and generates, or otherwise obtains, statistics regarding the candidate conditions. The system also forms rules based, at least in part, on the statistics and the candidate conditions and selectively adds the rules to the model.

Abstract: A client-side application (such as a browser, a browser plug-in, a browser toolbar plug-in, etc. on an end user's computer) is used to support the serving of content-relevant ads to the client device. The client-side application may provide such support by sending document information (such as a document identifier, document content, content relevance information, etc.) to a content ad server. The client-side application may also be used to combine content of the document and the content-relevant ads. For example, the client-side application may combine content of the document and the ads in a window (e.g., in a browser window), may provide the ads in a window above, below, adjacent to a document window, may provide the ads in “chrome” of the browser, etc.

Abstract: A geographic relevance component determines geographic relevance of web resources based on an analysis of data points that correspond to estimated physical locations of the IP addresses of a number of visitors to the web site. The geographic relevance component may additionally determine the probability that a particular user is within the geographical relevance corresponding to a web resource.

Abstract: A computer-implemented method for determining whether a target text-string is correctly spelled is provided. The target text-string is compared to a corpus to determine a set of contexts which each include an occurrence of the target text-string. Using heuristics, each context of the set is characterized based on occurrences in the corpus of the target text-string and a reference text-string. Contexts are characterized as including a correct spelling of the target text-string, an incorrect spelling of the reference text-string, or including an indeterminate usage of the target text-string. A likelihood that the target text-string is a misspelling of the reference text-string is computed as a function of the quantity of contexts including a correct spelling of the target text-string and the quantity of contexts including an incorrect spelling of a reference text-string. In one application, the target text-string is received in a search query, the search executed following a spell-check.

Abstract: A system may track statistics for a number of features using an approximate counting technique by: subjecting each feature to multiple, different hash functions to generate multiple, different hash values, where each of the hash values may identify a particular location in a memory, and storing statistics for each feature at the particular locations identified by the hash values. The system may generate rules for a model based on the tracked statistics.

Abstract: A client-side application (such as a browser, a browser plug-in, a browser toolbar plug-in, etc. on an end user's computer) is used to support the serving of content-relevant ads to the client device. The client-side application may provide such support by sending document information (such as a document identifier, document content, content relevance information, etc.) to a content ad server. The client-side application may also be used to combine content of the document and the content-relevant ads. For example, the client-side application may combine content of the document and the ads in a window (e.g., in a browser window), may provide the ads in a window above, below, adjacent to a document window, may provide the ads in “chrome” of the browser, etc.