Abstract: A computer-implemented method includes receiving a document insight request that requests document insights for a corpus of documents. The document insight request includes the corpus of documents, a set of entities contained within each document of the corpus of documents, and document insight request parameters that includes a confidence value threshold. The method also includes generating the document insights for the corpus of documents based on the confidence value threshold. Here, the document insights include an accuracy target and a user review rate target. The method also includes transmitting the document insights to the user device causing a graphical user interface to display the document insights on the user device.

Abstract: An example method includes providing, to a sequence model (i) a plurality of few-shot prompts, wherein each prompt comprises a demonstration passage, a demonstration task, and a demonstration query, wherein the demonstration task describes a type of retrieval, and wherein the demonstration query is relevant to the demonstration task, and (ii) a plurality of passages sampled from a corpus of passages. The method also includes receiving, from the sequence model and for the plurality of passages and based on the plurality of few-shot prompts, a respective plurality of predicted task-query pairs, the sequence model having been prompted to predict a task based on an input passage, and predict an output query relevant to the predicted task. The method further includes generating a synthetic training dataset comprising the plurality of passages and the respective plurality of predicted task-query pairs. The method also includes providing the synthetic training dataset.

Abstract: A computer-implemented method includes receiving a document insight request that requests document insights for a corpus of documents. The document insight request includes the corpus of documents, a set of entities contained within each document of the corpus of documents, and document insight request parameters that includes a confidence value threshold. The method also includes generating the document insights for the corpus of documents based on the confidence value threshold. Here, the document insights include an accuracy target and a user review rate target. The method also includes transmitting the document insights to the user device causing a graphical user interface to display the document insights on the user device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining a number of unique viewers of a content item. In one aspect, a method includes receiving an identifier specifying characteristics of a user associated with a device that was used to present a given content item. A user category is identified for the received identifier based on the characteristics. Each user category of a set of user categories include a respective number of pseudo-users. The received identifier is assigned to a given pseudo-user in the identified user category based on a non-linear distribution of identifiers per actual user in the identified user category. A number of unique users, including the given pseudo-user, that have viewed the given content item is determined based on a total number of pseudo-users that have been assigned an identifier corresponding to presentation of the given content item.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for collecting and applying visibility statistics in online advertising are disclosed. Ad block visibility data relating to initial visibility characteristics and subsequent visibility characteristics of ad blocks on webpages are collected from a sample of browser sessions and aggregated to provide a representative historical view of ad block visibility characteristics on those webpages. The collected visibility data are used to build a predictive model of ad block visibility characteristics for future sessions. Ad selection can be based on the predicted visibility characteristics for ad blocks on a webpage as rendered on a particular requesting client device. Ad targeting and pricing can be specified in terms of predicted visibility characteristics of ad blocks.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer-readable storage medium, for determining performance for a campaign.