Web page categorization has been extensively studied in the literature and has been successfully used to improve information retrieval, recommendation, personalization and ad targeting. With the new industry trend of not tracking users' online behavior without their explicit permission, using contextual targeting to accurately understand web pages in order to display ads that are topically relevant to the pages becomes more important. This is challenging, however, because an ad request only contains the URL of a web page. As a result, there is very limited available text for making accurate classifications. In this paper, we propose a unified multilingual model that can seamlessly classify web pages in 5 high-impact languages using either their full content or just their URLs with limited text. We adopt multiple data sampling techniques to increase coverage for rare categories in our training corpus, and modify the loss using class-based re-weighting to smooth the influence of frequent versus rare categories. We also propose using an ensemble of teacher models for knowledge distillation and explore different ways to create a teacher ensemble. Offline evaluation shows at least 2.6% improvement in mean average precision across 5 languages compared to a URL classification model trained with single-teacher knowledge distillation. The unified model for both full-content and URL-only input further improves the mean average precision of the dedicated URL classification model by 0.6%. We launched the proposed models, which achieve at least 37% better mean average precision than the legacy tree-based models, for contextual targeting in the Yahoo Demand Side Platform, leading to a significant ad delivery and revenue increase.

As we move toward a cookie-less world, the ability to track users' online activities for behavior targeting will be drastically reduced, making contextual targeting an appealing alternative for advertising platforms. Category-based contextual targeting displays ads on web pages that are relevant to advertiser-targeted categories, according to a pre-defined taxonomy. Accurate web page classification is key to the success of this approach. In this paper, we use multilingual Transformer-based transfer learning models to classify web pages in five high-impact languages. We adopt multiple data sampling techniques to increase coverage for rare categories, and modify the loss using class-based re-weighting to smooth the influence of frequent versus rare categories. Offline evaluation shows that these are crucial for improving our classifiers. We leverage knowledge distillation to train accurate models that are lightweight in terms of (i) model size, and (ii) the input text used. Classifying web pages using only text from the URL addresses a unique challenge for contextual targeting in that bid requests come to ad systems as URLs without content, while crawling is time consuming and costly. We launched the proposed models for contextual targeting in the Yahoo DSP, significantly increasing its revenue.

Multi-Label Hierarchical Text Classification (MLHTC) is the task of categorizing documents into one or more topics organized in an hierarchical taxonomy.MLHTC can be formulated by combining multiple binary classification problems with an independent classifier for each category.We propose a novel transfer learning based strategy, HTrans, where binary classifiers at lower levels in the hierarchy are initialized using parameters of the parent classifier and fine-tuned on the child category classification task.In HTrans, we use a Gated Recurrent Unit (GRU)-based deep learning architecture coupled with attention.Compared to binary classifiers trained from scratch, our HTrans approach results in significant improvements of 1% on micro-F1 and 3% on macro-F1 on the RCV1 dataset.Our experiments also show that binary classifiers trained from scratch are significantly better than single multi-label models.

Today’s business applications are typically built on top of middleware platforms such as J2EE and use transactions that have evolved into long running activities able to adapt to different circumstances. Specifications, such as the J2EE Activity Service, have arised for applications requiring that support. These applications also demand high availability to prevent financial losses and/or service level agreements (SLAs) violations due to service unavailability or crashes. Replication is a means to attain high availability but current middleware does not provide highly available transactions. In the advent of crashes, running transactions abort and the application is forced to re-execute them, what results in a loss of availability and transparency. Most approaches using J2EE consider the replication of either the application server or the database. This results in poor availability when the non-replicated tier crashes. This paper presents a novel J2EE replication support for both, application server and database layers providing highly available transactions and long running activities. Failure masking is transparent to client applications. A prototype has been implemented and evaluated.

Due to the rapid acceptance of web services and its fast spreading, a number of mission-critical systems will be deployed as web services in next years. The availability of those systems must be guaranteed in case of failures and network disconnections. An example of web services for which availability will be a crucial issue are those belonging to coordination web service infrastructure, such as web services for transactional coordination (e.g., WS-CAF and WS-Transaction). These services should remain available despite site and connectivity failures to enable business interactions on a 24x7 basis. Some of the common techniques for attaining availability consist in the use of a clustering approach. However, in an Internet setting a domain can get partitioned from the network due to a link overload or some other connectivity problems. The unavailability of a coordination service impacts the availability of all the partners in the business process. That is, coordination services are an example of critical components that need higher provisions for availability. In this paper, we address this problem by providing an infrastructure, WS-Replication, for WAN replication of web services. The infrastructure is based on a group communication web service, WS-Multicast, that respects the web service autonomy. The transport of WS-Multicast is based on SOAP and relies exclusively on web service technology for interaction across organizations. We have replicated WS-CAF using our WS-Replication framework and evaluated its performance.

Web services have become a very powerful technology to build service oriented architectures and standardize the access to legacy services. Through Web service composition new added value Web services can be created out of existing ones. Examples of these compositions are virtual organizations, outsourcing, enterprise application integration, business process definitions and business to business inter/intra-enterprise relationships. In order to enable the construction of business processes as composite Web services, a number of composition languages has been proposed by the software industry. However, the handiwork of specifying a business process with these languages through simple text or XML editors is tough, complex and error prone. Visual support can ease the definition of business processes. In this paper, we describe ZenFlow, a visual composition tool for Web services written in BPEL4WS. ZenFlow provides several visual facilities to ease the definition of a business process such as multiple views of a process, syntactic and semantic awareness, filtering, logical zooming capabilities and hierarchical representations.