In the era of mobile computing, deploying efficient Natural Language Processing (NLP) models in resource-restricted edge settings presents significant challenges, particularly in environments requiring strict privacy compliance, real-time responsiveness, and diverse multi-tasking capabilities. These challenges create a fundamental need for ultra-compact models that maintain strong performance across various NLP tasks while adhering to stringent memory constraints. To this end, we introduce Edge ultra-lIte BERT framework (EI-BERT) with a novel cross-distillation method. EI-BERT efficiently compresses models through a comprehensive pipeline including hard token pruning, cross-distillation, parameter quantization, and plugin-and-play deployment. Specifically, the cross-distillation method uniquely positions the teacher model to understand the student model's perspective, ensuring efficient knowledge transfer through parameter integration and the mutual interplay between models. Through extensive experiments, we achieve a remarkably compact BERT-based model of only 1.91 MB - the smallest to date for Natural Language Understanding (NLU) tasks. This ultra-compact model has been successfully deployed across multiple scenarios within the Alipay ecosystem, demonstrating significant improvements in real-world applications. For example, it has been integrated into Alipay's live Edge Recommendation system since January 2024, currently serving the app's recommendation traffic across 8.4 million daily active devices.

The recently explosive growth of Super Apps brings great convenience to people's daily life by providing a wide variety of services through mini-programs, including online shopping, travel, finance, and so on. Due to the considerable gap between various scenarios, the restriction of effective information transfer and sharing severely blocks the efficient delivery of online services, potentially affecting the user's app experience. To deeply understand users' needs, we propose SupKG, a commonsense knowledge graph towards Super APP to help comprehensively characterize user behaviors across different business scenarios. In particular, our SupKG is carefully established from multiplex and heterogeneous data source in Alipay (a well-known Super App in China), which also emphasize abundant spatiotemporal relations and intent-related entities to answer the fundamental question in life service ''which service do users need at what time and where''.

While online advertising is one of the major sources of income for search engines, pumping up the incomes from business advertisements while ensuring the user experience becomes a challenging but emerging area. Designing high-quality advertisements with persuasive content has been proved as a way to increase revenues through improving the Click-Through Rate (CTR). However, it is difficult to scale up the design of high-quality ads, due to the lack of automation in creativity. In this paper, we present Commonsense-Enriched Advertisement on Search Engine (CHASE) --- a system for the automatic generation of persuasive ads. CHASE adopts a specially designed language model that fuses the keywords, commonsense-related texts, and marketing contents to generate persuasive advertisements. Specifically, the language model has been pre-trained using massive contents of explicit knowledge and fine-tuned with well-constructed quasi-parallel corpora with effective control of the proportion of commonsense in the generated ads and fitness to the ads' keywords. The effectiveness of the proposed method CHASE has been verified by real-world web traffics for search and manual evaluation. In A/B tests, the advertisements generated by CHASE would bring 11.13% CTR improvement. The proposed model has been deployed to cover three advertisement domains (which are kid education, psychological counseling, and beauty e-commerce) at Baidu, the world's largest Chinese search engine, with adding revenue of about 1 million RMB (Chinese Yuan) per day.

OBJECTIVE: Quantitative Structure-Activity Relationship (QSAR) models can predict adverse drug reactions (ADRs), and thus provide early warnings of potential hazards. Timely identification of potential safety concerns could protect patients and aid early diagnosis of ADRs among the exposed. Our objective was to determine whether global spontaneous reporting patterns might allow chemical substructures associated with Stevens-Johnson Syndrome (SJS) to be identified and utilized for ADR prediction by QSAR models. MATERIALS AND METHODS: Using a reference set of 364 drugs having positive or negative reporting correlations with SJS in the VigiBase global repository of individual case safety reports (Uppsala Monitoring Center, Uppsala, Sweden), chemical descriptors were computed from drug molecular structures. Random Forest and Support Vector Machines methods were used to develop QSAR models, which were validated by external 5-fold cross validation. Models were employed for virtual screening of DrugBank to predict SJS actives and inactives, which were corroborated using knowledge bases like VigiBase, ChemoText, and MicroMedex (Truven Health Analytics Inc, Ann Arbor, Michigan). RESULTS: We developed QSAR models that could accurately predict if drugs were associated with SJS (area under the curve of 75%-81%). Our 10 most active and inactive predictions were substantiated by SJS reports (or lack thereof) in the literature. DISCUSSION: Interpretation of QSAR models in terms of significant chemical descriptors suggested novel SJS structural alerts. CONCLUSIONS: We have demonstrated that QSAR models can accurately identify SJS active and inactive drugs. Requiring chemical structures only, QSAR models provide effective computational means to flag potentially harmful drugs for subsequent targeted surveillance and pharmacoepidemiologic investigations.