Search in social networks such as Facebook poses different challenges than in classical web search: besides the query text, it is important to take into account the searcher's context to provide relevant results. Their social graph is an integral part of this context and is a unique aspect of Facebook search. While embedding-based retrieval (EBR) has been applied in eb search engines for years, Facebook search was still mainly based on a Boolean matching model. In this paper, we discuss the techniques for applying EBR to a Facebook Search system. We introduce the unified embedding framework developed to model semantic embeddings for personalized search, and the system to serve embedding-based retrieval in a typical search system based on an inverted index. We discuss various tricks and experiences on end-to-end optimization of the whole system, including ANN parameter tuning and full-stack optimization. Finally, we present our progress on two selected advanced topics about modeling. We evaluated EBR on verticals 1 for Facebook Search with significant metrics gains observed in online A/B experiments. We believe this paper will provide useful insights and experiences to help people on developing embedding-based retrieval systems in search engines. CCS CONCEPTS • Information systems → Retrieval models and ranking; Search engine architectures and scalability; • Computing methodologies → Learning latent representations.

Empathy is critical to successful mental health support.Empathy measurement has predominantly occurred in synchronous, face-toface settings, and may not translate to asynchronous, text-based contexts. Because millions of people use text-based platforms for mental health support, understanding empathy in these contexts is crucial. In this work, we present a computational approach to understanding how empathy is expressed in online mental health platforms. We develop a novel unifying theoretically-grounded framework for characterizing the communication of empathy in text-based conversations. We collect and share a corpus of 10k (post, response) pairs annotated using this empathy framework with supporting evidence for annotations (rationales). We develop a multi-task RoBERTa-based bi-encoder model for identifying empathy in conversations and extracting rationales underlying its predictions. Experiments demonstrate that our approach can effectively identify empathic conversations. We further apply this model to analyze 235k mental health interactions and show that users do not self-learn empathy over time, revealing opportunities for empathy training and feedback.

No abstract

No abstract

Hereditary hemochromatosis (HHC) is one of the most frequent genetic disorders in humans. In healthy individuals, absorption of iron in the intestine is tightly regulated by cells with the highest iron demand, in particular erythroid precursors. Cloning of intestinal iron transporter proteins provided new insight into mechanisms and regulation of intestinal iron absorption. The aim of this study was to assess whether, in humans, the two transporters are regulated in an iron-dependent manner and whether this regulation is disturbed in HHC. Using quantitative PCR, we measured mRNA expression of divalent cation transporter 1 (DCT1), iron-regulated gene 1 (IREG1), and hephaestin in duodenal biopsy samples of individuals with normal iron levels, iron-deficiency anemia, or iron overload. In controls, we found inverse relationships between the DCT1 splice form containing an iron-responsive element (IRE) and blood hemoglobin, serum transferrin saturation, or ferritin. Subjects with iron-deficiency anemia showed a significant increase in expression of the spliced form, DCT1(IRE) mRNA. Similarly, in subjects homozygous for the C282Y HFE mutation, DCT1(IRE) expression levels remained high despite high serum iron saturation. Furthermore, a significantly increased IREG1 expression was observed. Hephaestin did not exhibit a similar iron-dependent regulation. Our data show that expression levels of human DCT1 mRNA, and to a lesser extent IREG1 mRNA, are regulated in an iron-dependent manner, whereas mRNA of hephaestin is not affected. The lack of appropriate downregulation of apical and basolateral iron transporters in duodenum likely leads to excessive iron absorption in persons with HHC.

Background In the present study, 20 patients with mandibular fracture were included to evaluate the versatility of titanium 3D plate in comparison with conventional titanium miniplate fixation. Methods The patients were alternatively allocated to either the 3D plate group or Miniplate group. The patients were evaluated for the clinical assessment of mobility after fixation, pre and post-surgical occlusal relationship, adequacy of reduction on post operative radiograph and any post surgical complications. Results All 25 fractures in 20 patients were found to be adequately fixed when checked intra-operatively. No postoperative IMF was required in either of the groups. The mean radiographic score at post operative time interval in Miniplate group was found to be 2.80 ± 0.42 and in 3D Plate was found to be 2.90 ± 0.32. The mean radiographic score at 3 months time interval in Miniplate group was found to be 2.70 ± 0.48 and in 3D Plate was found to be 2.70 ± 0.48. Radiolucency at 3 months period was found in 1 patient (10%) in the miniplate group and it was not found in any patients in the 3D plate group. None of the patients in both the groups had complications of non-union or mal-union. In miniplate group, 2 patients (20%) had infections and in 3D plate group 1 patient (10%) had infection. 3 patients in miniplate group had occlusal discrepancies (30%) and 1 patient in 3D plate group had occlusal discrepancies (10%). Overall, complications were found in 6 patients (60%) in miniplate group and 2 patients (20%) in 3D plate group. The data when compared was statistically significant (P \ 0.05). ConclusionThe 3D plating system was found to be advantageous over conventional miniplates. It uses lesser foreign material, reduces the operation time and overall cost of the treatment. Thus 3D plate can be used as an alternative to conventional miniplates. The system is reliable and effective treatment modality for mandibular fractures.

No abstract

We present a de novo hierarchical simulation framework for first-principles based predictive simulations of materials and their validation on high-end parallel supercomputers and geographically distributed clusters. In this framework, highend chemically reactive and non-reactive molecular dynamics (MD) simulations explore a wide solution space to discover microscopic mechanisms that govern macroscopic material properties, into which highly accurate quantum mechanical (QM) simulations are embedded to validate the discovered mechanisms and quantify the uncertainty of the solution. The framework includes an embedded divide-andconquer (EDC) algorithmic framework for the design of linear-scaling simulation algorithms with minimal bandwidth complexity and tight error control. The EDC framework also enables adaptive hierarchical simulation with automated model transitioning assisted by graph-based event tracking. A tunable hierarchical cellular decomposition parallelization framework then maps the O(N) EDC algorithms onto petaflops computers, while achieving performance tunability through a hierarchy of parameterized cell data/ computation structures, as well as its implementation using hybrid grid remote procedure call + message passing + threads programming. High-end computing platforms such as IBM BlueGene/L, SGI Altix 3000 and the NSF TeraGrid provide an excellent test grounds for the framework. On these platforms, we have achieved unprecedented scales of quantum-mechanically accurate and well validated, chemically reactive atomistic simulations-1.06 billion-atom fast reactive force-field MD and 11.8 million-atom (1.04 trillion grid points) quantum-mechanical MD in the framework of the EDC density functional theory on adaptive multigridsin addition to 134 billion-atom non-reactive space-time multiresolution MD, with the parallel efficiency as high as 0.998 on 65,536 dual-processor BlueGene/L nodes. We have also achieved an automated execution of hierarchical QM/MD simulation on a grid consisting of 6 supercomputer centers in the US and Japan (in total of 150,000 processor hours), in which the number of processors change dynamically on demand and resources are allocated and migrated dynamically in response to faults. Furthermore, performance portability has been demonstrated on a wide range of platforms such as BlueGene/L, Altix 3000, and AMD Opteron-based Linux clusters.