Relying entirely on an attention mechanism, the Transformer introduced by Vaswani et al. (2017) achieves state-of-the-art results for machine translation. In contrast to recurrent and convolutional neural networks, it does not explicitly model relative or absolute position information in its structure. Instead, it requires adding representations of absolute positions to its inputs. In this work we present an alternative approach, extending the self-attention mechanism to efficiently consider representations of the relative positions, or distances between sequence elements. On the WMT 2014 English-to-German and English-to-French translation tasks, this approach yields improvements of 1.3 BLEU and 0.3 BLEU over absolute position representations, respectively. Notably, we observe that combining relative and absolute position representations yields no further improvement in translation quality. We describe an efficient implementation of our method and cast it as an instance of relation-aware self-attention mechanisms that can generalize to arbitrary graphlabeled inputs.

This study reports on the accuracy of smartphone sound measurement applications (apps) and whether they can be appropriately employed for occupational noise measurements. A representative sample of smartphones and tablets on various platforms were acquired, more than 130 iOS apps were evaluated but only 10 apps met our selection criteria. Only 4 out of 62 Android apps were tested. The results showed two apps with mean differences of 0.07 dB (unweighted) and −0.52 dB (A-weighted) from the reference values. Two other apps had mean differences within ± 2 dB. The study suggests that certain apps may be appropriate for use in occupational noise measurements.

We study the task of cross-database semantic parsing (XSP), where a system that maps natural language utterances to executable SQL queries is evaluated on databases unseen during training. Recently, several datasets, including Spider, were proposed to support development of XSP systems. We propose a challenging evaluation setup for cross-database semantic parsing, focusing on variation across database schemas and in-domain language use. We re-purpose eight semantic parsing datasets that have been well-studied in the setting where in-domain training data is available, and instead use them as additional evaluation data for XSP systems instead. We build a system that performs well on Spider, and find that it struggles to generalize to our re-purposed set. Our setup uncovers several generalization challenges for cross-database semantic parsing, demonstrating the need to use and develop diverse training and evaluation datasets. * Work done during an internship at Google. Advising (Finegan-Dollak et al., 2018) NL: For EECS 478, how many credits is it? SQL: select distinct credits from course where department ='EECS' and number = 478; GeoQuery (Zelle and Mooney, 1996) NL: How many people live in mississippi? SQL: select population from state where state name = 'mississippi'; ATIS (Hemphill et al., 1990; Dahl et al., 1994) NL: Flights from Phoenix to Milwaukee SQL: select distinct T1.flight id from airport service as T2, airport service as T3, city as T4, city as T5, flight as T1 where T4.city code = T2.city code and T4.city name = 'Phoenix' and T5.city code = T3.city code and T5.city name = 'Milwaukee' and T1.from airport = T2.airport code and T1.to airport = T3.airport code; Spider (Yu et al., 2018) NL: List the emails of the professionals who live in the state of Hawaii or the state of Wisconsin.

Objective Osteoarthritis (OA) is one of the leading causes of disability in the adult population. Common nonoperative treatment options include nonsteroidal anti-inflammatory drugs (NSAIDs), intra-articular corticosteroids, and intra-articular injections of hyaluronic acid (HA). HA is found intrinsically within the knee joint providing viscoelastic properties to the synovial fluid. HA therapy provides anti-inflammatory relief through a number of different pathways, including the suppression of pro-inflammatory cytokines and chemokines. Methods We conducted a systematic review to summarize the published literature on the anti-inflammatory properties of hyaluronic acid in osteoarthritis. Included articles were categorized based on the primary anti-inflammatory responses described within them, by the immediate cell surface receptor protein assessed within the article, or based on the primary theme of the article. Key findings aimed to describe the macromolecules and inflammatory-mediated responses associated with the cell transmembrane receptors. Results Forty-eight articles were included in this systematic review that focused on the general anti-inflammatory effects of HA in knee OA, mediated through receptor-binding relationships with cluster determinant 44 (CD44), toll-like receptor 2 (TLR-2) and 4 (TLR-4), intercellular adhesion molecule-1 (ICAM-1), and layilin (LAYN) cell surface receptors. Higher molecular weight HA (HMWHA) promotes anti-inflammatory responses, whereas short HA oligosaccharides produce inflammatory reactions. Conclusions Intra-articular HA is a viable therapeutic option in treating knee OA and suppressing inflammatory responses. HMWHA is effective in suppressing the key macromolecules that elicit the inflammatory response by short HA oligosaccharides.

No abstract