This paper describes a warrant classification system for SemEval 2018 Task 12, that attempts to learn semantic representations of reasons, claims and warrants. The system consists of 3 stacked LSTMs: one for the reason, one for the claim, and one shared Siamese Network for the 2 candidate warrants. Our main contribution is to force the embeddings into a shared feature space using vector operations, semantic similarity classification, Siamese networks, and multi-task learning. In doing so, we learn a form of generative implication, in encoding implication interrelationships between reasons, claims, and the associated correct and incorrect warrants. We augment the limited data in the task further by utilizing WordNet synonym "fuzzing". When applied to SemEval 2018 Task 12, our system performs well on the development data, and officially ranked 8th among 21 teams.

No abstract

North Carolina's coastal area, and in particular the associated estuaries, are among the most biologically productive and environmentally sensitive regions of this State and of the nation (NC Coastal Area Management Act, 1974). However, North Carolina's coastal counties are experiencing some of the fastest population growth in the Southeastern Region of the United States. The resulting, often-conflicting, needs of the expanding human population place undue pressure on these crucial estuarine resources and threaten the very features which make the area so ecologically diverse and economically desirable. Recently enacted regulations and statutes have significantly restricted how wastewater is managed from new or expanding communities on the Carolina Coastal Plain. Prior solutions, involving use of homeowner associationmanaged factory-built wastewater treatment plants or 3-celled facultative lagoons that discharge to tidal creeks and estuaries, have produced a variety of water quality problems leading to ecological degradation of sensitive shellfish waters. In light of these issues, McKim & Creed has recently completed designs for six new satellite reclaimed water facilities ranging in size from 0.1 MGD to 0.5 MGD, all of which serve upscale waterfront communities in eastern North Carolina. Each of the designs utilizes a multiple-barrier approach and incorporates chemically-enhanced biological nutrient removal processes with membrane or cloth disk filtration followed by medium pressure UV disinfection to produce extremely high quality reclaimed water for beneficial reuse. The reclaimed water is then available for a variety of on-site uses, including maintaining water levels in amenity lakes and water features as well as for irrigation of lawns and common areas. Due to the coastal location and associated high risk of hurricane exposure, each facility was designed with dual treatment trains, full stand-by emergency power generation, and 5-day lined upset basins. In addition, special precautions were implemented to improve aesthetics and minimize the risk of odors due to the close proximity of the treatment works relative to surrounding residential properties. KEYWORDSWastewater, membrane bioreactor, reclaimed water, innovative technology. 9089 WEFTEC®.07

No abstract

A key part of the NLP ethics movement is responsible use of data, but exactly what that means or how it can be best achieved remain unclear. This position paper discusses the core legal and ethical principles for collection and sharing of textual data, and the tensions between them.We propose a potential checklist for responsible data (re-)use that could both standardise the peer review of conference submissions, as well as enable a more in-depth view of published research across the community. Our proposal aims to contribute to the development of a consistent standard for data (re-)use, embraced across NLP conferences.