Last December, flames engulfed Ohio's Overfield Tavern Museum. Now archaeologists get to dig beneath the floorboards. A 50 cent coin from 1817 (left) and an 1846 Liberty head one-cent coin (right) are just two of the numerous objects uncovered in a dig in Troy, Ohio. Breakthroughs, discoveries, and DIY tips sent every weekday. Out of the ashes of a devastating fire, archeologists are uncovering exciting insights into Ohio history.

We expand the second language (L2) Korean Universal Dependencies (UD) treebank with 5,454 manually annotated sentences. The annotation guidelines are also revised to better align with the UD framework. Using this enhanced treebank, we fine-tune three Korean language models and evaluate their performance on in-domain and out-of-domain L2-Korean datasets. The results show that fine-tuning significantly improves their performance across various metrics, thus highlighting the importance of using well-tailored L2 datasets for fine-tuning first-language-based, general-purpose language models for the morphosyntactic analysis of L2 data.

Shallow water equations (SWEs) are the backbone of most hydrodynamics models for flood prediction, river engineering, and many other water resources applications. The estimation of flow resistance, i.e., the Manning's roughness coefficient $n$, is crucial for ensuring model accuracy, and has been previously determined using empirical formulas or tables. To better account for temporal and spatial variability in channel roughness, inverse modeling of $n$ using observed flow data is more reliable and adaptable; however, it is challenging when using traditional SWE solvers. Based on the concept of universal differential equation (UDE), which combines physics-based differential equations with neural networks (NNs), we developed a universal SWEs (USWEs) solver, Hydrograd, for hybrid hydrodynamics modeling. It can do accurate forward simulations, support automatic differentiation (AD) for gradient-based sensitivity analysis and parameter inversion, and perform scientific machine learning for physics discovery. In this work, we first validated the accuracy of its forward modeling, then applied a real-world case to demonstrate the ability of USWEs to capture model sensitivity (gradients) and perform inverse modeling of Manning's $n$. Furthermore, we used a NN to learn a universal relationship between $n$, hydraulic parameters, and flow in a real river channel. Unlike inverse modeling using surrogate models, Hydrograd uses a two-dimensional SWEs solver as its physics backbone, which eliminates the need for data-intensive pretraining and resolves the generalization problem when applied to out-of-sample scenarios. This differentiable modeling approach, with seamless integration with NNs, provides a new pathway for solving complex inverse problems and discovering new physics in hydrodynamics.

We propose a novel architecture for graph-based dependency parsing that explicitly constructs vectors, from which both arcs and labels are scored. Our method addresses key limitations of the standard two-pipeline approach by unifying arc scoring and labeling into a single network, reducing scalability issues caused by the information bottleneck and lack of parameter sharing. Additionally, our architecture overcomes limited arc interactions with transformer layers to efficiently simulate higher-order dependencies. Experiments on PTB and UD show that our model outperforms state-of-the-art parsers in both accuracy and efficiency.

Making recommendations by exploiting the plethora of text data that accompanies products seems like an under-explored area, especially using recent advances in deep language models. I commend the authors for contributing to this research direction. The CRAE seems to work well (at least in recall at k), performing at a high level on two real-world datasets. However, I think this paper would be a better fit for a more applied conference, such as KDD or RecSys, because there is little novelty to the model's core components. I'll address each individually, in order of (my perceived) importance: 1) Robust Recurrent Networks (RRN): The proposed RRN uses distributional activations that are backpropagated through directly.

Searching dependency graphs and manipulating them can be a time consuming and challenging task to get right. We document Semgrex, a system for searching dependency graphs, and introduce Ssurgeon, a system for manipulating the output of Semgrex. The compact language used by these systems allows for easy command line or API processing of dependencies. Additionally, integration with publicly released toolkits in Java and Python allows for searching text relations and attributes over natural text.

Friction is one of the cruxes of hydrodynamic modeling; flood conditions are highly sensitive to the Friction Factors (FFs) used to calculate momentum losses. However, empirical FFs are challenging to measure because they require laboratory experiments. Flood models often rely on surrogate observations (such as land use) to estimate FFs, introducing uncertainty. This research presents a laboratory-trained Deep Neural Network (DNN), trained using flume experiments with data augmentation techniques, to measure Manning's n based on Point Cloud data. The DNN was deployed on real-world lidar Point Clouds to directly measure Manning's n under regulatory and extreme storm events, showing improved prediction capabilities in both 1D and 2D hydrodynamic models. For 1D models, the lidar values decreased differences with regulatory models for in-channel water depth when compared to land cover values. For 1D/2D coupled models, the lidar values produced better agreement with flood extents measured from airborne imagery, while better matching flood insurance claim data for Hurricane Harvey. In both 1D and 1D/2D coupled models, lidar resulted in better agreement with validation gauges. For these reasons, the lidar measurements of Manning's n were found to improve both regulatory models and forecasts for extreme storm events, while simultaneously providing a pathway to standardize the measurement of FFs. Changing FFs significantly affected fluvial and pluvial flood models, while surge flooding was generally unaffected. Downstream flow conditions were found to change the importance of FFs to fluvial models, advancing the literature of friction in flood models. This research introduces a reliable, repeatable, and readily-accessible avenue to measure high-resolution FFs based on 3D point clouds, improving flood prediction, and removing uncertainty from hydrodynamic modeling.

Texas Longhorns quarterback Arch Manning may have to wait at least one more season before he gets his chance to start for the team. With EA Sports releasing College Football 25 this summer, fans may have gotten the chance to make him their QB1 in the video game -- if he opted in. But it doesn't appear that will be the case. Manning has not opted in to have his name, image and likeness used in the game, Orangebloods.com He is reportedly "focused on playing football on the field."

Elon Musk started the week by posting testily on X about his struggles to set up a new laptop running Windows. He ended it by filing a lawsuit accusing OpenAI of recklessly developing human-level AI and handing it over to Microsoft. Musk's lawsuit is filed against OpenAI and two of its executives, CEO Sam Altman and president Greg Brockman, both of whom worked with the rocket and car entrepreneur to found the company in 2015. A large part of the case pivots around a bold and questionable technical claim: That OpenAI has developed so-called artificial general intelligence, or AGI, a term generally used to refer to machines that can comprehensively match or outsmart humans. The case claims that Altman and Brockman have breached the original "Founding Agreement" for OpenAI worked out with Musk, which it says pledged the company to develop AGI openly and "for the benefit of humanity. Musk's suit alleges that the for-profit arm of the company, established in 2019 after he parted ways with OpenAI, has instead created AGI without proper transparency and licensed it to Microsoft, which has invested billions into the company. It demands that OpenAI be forced to release its technology openly and that it be barred from using it to financially benefit Microsoft, Altman, or Brockman. "On information and belief, GPT-4 is an AGI algorithm," the lawsuit states, referring to the large language model that sits behind OpenAI's ChatGPT. It cites studies that found the system can get a passing grade on the Uniform Bar Exam and other standard tests as proof that it has surpassed some fundamental human abilities. "GPT-4 is not just capable of reasoning.

Structural probes learn a linear transformation to find how dependency trees are embedded in the hidden states of language models. This simple design may not allow for full exploitation of the structure of the encoded information. Hence, to investigate the structure of the encoded information to its full extent, we incorporate non-linear structural probes. We reformulate the design of non-linear structural probes introduced by White et al. making its design simpler yet effective. We also design a visualization framework that lets us qualitatively assess how strongly two words in a sentence are connected in the predicted dependency tree. We use this technique to understand which non-linear probe variant is good at encoding syntactical information. Additionally, we also use it to qualitatively investigate the structure of dependency trees that BERT encodes in each of its layers. We find that the radial basis function (RBF) is an effective non-linear probe for the BERT model than the linear probe.