More Like this

1. Transferring Legal Natural Language Inference Model from a US State to Another: What Makes It So Hard?

   https://doi.org/10.18653/v1/2023.nllp-1.21  

   Kwak, Alice; Forte, Gaetano; Bambauer, Derek; Surdeanu, Mihai (January 2023, Proceedings of the Natural Legal Language Processing Workshop 2023)

   This study investigates whether a legal natural language inference (NLI) model trained on the data from one US state can be transferred to another state. We fine-tuned a pre-trained model on the task of evaluating the validity of legal will statements, once with the dataset containing the Tennessee wills and once with the dataset containing the Idaho wills. Each model’s performance on the in-domain setting and the out-of-domain setting are compared to see if the models can across the states. We found that the model trained on one US state can be mostly transferred to another state. However, it is clear that the model’s performance drops in the out-of-domain setting. The F1 scores of the Tennessee model and the Idaho model are 96.41 and 92.03 when predicting the data from the same state, but they drop to 66.32 and 81.60 when predicting the data from another state. Subsequent error analysis revealed that there are two major sources of errors. First, the model fails to recognize equivalent laws across states when there are stylistic differences between laws. Second, difference in statutory section numbering system between the states makes it difficult for the model to locate laws relevant to the cases being predicted on. This analysis provides insights on how the future NLI system can be improved. Also, our findings offer empirical support to legal experts advocating the standardization of legal documents. 

   more » « less
2. Collaborative Talk Across Two Pair-Programming Configurations

   Zacharia, Z; Boulden, D; Vandenberg, J; Tsan, J; Lynch, C; Wiebe, E; Boyer, K (June 2019, A Wide Lens: Combining Embodied, Enactive, Extended, and Embedded Learning in Collaborative Settings, 13th International Conference on Computer Supported Collaborative Learning (CSCL) 2019)

   Abstract: Given that pair programming has proved to be an effective pedagogical approach for teaching programming skills, it is now important to explore alternative collaborative configurations. One popular configuration is where dyads collaborate by sharing a single computer sitting side-by-side. However, prior research points to potential challenges for elementary students when sharing a single computer when collaborating. This prompted us to explore another configuration where dyads sit side by side but collaborate on a shared virtual platform with individual computers. We compared the discourse of students’ collaboration under these two settings. Results show that although there are no significant differences in the amount of collaborative talk between the two configurations, there is qualitative evidence of how differing affordances of two configurations shape collaborative elementary students’ practices. 

   more » « less
3. Mössbauer analysis of compositional tuning of magnetic exchange interactions in high entropy alloys

   https://doi.org/10.1063/1.5079744  

   Perrin, Alice; Sorescu, Monica; Ravi, Vishal; Laughlin, David_E; McHenry, Michael_E (March 2019, AIP Advances)

   We measured the change in the average hyperfine field strength of several high entropy alloys in relation to small compositional deviations from the equiatomic alloy, FeCoNiCuMn. Mössbauer spectra of four psuedo-binary systems, in which Mn content is increased and another element was decreased in equal measure, reveal several discrete peaks in the hyperfine field distribution that show evidence of the discrete exchange interactions between magnetic elements in the alloy. A simple linear regression modelling the perturbation of the average hyperfine field when the composition is altered calculates the contribution of each atom to the overall average. The average hyperfine field is linear with Tc, so these values allow us to estimate Tc for alloys with more complex compositional variation within the window of linearity (<24% Mn based on other alloys). The results were confirmed experimentally by calculating Tc of two new alloys, Fe19Co20Ni19Cu19Mn23 and Fe19Co20Ni19Cu20Mn22. 

   more » « less
4. Revealed strength of preference: Inference from response times

   Konovalov, Arkady; Krajbich, Ian. (July 2019, Judgment and decision making)

   null (Ed.)

   Revealed preference is the dominant approach for inferring preferences, but it is limited in that it relies solely on discrete choice data. When a person chooses one alternative over another, we cannot infer the strength of their preference or predict how likely they will be to make the same choice again. However, the choice process also produces response times (RTs), which are continuous and easily observable. It has been shown that RTs often decrease with strength-of-preference. This is a basic property of sequential sampling models such as the drift diffusion model. What remains unclear is whether this relationship is sufficiently strong, relative to the other factors that affect RTs, to allow us to reliably infer strength-of-preference across individuals. Using several experiments, we show that even when every subject chooses the same alternative, we can still rank them based on their RTs and predict their behavior on other choice problems. We can also use RTs to predict whether a subject will repeat or reverse their decision when presented with the same choice problem a second time. Finally, as a proof-of-concept, we demonstrate that it is also possible to recover individual preference parameters from RTs alone. These results demonstrate that it is indeed possible to use RTs to infer preferences. 

   more » « less
5. Bridging adaptive management and reinforcement learning for more robust decisions

   https://doi.org/10.1098/rstb.2022.0195  

   Chapman, Melissa; Xu, Lily; Lapeyrolerie, Marcus; Boettiger, Carl (July 2023, Philosophical Transactions of the Royal Society B: Biological Sciences)

   From out-competing grandmasters in chess to informing high-stakes healthcare decisions, emerging methods from artificial intelligence are increasingly capable of making complex and strategic decisions in diverse, high-dimensional and uncertain situations. But can these methods help us devise robust strategies for managing environmental systems under great uncertainty? Here we explore how reinforcement learning (RL), a subfield of artificial intelligence, approaches decision problems through a lens similar to adaptive environmental management: learning through experience to gradually improve decisions with updated knowledge. We review where RL holds promise for improving evidence-informed adaptive management decisions even when classical optimization methods are intractable and discuss technical and social issues that arise when applying RL to adaptive management problems in the environmental domain. Our synthesis suggests that environmental management and computer science can learn from one another about the practices, promises and perils of experience-based decision-making. This article is part of the theme issue ‘Detecting and attributing the causes of biodiversity change: needs, gaps and solutions’. 

   more » « less