Hrishikesh Joshi | Searcharxiv

arXiv2023

Model adaptation for hyperbolic balance laws

In this work, we devise a model adaptation strategy for a class of model hierarchies consisting of two levels of model complexity. In particular, the fine model consists of a system of hyperbolic balance laws with stiff reaction terms and the coarse model consists of a system of hyperbolic conservation laws. We employ the relative entropy stability framework to obtain an a posteriori modeling error estimator. The efficiency of the model adaptation strategy is demonstrated by conducting simulations for chemically reacting fluid mixtures in one space dimension.

math.NA↗

arXiv2016

Semi-supervised Question Retrieval with Gated Convolutions

Question answering forums are rapidly growing in size with no effective automated ability to refer to and reuse answers already available for previous posted questions. In this paper, we develop a methodology for finding semantically related questions. The task is difficult since 1) key pieces of information are often buried in extraneous details in the question body and 2) available annotations on similar questions are scarce and fragmented. We design a recurrent and convolutional model (gated convolution) to effectively map questions to their semantic representations. The models are pre-trained within an encoder-decoder framework (from body to title) on the basis of the entire raw corpus, and fine-tuned discriminatively from limited annotations. Our evaluation demonstrates that our model yields substantial gains over a standard IR baseline and various neural network architectures (including CNNs, LSTMs and GRUs).

cs.CL↗