arXiv subjects

Nikhil Gupta

Publications and source records attributed to Nikhil Gupta.

21 records · Page 2Linked to original sources

arXiv2019

Disentangling Language and Knowledge in Task-Oriented Dialogs

The Knowledge Base (KB) used for real-world applications, such as booking a movie or restaurant reservation, keeps changing over time. End-to-end neural networks trained for these task-oriented dialogs are expected to be immune to any changes in the KB. However, existing approaches breakdown when asked to handle such changes. We propose an encoder-decoder architecture (BoSsNet) with a novel Bag-of-Sequences (BoSs) memory, which facilitates the disentangled learning of the response's language model and its knowledge incorporation. Consequently, the KB can be modified with new knowledge without a drop in interpretability. We find that BoSsNet outperforms state-of-the-art models, with considerable improvements (> 10\%) on bAbI OOV test sets and other human-human datasets. We also systematically modify existing datasets to measure disentanglement and show BoSsNet to be robust to KB modifications.

cs.LG↗

arXiv2017

LookOut on Time-Evolving Graphs: Succinctly Explaining Anomalies from Any Detector

Why is a given node in a time-evolving graph ($t$-graph) marked as an anomaly by an off-the-shelf detection algorithm? Is it because of the number of its outgoing or incoming edges, or their timings? How can we best convince a human analyst that the node is anomalous? Our work aims to provide succinct, interpretable, and simple explanations of anomalous behavior in $t$-graphs (communications, IP-IP interactions, etc.) while respecting the limited attention of human analysts. Specifically, we extract key features from such graphs, and propose to output a few pair (scatter) plots from this feature space which "best" explain known anomalies. To this end, our work has four main contributions: (a) problem formulation: we introduce an "analyst-friendly" problem formulation for explaining anomalies via pair plots, (b) explanation algorithm: we propose a plot-selection objective and the LookOut algorithm to approximate it with optimality guarantees, (c) generality: our explanation algorithm is both domain- and detector-agnostic, and (d) scalability: we show that LookOut scales linearly on the number of edges of the input graph. Our experiments show that LookOut performs near-ideally in terms of maximizing explanation objective on several real datasets including Enron e-mail and DBLP coauthorship. Furthermore, LookOut produces fast, visually interpretable and intuitive results in explaining "ground-truth" anomalies from Enron, DBLP and LBNL (computer network) data.

cs.SI↗

arXiv2015

Deformation of an elastic body in low Reynolds number transport: Relevance to biofilm deformation and streamer formation

In this paper, we obtain analytical results for shear stress distributions inside an elastic body placed in a low Reynolds number transport. The problem definition is inspired by a recent experimental study (Valiei et al., Lab Chip, 2012, 12, 5133-5137) that reports the flow-triggered deformation of bacterial biofilms, formed on cylindrical rigid microposts, into long filamentous structures known as streamers. In our analysis, we consider an elastic body of finite thickness (forming a rim) placed over a rigid cylinder, i.e., we mimic the biofilm structure in the experiment. We consider Oseen flow solution to describe the low Reynolds transport past this cylindrical elastic structure. The stress and strain distributions inside the elastic structure are found to be functions of position, Poisson ratio, initial thickness of the elastic rim and the ratio of the flow-driven shear stress to the shear modulus of the elastic body. More importantly, these analyses, which can be deemed as one of the first formal analyses to understand the fluid-structure-interaction issues associated with the biofilm streamer formation, help us interpret several qualitative aspects associated with the streamer formation reported in different experiments.

physics.flu-dyn↗