Volume 1

By C. Pastoor, John J. Han, Todd C. Ream, Hyun‐Sook Kim, Anthony Sara Choate, Rachel Hayes, T. Wolff, Anita Helmbold. 2020

Subfields: Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Evaluation & Benchmarks

Citations in the corpus

Story Ending Prediction by Transferable BERT (2019, neutral): “• MNLI (Multi-Genre Natural Language Inference) is a 410k crowd-sourced multi-genre entailment classification dataset [Williams et al., 2018].”
Closed-Loop Memory GAN for Continual Learning (2018, methodology): “In other words, we performed a roulette weighting procedure such as in genetic selection [Goldberg and Deb, 1991].”
Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks (2018, background): “Stochastic gradient descent (SGD) is now one of the most dominant approaches for training deep neural networks (Goodfellow et al., 2016).”
Achieving non-discrimination in prediction (2017, unknown): “According to the generalization bound in statistical learning theory [Vapnik, 1998], ifH is finite we have P (∣∣∣P(l̃+|c+) − P̂(l̃+|c+)∣∣∣ ≥ t) ≤ 2|H|e−2n+t2 ,”
Bayesian Variational Autoencoders for Unsupervised Out-of-Distribution Detection (2019, background): “…(DNNs) have successfully tackled complex real-world problems in various domains including vision, speech and language (Schmid-huber, 2015; LeCun et al., 2015; Goodfellow et al., 2016), they still face signiﬁcant limitations that make them unﬁt for safety-critical applications (Amodei et al., 2016).”
Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systems (2019, background): “Meta-learning or learning-to-learn, which can date back to some early works [Naik and Mammone, 1992], has recently attracted extensive attentions.”
A Survey on Methods and Theories of Quantized Neural Networks (2018, background): “[Vanhoucke et al., 2011] quantized the activations to 8 bits.”
Pre-training of Graph Augmented Transformers for Medication Recommendation (2019, methodology): “Recently, language model pre-training techniques such as [ Peters et al. , 2018; Radford et al. , 2018; Devlin et al. , 2018 ] have shown to largely improve the performance on multiple NLP tasks.”
Data-Driven Market-Making via Model-Free Learning (2020, methodology): “The implication is that we cannot use any of the three main off-policy evaluation methods: direct method [Bertsekas et al., 1995; Lagoudakis and Parr, 2003; Sutton and Barto, 2018], importance sampling[Swaminathan and Joachims, 2015], and doubly robust method [Dudı́k et al.”
Interpretable Adversarial Perturbation in Input Embedding Space for Text (2018, methodology): “Other reported results [ Rei and Yannakoudakis, 2016; Kaneko et al. , 2017 ] are around the current state-of-the-art performance on this dataset.”
Self-Supervised Tuning for Few-Shot Segmentation (2020, background): “[Dong and Xing, 2018] generalizes the few-shot semantic segmentation problem from 1way (class) to N-way (classes).”
Knowledge-Guided Agent-Tactic-Aware Learning for StarCraft Micromanagement (2018, background): “In this stage, the whole game is considered as a stochastic game G [Nisan et al., 2007; Shapley, 1953], defined by G = 〈S,U, P,R, γ〉.”
A framework for automatic question generation from text using deep reinforcement learning (2018, methodology): “The generator is a sequence-to-sequence model, augmented with (i) an encoding for the potentially best pivotal answer, (ii) the copy mechanism [Gu et al., 2016] to help generate contextually important words, and (iii) the coverage mechanism [Tu et al.”
GeoMAN: Multi-level Attention Networks for Geo-sensory Time Series Prediction (2018, background): “Later, researchers developed a number of multilevel attention-based models to select the relevant features and encoder hidden states in different applications [Wang et al., 2016; Yu et al., 2017].”
Survey on evaluation methods for dialogue systems (2019, methodology): “It has been widely used to design dialogue systems and many toolkits are available such as the one from the Center for Spoken Language Understanding [Cole, 1999] or VoiceXML.”