On the VirtualHome framework, we get improvements of up to 9. 0% on the Longest Common Subsequence metric and 14. 7% on recall-based metrics over previous work on this framework (Puig et al., 2018).
no code implementations • 25 Sep 2021 • Ashkan Yousefpour, Igor Shilov, Alexandre Sablayrolles, Davide Testuggine, Karthik Prasad, Mani Malek, John Nguyen, Sayan Ghosh, Akash Bharadwaj, Jessica Zhao, Graham Cormode, Ilya Mironov
We introduce Opacus, a free, open-source PyTorch library for training deep learning models with differential privacy (hosted at opacus. ai).
Contextual representations learned by language models can often encode undesirable attributes, like demographic associations of the users, while being trained for an unrelated target task.
While large language models have shown exciting progress on several NLP benchmarks, evaluating their ability for complex analogical reasoning remains under-explored.
One of the critical components in Industrial Gas Turbines (IGT) is the turbine blade.
Many approaches to this problem use Reinforcement Learning (RL), which maximizes a single manually defined reward, such as BLEU.
Online social media platforms increasingly rely on Natural Language Processing (NLP) techniques to detect abusive content at scale in order to mitigate the harms it causes to their users.
In this paper we propose the IMA (Importance-based Multimodal Autoencoder) model, a scalable model that learns modality importances and robust multimodal representations through a novel cross-covariance based loss function.
Without a prior definition of the model structure, first a free-form of the equation is discovered, and then calibrated and validated against the available data.
First, PROVER generates proofs with an accuracy of 87%, while retaining or improving performance on the QA task, compared to RuleTakers (up to 6% improvement on zero-shot evaluation).
The region of interest can be specified based on the localization features of the solution, user interest, and correlation length of the random material properties.
The comparison shows that the proposed method improves the active subspace recovery and predictive accuracy, in both the deterministic and probabilistic sense, when only few model observations are available for training, at the cost of increased training time.
We present a Bayesian approach to identify optimal transformations that map model input points to low dimensional latent variables.
This helps spread awareness regarding the various causes, cures and prevention methods of cancer.
The methodology, called GE's Bayesian Hybrid Modeling (GEBHM), is a probabilistic modeling method, based on the Kennedy and O'Hagan framework, that has been continuously scaled-up and industrialized over several years.
We describe a method for Bayesian optimization by which one may incorporate data from multiple systems whose quantitative interrelationships are unknown a priori.
Multi-fidelity Gaussian process is a common approach to address the extensive computationally demanding algorithms such as optimization, calibration and uncertainty quantification.
Multilingual individuals code switch between languages as a part of a complex communication process.
In this paper, we develop a content-cum-user based deep learning framework DeepTagRec to recommend appropriate question tags on Stack Overflow.
Because the readers lack the time to go over an entire article, most of the comments are relevant to only particular sections of an article.
Human verbal communication includes affective messages which are conveyed through use of emotionally colored words.
Experiments on a well-established real-life speech dataset (IEMOCAP) show that the learnt representations are comparable to state of the art feature extractors (such as voice quality features and MFCCs) and are competitive with state-of-the-art approaches at emotion and dimensional affect recognition.