Provided with the interpretable concepts and knowledge encoded in a pre-trained neural model, we investigate whether the tagged concepts can be applied to a broader class of applications.
The objective of non-parallel text style transfer, or controllable text generation, is to alter specific attributes (e. g. sentiment, mood, tense, politeness, etc) of a given text while preserving its remaining attributes and content.
An acrostic is a form of writing that the first token of each line (or other recurring features in the text) forms a meaningful sequence.
Human beings are creatures of habit.
Unsupervised document representation learning is an important task providing pre-trained features for NLP applications.
Adversarial loss in a conditional generative adversarial network (GAN) is not designed to directly optimize evaluation metrics of a target task, and thus, may not always guide the generator in a GAN to generate data with improved metric scores.
Ranked #9 on Speech Enhancement on DEMAND
State-of-the-art deep neural networks (DNNs) typically have tens of millions of parameters, which might not fit into the upper levels of the memory hierarchy, thus increasing the inference time and energy consumption significantly, and prohibiting their use on edge devices such as mobile phones.
If artificially intelligent (AI) agents make decisions on behalf of human beings, we would hope they can also follow established regulations while interacting with humans or other AI agents.
We consider a generalization of mixed regression where the response is an additive combination of several mixture components.
Attribute-aware CF models aims at rating prediction given not only the historical rating from users to items, but also the information associated with users (e. g. age), items (e. g. price), or even ratings (e. g. rating time).
Lexicon relation extraction given distributional representation of words is an important topic in NLP.
Inspired by Memory Network proposed for solving the question-answering task, we propose a deep learning based model named Memory Time-series network (MTNet) for time series forecasting.
This work provides a thorough study on how reward scaling can affect performance of deep reinforcement learning agents.
This paper proposes a privacy-preserving distributed recommendation framework, Secure Distributed Collaborative Filtering (SDCF), to preserve the privacy of value, model and existence altogether.
The latent feature model (LFM), proposed in (Griffiths \& Ghahramani, 2005), but possibly with earlier origins, is a generalization of a mixture model, where each instance is generated not from a single latent class but from a combination of latent features.
In past few years, several techniques have been proposed for training of linear Support Vector Machine (SVM) in limited-memory setting, where a dual block-coordinate descent (dual-BCD) method was used to balance cost spent on I/O and computation.
In this paper, we propose a Sparse Random Feature algorithm, which learns a sparse non-linear predictor by minimizing an $\ell_1$-regularized objective function over the Hilbert Space induced from kernel function.