MaskEval: Weighted MLM-Based Evaluation for Text Summarization and Simplification
Yu Lu Liu
Rachel Bawden
Thomas Scaliom
Benoı̂t Sagot
AB0393 SURVIVAL ON JANUS KINASE INHIBITORS VERSUS OTHER ADVANCED THERAPIES IN RHEUMATOID ARTHRITIS
N. Bakhtiar
Leanne Gray
S. Bilgrami
Lesley Lesley Ottewell
Frank Wood
Mohsin Bukhari
ASHA: Assistive Teleoperation via Human-in-the-Loop Reinforcement Learning
Sean Chen
Jensen Gao
Siddharth Reddy
Anca Dragan
Sergey Levine
Building assistive interfaces for controlling robots through arbitrary, high-dimensional, noisy inputs (e.g., webcam images of eye gaze) can… (voir plus) be challenging, especially when it involves inferring the user's desired action in the absence of a natural ‘default’ interface. Reinforcement learning from online user feedback on the system's performance presents a natural solution to this problem, and enables the interface to adapt to individual users. However, this approach tends to require a large amount of human-in-the-loop training data, especially when feedback is sparse. We propose a hierarchical solution that learns efficiently from sparse user feedback: we use offline pre-training to acquire a latent embedding space of useful, high-level robot behaviors, which, in turn, enables the system to focus on using online user feedback to learn a mapping from user inputs to desired high-level behaviors. The key insight is that access to a pre-trained policy enables the system to learn more from sparse rewards than a naïve RL algorithm: using the pre-trained policy, the system can make use of successful task executions to relabel, in hindsight, what the user actually meant to do during unsuccessful executions. We evaluate our method primarily through a user study with 12 participants who perform tasks in three simulated robotic manipulation domains using a webcam and their eye gaze: flipping light switches, opening a shelf door to reach objects inside, and rotating a valve. The results show that our method successfully learns to map 128-dimensional gaze features to 7-dimensional joint torques from sparse rewards in under 10 minutes of online training, and seamlessly helps users who employ different gaze strategies, while adapting to distributional shift in webcam inputs, tasks, and environments
Diffusion Kurtosis Imaging of the neonatal Spinal Cord: design and application of the first processing pipeline implemented in Spinal Cord Toolbox
Rosella Trò
Monica Roascio
Domenico Tortora
Mariasavina Severino
Andrea Rossi
Marco Massimo Fato
Gabriele Arnulfo
Diffusion Kurtosis Imaging (DKI) has undisputed advantages over more classical diffusion Magnetic Resonance Imaging (dMRI), as witnessed by … (voir plus)a fast-increasing number of clinical applications and software packages widely adopted in brain imaging domain. Despite its power in probing tissue microstructure compared to conventional MRI, DKI is still largely underutilized in Spinal Cord (SC) imaging because of its inherently demanding technological requirements. If state-of-the-art hardware advancements have recently allowed to make great strides in applying this emerging method to adult and child SC, the same does not apply to neonatal setting. Indeed, amplified technical issues related to SC district in this age range have made this field still unexplored. However, results arising from recent application of DKI to adult and child SC are promising enough to suggest how informative this technique would be in investigating newborns, too. Due to its extreme sensitivity to non-gaussian diffusion, DKI proves particularly suitable for detecting complex, subtle, fast microstructural changes occurring in this area at this early and critical stage of development, and not identifiable with only DTI. Given the multiplicity of congenital anomalies of the spinal canal, their crucial effect on later developmental outcome, and the close interconnection between SC region and the above brain, managing to apply such a method to neonatal cohort becomes of utmost importance. In this work, we illustrate the first semi-automated pipeline for handling with DKI data of neonatal SC, from acquisition setting to estimation of diffusion (DTI & DKI) measures, through accurate adjustment of processing algorithms customized for adult SC. Each processing step of this pipeline, built on Spinal Cord Toolbox (SCT) software, has undergone Quality Control check by supervision of an expert pediatric neuroradiologist, and the overall procedure has preliminarily been tested in a pilot clinical case study. Results of this application agree with findings achieved in a corresponding adult survey, thus confirming validity of adopted pipeline and diagnostic value of DKI in pediatrics. This novel tool hence paves the wave for extending its application also to other promising advanced dMRI models, such as Neurite Orientation Dispersion and Density Imaging (NODDI), and to a wider range of potential clinical applications concerning neonatal period.
Improving Source Separation by Explicitly Modeling Dependencies between Sources
Ethan Manilow
Curtis Hawthorne
Bryan Pardo
Jesse Engel
We propose a new method for training a supervised source separation system that aims to learn the interdependent relationships between all c… (voir plus)ombinations of sources in a mixture. Rather than independently estimating each source from a mix, we reframe the source separation problem as an Orderless Neural Autoregressive Density Estimator (NADE), and estimate each source from both the mix and a random subset of the other sources. We adapt a standard source separation architecture, Demucs, with additional inputs for each individual source, in addition to the input mixture. We randomly mask these input sources during training so that the network learns the conditional dependencies between the sources. By pairing this training method with a blocked Gibbs sampling procedure at inference time, we demonstrate that the network can iteratively improve its separation performance by conditioning a source estimate on its earlier source estimates. Experiments on two source separation datasets show that training a Demucs model with an Orderless NADE approach and using Gibbs sampling (up to 512 steps) at inference time strongly outperforms a Demucs baseline that uses a standard regression loss and direct (one step) estimation of sources.
Real-M: Towards Speech Separation on Real Mixtures
Samuele Cornell
François Grondin
In recent years, deep learning based source separation has achieved impressive results. Most studies, however, still evaluate separation mod… (voir plus)els on synthetic datasets, while the performance of state-of-the-art techniques on in-the-wild speech data remains an open question. This paper contributes to fill this gap in two ways. First, we release the REAL-M dataset, a crowd-sourced corpus of real-life mixtures. Secondly, we address the problem of performance evaluation of real-life mixtures, where the ground truth is not available. We bypass this issue by carefully designing a blind Scale-Invariant Signal-to-Noise Ratio (SI-SNR) neural estimator. Through a user study, we show that our estimator reliably evaluates the separation performance on real mixtures, i.e. we observe that the performance predictions of the SI-SNR estimator correlate well with human opinions. Moreover, when evaluating popular speech separation models, we observe that the performance trends predicted by our estimator on the REAL-M dataset closely follow the performance trends achieved on synthetic benchmarks.
A Remedy For Distributional Shifts Through Expected Domain Translation
Jean-Christophe Gagnon-Audet
Soroosh Shahtalebi
Frank Rudzicz
Machine learning models often fail to generalize to unseen domains due to the distributional shifts. A family of such shifts, “correlation… (voir plus) shifts,” is caused by spurious correlations in the data. It is studied under the overarching topic of “domain generalization.” In this work, we employ multi-modal translation networks to tackle the correlation shifts that appear when data is sampled out-of-distribution. Learning a generative model from training domains enables us to translate each training sample under the special characteristics of other possible domains. We show that by training a predictor solely on the generated samples, the spurious correlations in training domains average out, and the invariant features corresponding to true correlations emerge. Our proposed technique, Expected Domain Translation (EDT), is benchmarked on the Colored MNIST dataset and drastically improves the state-of-the-art classification accuracy by 38% with train-domain validation model selection.
Roboethics as a Design Challenge: Lessons Learned from the Roboethics to Design and Development Competition
Jimin Rhim
Cheng Lin
Alexander Werner
Brandon DeHart
Vivian Qiang
Shalaleh Rismani
How do we make concrete progress towards de-signing robots that can navigate ethically sensitive contexts? Almost two decades after the word… (voir plus) ‘roboethics’ was coined, translating interdisciplinary roboethics discussions into techni-cal design still remains a daunting task. This paper describes our first attempt at addressing these challenges through a roboethics-themed design competition. The design competition setting allowed us to (a) formulate ethical considerations as an engineering design task that anyone with basic programming skills can tackle; and (b) develop a prototype evaluation scheme that incorporates diverse normative perspectives of multiple stakeholders. The initial implementation of the competition was held online at the RO-MAN 2021 conference. The competition task involved programming a simulated mobile robot (TIAGo) that delivers items for individuals in the home environment, where many of these tasks involve ethically sensitive con-texts (e.g., an underage family member asks for an alcoholic drink). This paper outlines our experiences implementing the competition and the lessons we learned. We highlight design competitions as a promising mechanism to enable a new wave of roboethics research equipped with technical design solutions.
Better Modeling the Programming World with Code Concept Graphs-augmented Multi-modal Learning
Martin Weyssow
Houari Sahraoui
The progress made in code modeling has been tremendous in recent years thanks to the design of natural language processing learning approach… (voir plus)es based on state-of-the-art model architectures. Nevertheless, we believe that the current state-of-the-art does not focus enough on the full potential that data may bring to a learning process in software engineering. Our vision articulates on the idea of leveraging multi-modal learning approaches to modeling the programming world. In this paper, we investigate one of the underlying idea of our vision whose objective based on concept graphs of identifiers aims at leveraging high-level relationships between domain concepts manipulated through particular language constructs. In particular, we propose to enhance an existing pretrained language model of code by joint-learning it with a graph neural network based on our concept graphs. We conducted a preliminary evaluation that shows gain of effectiveness of the models for code search using a simple joint-learning method and prompts us to further investigate our research vision.
Coordinating Policies Among Multiple Agents via an Intelligent Communication Channel
Dianbo Liu
Vedant Shah
Oussama Boussif
Cristian Meo
Anirudh Goyal
Tianmin Shu
Michael Curtis Mozer
Nicolas Heess
In Multi-Agent Reinforcement Learning (MARL), specialized channels are often introduced that allow agents to communicate directly with one a… (voir plus)nother. In this paper, we propose an alternative approach whereby agents communicate through an intelligent facilitator that learns to sift through and interpret signals provided by all agents to improve the agents’ collective performance. To ensure that this facilitator does not become a centralized controller, agents are incentivized to reduce their dependence on the messages it conveys, and the messages can only influence the selection of a policy from a fixed set, not instantaneous actions given the policy. We demonstrate the strength of this architecture over existing baselines on several cooperative MARL environments.
Bayesian Structure Learning with Generative Flow Networks
Tristan Deleu
António Góis
Chris Emezue
Mansi Rankawat
Stefan Bauer
In Bayesian structure learning, we are interested in inferring a distribution over the directed acyclic graph (DAG) structure of Bayesian ne… (voir plus)tworks, from data. Defining such a distribution is very challenging, due to the combinatorially large sample space, and approximations based on MCMC are often required. Recently, a novel class of probabilistic models, called Generative Flow Networks (GFlowNets), have been introduced as a general framework for generative modeling of discrete and composite objects, such as graphs. In this work, we propose to use a GFlowNet as an alternative to MCMC for approximating the posterior distribution over the structure of Bayesian networks, given a dataset of observations. Generating a sample DAG from this approximate distribution is viewed as a sequential decision problem, where the graph is constructed one edge at a time, based on learned transition probabilities. Through evaluation on both simulated and real data, we show that our approach, called DAG-GFlowNet, provides an accurate approximation of the posterior over DAGs, and it compares favorably against other methods based on MCMC or variational inference.
Hardware Architecture for Guessing Random Additive Noise Decoding Markov Order (GRAND-MO)
Syed Mohsin Abbas
Marwan Jalaleddine