Publications

BanditSum: Extractive Summarization as a Contextual Bandit
Yue Dong
Yikang Shen
Eric Crawford
Herke van Hoof
Jackie Cheung
In this work, we propose a novel method for training neural networks to perform single-document extractive summarization without heuristical… (voir plus)ly-generated extractive labels. We call our approach BanditSum as it treats extractive summarization as a contextual bandit (CB) problem, where the model receives a document to summarize (the context), and chooses a sequence of sentences to include in the summary (the action). A policy gradient reinforcement learning algorithm is used to train the model to select sequences of sentences that maximize ROUGE score. We perform a series of experiments demonstrating that BanditSum is able to achieve ROUGE scores that are better than or comparable to the state-of-the-art for extractive summarization, and converges using significantly fewer update steps than competing approaches. In addition, we show empirically that BanditSum performs significantly better than competing approaches when good summary sentences appear late in the source document.
2018-10-01
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (publié)
doi.org
arxiv.org
A Knowledge Hunting Framework for Common Sense Reasoning
Ali Emami
Noelia De La Cruz
Adam Trischler
Kaheer Suleman
Jackie Cheung
We introduce an automatic system that achieves state-of-the-art results on the Winograd Schema Challenge (WSC), a common sense reasoning tas… (voir plus)k that requires diverse, complex forms of inference and knowledge. Our method uses a knowledge hunting module to gather text from the web, which serves as evidence for candidate problem resolutions. Given an input problem, our system generates relevant queries to send to a search engine, then extracts and classifies knowledge from the returned results and weighs them to make a resolution. Our approach improves F1 performance on the full WSC by 0.21 over the previous best and represents the first system to exceed 0.5 F1. We further demonstrate that the approach is competitive on the Choice of Plausible Alternatives (COPA) task, which suggests that it is generally applicable.
2018-10-01
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (publié)
doi.org
arxiv.org
Combining adaptive algorithms and hypergradient method: a performance and robustness study
Akram Erraqabi
Nicolas Le Roux
2018-09-27
(publié)
www.semanticscholar.org
Exploring Uncertainty Measures in Deep Networks for Multiple Sclerosis Lesion Detection and Segmentation
Tanya Nair
Doina Precup
Douglas Arnold
Tal Arbel
2018-09-26
Medical Image Computing and Computer Assisted Intervention – MICCAI 2018 (publié)
doi.org
arxiv.org
CNN Prediction of Future Disease Activity for Multiple Sclerosis Patients from Baseline MRI and Lesion Labels
Nazanin Mohammadi Sepahvand
Tal Hassner
Douglas Arnold
Tal Arbel
2018-09-16
BrainLes@MICCAI (publié)
doi.org
3D U-Net for Brain Tumour Segmentation
Raghav Mehta
Tal Arbel
2018-09-16
BrainLes@MICCAI (publié)
doi.org
How to Exploit Weaknesses in Biomedical Challenge Design and Organization
Annika Reinke
Matthias Eisenmann
Sinan Onogur
Marko Stankovic
Patrick Scholz
Peter M. Full
Hrvoje Bogunovic
Bennett Landman
Oskar Maier
Bjoern Menze
Gregory C. Sharp
Korsuk Sirinukunwattana
Stefanie Speidel
F. V. D. Sommen
Guoyan Zheng
Henning Müller
Michal Kozubek
Tal Arbel
Andrew P. Bradley
Pierre Jannin … (voir 2 de plus)
Annette Kopp-Schneider
Lena Maier-Hein
2018-09-13
Medical Image Computing and Computer Assisted Intervention – MICCAI 2018 (publié)
doi.org
RS-Net: Regression-Segmentation 3D CNN for Synthesis of Full Resolution Missing Brain MRI in the Presence of Tumours
Raghav Mehta
Tal Arbel
2018-09-12
Simulation and Synthesis in Medical Imaging (publié)
doi.org
arxiv.org
Social-Affiliation Networks: Patterns and the SOAR Model
Dhivya Eswaran
Reihaneh Rabbany
Artur Dubrawski
Christos Faloutsos
2018-09-10
ECML/PKDD (publié)
doi.org
Structured deep Fisher pruning for efficient facial trait classification
Qing Tian
Tal Arbel
James J. Clark
2018-09-01
Image and Vision Computing (publié)
doi.org
Domain Knowledge Discovery Guided by Software Trace Links
Jin Guo
Natawut Monaikul
Jane Cleland-Huang
Software-intensive projects are specified and modeled using domain terminology. Knowledge of the domain terminology is necessary for perform… (voir plus)ing many Software Engineering tasks such as impact analysis, compliance verification, and safety certification. However, discovering domain terminology and reasoning about their interrelationships for highly technical software and system engineering domains is a complex task which requires significant domain expertise and human effort. In this paper, we present a novel approach for leveraging trace links in software intensive systems to guide the process of mining facts that contain domain knowledge. The trace links which drive our mining process, define relationships between artifacts such as regulations and requirements and enable a guided search through high-yield combinations of domain terms. Our proof-of-concept evaluation shows that our approach aids in the discovery of domain facts even in highly complex technical domains. These domain facts can provide support for a variety of Software Engineering activities. As a use case, we demonstrate how the mined facts can facilitate the task of project Q&A.
2018-08-21
2018 5th International Workshop on Artificial Intelligence for Requirements Engineering (AIRE) (publié)
doi.org
arxiv.org
The Deconfounded Recommender: A Causal Inference Approach to Recommendation
Yixin Wang
Dawen Liang
Laurent Charlin
David Blei
The goal of a recommender system is to show its users items that they will like. In forming its prediction, the recommender system tries to … (voir plus)answer: "what would the rating be if we 'forced' the user to watch the movie?" This is a question about an intervention in the world, a causal question, and so traditional recommender systems are doing causal inference from observational data. This paper develops a causal inference approach to recommendation. Traditional recommenders are likely biased by unobserved confounders, variables that affect both the "treatment assignments" (which movies the users watch) and the "outcomes" (how they rate them). We develop the deconfounded recommender, a strategy to leverage classical recommendation models for causal predictions. The deconfounded recommender uses Poisson factorization on which movies users watched to infer latent confounders in the data; it then augments common recommendation models to correct for potential confounding bias. The deconfounded recommender improves recommendation and it enjoys stable performance against interventions on test sets.
2018-08-20
ArXiv (prépublication)
arxiv.org
arxiv.org