224 Results
September 8, 2018
DeepWrinkles: Accurate and Realistic Clothing Modeling
European Conference on Computer Vision (ECCV)
We present a novel method to generate accurate and realistic clothing deformation from real data capture. Previous methods for realistic cloth modeling mainly rely on intensive computation of physics-based simulation (with numerous heuristic parameters), while models reconstructed from visual observations typically suffer from lack of geometric details.
By: Zorah Lähner, Daniel Cremers, Tony Tung
AR/VR 
Computer Vision 
Machine Learning August 19, 2018
A real-time framework for detecting efficiency regressions in a globally distributed codebase
Knowledge Discovery in Databases (KDD)
This paper describes the end-to-end regression detection system designed and used at Facebook. The main detection algorithm is based on sequential statistics supplemented by signal processing transformations, and the performance of the algorithm was assessed with a mixture of online and offline tests across different use cases.
By: Martin Valdez-Vivas, Caner Gocmen, Andrii Korotkov, Ethan Fang, Kapil Goenka, Sherry Chen
Data Science 
Systems & Networking August 13, 2018
Unsupervised Generation of Free-Form and Parameterized Avatars
TPAMI: SI: ICCV
We study two problems involving the task of mapping images between different domains. The first problem, transfers an image in one domain to an analog image in another domain. The second problem, extends the previous one by mapping an input image to a tied pair, consisting of a vector of parameters and an image that is created using a graphical engine from this vector of parameters.
By: Adam Polyak, Yaniv Taigman, Lior WolfJuly 20, 2018
Controllable Abstractive Summarization
ACL NMT Workshop
We present a neural summarization model with a simple but effective mechanism to enable users to specify these high level attributes in order to control the shape of the final summaries to better suit their needs.
By: Angela Fan, David Grangier, Michael Auli
Facebook AI Research July 18, 2018
What you can cram into a single $&!#* vector: Probing sentence embeddings for linguistic properties
Association for Computational Linguistics (ACL)
We introduce here 10 probing tasks designed to capture simple linguistic features of sentences, and we use them to study embeddings generated by three different encoders trained in eight distinct ways, uncovering intriguing properties of both encoders and training methods.
By: Alexis Conneau, Germán Kruszewski, Guillaume Lample, LoÏc Barrault, Marco Baroni
Natural Language Processing & Speech July 15, 2018
Personalizing Dialogue Agents: I have a dog, do you have pets too?
Association for Computational Linguistics (ACL)
Chit-chat models are known to have several problems: they lack specificity, do not display a consistent personality and are often not very captivating. In this work we present the task of making chit-chat more engaging by conditioning on profile information.
By: Saizheng Zhang, Emily Dinan, Jack Urbanek, Arthur Szlam, Douwe Kiela, Jason WestonJuly 15, 2018
Hierarchical Neural Story Generation
Association for Computational Linguistics (ACL)
We explore story generation: creative systems that can build coherent and fluent passages of text about a topic. We collect a large dataset of 300K human-written stories paired with writing prompts from an online forum.
By: Angela Fan, Michael Lewis, Yann DauphinJuly 15, 2018
Filtering and Mining Parallel Data in a Joint Multilingual Space
Association for Computational Linguistics (ACL)
We learn a joint multilingual sentence embedding and use the distance between sentences in different languages to filter noisy parallel data and to mine for parallel data in large news collections.
By: Holger SchwenkJuly 13, 2018
Analyzing Uncertainty in Neural Machine Translation
International Conference on Machine Learning (ICML)
Our study relates some of these issues to the inherent uncertainty of the task, due to the existence of multiple valid translations for a single source sentence, and to the extrinsic uncertainty caused by noisy training data.
By: Myle Ott, Michael Auli, David Grangier, Marc'Aurelio RanzatoJuly 13, 2018
Multilingual seq2seq training with similarity loss for cross-lingual document classification
RepL4NLP Workshop at ACL
In this paper we continue the line of work where neural machine translation training is used to produce joint cross-lingual fixed-dimensional sentence embeddings.
By: Katherin Yu, Haoran Li, Barlas Oguz