All Research Areas
Research Areas
Year Published

527 Results

July 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 Schwenk
July 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 Ranzato
July 13, 2018

Code-Switched Named Entity Recognition with Embedding Attention

ACL CALCS Workshop

We describe our work for the CALCS 2018 shared task on named entity recognition on code-switched data.

By: Changhan Wang, Kyunghyun Cho, Douwe Kiela
July 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
July 13, 2018

A Multi-lingual Multi-task Architecture for Low-resource Sequence Labeling

Association for Computational Linguistics (ACL)

We propose a multi-lingual multi-task architecture to develop supervised models with a minimal amount of labeled data for sequence labeling.

By: Ying Lin, Shengqi Yang, Veselin Stoyanov, Heng Ji
July 12, 2018

Improved Regret Bounds for Thompson Sampling in Linear Quadratic Control

International Conference on Machine Learning (ICML)

In this paper, we study an instance of TS in the challenging setting of the infinite-horizon linear quadratic (LQ) control, which models problems with continuous state-action variables, linear dynamics, and quadratic cost.

By: Marc Abeille, Alessandro Lazaric
July 12, 2018

Improved Large-Scale Graph Learning through Ridge Spectral Sparsification

International Conference on Machine Learning (ICML)

In this paper, we combine a spectral sparsification routine with Laplacian learning.

By: Daniele Calandriello, Alessandro Lazaric, Ioannis Koutis, Michal Valko
July 12, 2018

Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning

International Conference on Machine Learning (ICML)

In this paper, we relax the optimization problem at the core of REGAL.C, we carefully analyze its properties, and we provide the first computationally efficient algorithm to solve it.

By: Ronan Fruit, Matteo Pirotta, Alessandro Lazaric, Ronald Ortner
July 11, 2018

Convergent TREE BACKUP and RETRACE with Function Approximation

International Conference on Machine Learning (ICML)

In this work, we show that the TREE BACKUP and RETRACE algorithms are unstable with linear function approximation, both in theory and in practice with specific examples.

By: Ahmed Touati, Pierre-Luc Bacon, Doina Precup, Pascal Vincent
July 11, 2018

Fitting New Speakers Based on a Short Untranscribed Sample

International Conference on Machine Learning (ICML)

We present a method that is designed to capture a new speaker from a short untranscribed audio sample.

By: Eliya Nachmani, Adam Polyak, Yaniv Taigman, Lior Wolf