All Research Areas
Research Areas
Year Published

129 Results

October 8, 2017

Living a Discrete Life in a Continuous World: Reference in Cross-Modal Entity Tracking

Proceedings of IWCS (12th International Conference on Computational Semantics)

This paper (a) introduces a concrete referential task to test both aspects, called cross-modal entity tracking; (b) proposes a neural network architecture that uses external memory to build an entity library inspired in the DRSs of DRT, with a mechanism to dynamically introduce new referents or add information to referents that are already in the library.

By: Gemma Boleda, Sebastian Pado', Nghia The Pham, Marco Baroni
October 5, 2017

STARDATA: a StarCraft AI Research Dataset

Association for the Advancement of Artificial Intelligence Digital Entertainment Conference

We release a dataset of 65646 StarCraft replays that contains 1535 million frames and 496 million player actions. We provide full game state data along with the original replays that can be viewed in StarCraft.

By: Zeming Lin, Jonas Gehring, Vasil Khalidov, Gabriel Synnaeve
September 7, 2017

Natural Language Does Not Emerge ‘Naturally’ in Multi-Agent Dialog

Conference on Empirical Methods in Natural Language Processing (EMNLP)

In this paper, using a Task & Talk reference game between two agents as a testbed, we present a sequence of ‘negative’ results culminating in a ‘positive’ one – showing that while most agent-invented languages are effective (i.e. achieve near-perfect task rewards), they are decidedly not interpretable or compositional.

By: Satwik Kottur, José M.F. Moura, Stefan Lee, Dhruv Batra
September 7, 2017

Supervised Learning of Universal Sentence Representations from Natural Language Inference Data

Conference on Empirical Methods on Natural Language Processing (EMNLP)

In this paper, we show how universal sentence representations trained using the supervised data of the Stanford Natural Language Inference datasets can consistently outperform unsupervised methods like SkipThought vectors (Kiros et al., 2015) on a wide range of transfer tasks.

By: Alexis Conneau, Douwe Kiela, Holger Schwenk, LoÏc Barrault, Antoine Bordes
September 7, 2017

Grasping the Finer Point: A Supervised Similarity Network for Metaphor Detection

The Conference on Empirical Methods in Natural Language Processing (EMNLP)

In this paper, we present the first deep learning architecture designed to capture metaphorical composition. Our results demonstrate that it outperforms the existing approaches in the metaphor identification task.

By: Marek Rei, Luana Bulat, Douwe Kiela, Ekaterina Shutova
August 6, 2017

Unsupervised Learning by Predicting Noise

International Conference on Machine Learning (ICML)

Convolutional neural networks provide visual features that perform well in many computer vision applications. However, training these networks requires large amounts of supervision; this paper introduces a generic framework to train such networks, end-to-end, with no supervision. We propose to fix a set of target representations, called Noise As Targets (NAT), and to constrain the deep features to align to them.

By: Piotr Bojanowski, Armand Joulin
August 6, 2017

Wasserstein Generative Adversarial Networks

International Conference on Machine Learning (ICML)

We introduce a new algorithm named WGAN, an alternative to traditional GAN training. In this new model, we show that we can improve the stability of learning, get rid of problems like mode collapse, and provide meaningful learning curves useful for debugging and hyperparameter searches.

By: Martin Arjovsky, Soumith Chintala, Leon Bottou
August 6, 2017

Language Modeling with Gated Convolutional Networks

International Conference on Machine Learning (ICML)

The pre-dominant approach to language modeling to date is based on recurrent neural networks. Their success on this task is often linked to their ability to capture unbounded context. In this paper we develop a finite context approach through stacked convolutions, which can be more efficient since they allow parallelization over sequential tokens.

By: Yann Dauphin, Angela Fan, Michael Auli, David Grangier
August 6, 2017

Efficient Softmax Approximation for GPUs

International Conference on Machine Learning (ICML)

We propose an approximate strategy to efficiently train neural network based language models over very large vocabularies.

By: Edouard Grave, Armand Joulin, Moustapha Cisse, David Grangier, Hervé Jégou
August 6, 2017

Convolutional Sequence to Sequence Learning

International Conference on Machine Learning (ICML)

We introduce an architecture based entirely on convolutional neural networks.

By: Jonas Gehring, Michael Auli, David Grangier, Denis Yarats, Yann N. Dauphin