Translating Embeddings for Modeling Multi-relational Data
- Antoine Bordes, Nicolas Usunier, Alberto García-Durán, J. Weston, Oksana Yakhnenko
- Computer ScienceNIPS
- 5 December 2013
TransE is proposed, a method which models relationships by interpreting them as translations operating on the low-dimensional embeddings of the entities, which proves to be powerful since extensive experiments show that TransE significantly outperforms state-of-the-art methods in link prediction on two knowledge bases.
Deep Sparse Rectifier Neural Networks
- Xavier Glorot, Antoine Bordes, Yoshua Bengio
- Computer ScienceInternational Conference on Artificial…
- 14 June 2011
This paper shows that rectifying neurons are an even better model of biological neurons and yield equal or better performance than hyperbolic tangent networks in spite of the hard non-linearity and non-dierentiabil ity.
Supervised Learning of Universal Sentence Representations from Natural Language Inference Data
- Alexis Conneau, Douwe Kiela, Holger Schwenk, Loïc Barrault, Antoine Bordes
- Computer ScienceConference on Empirical Methods in Natural…
- 5 May 2017
It is shown how universal sentence representations trained using the supervised data of the Stanford Natural Language Inference datasets can consistently outperform unsupervised methods like SkipThought vectors on a wide range of transfer tasks.
Reading Wikipedia to Answer Open-Domain Questions
- Danqi Chen, Adam Fisch, J. Weston, Antoine Bordes
- Computer ScienceAnnual Meeting of the Association for…
- 31 March 2017
This approach combines a search component based on bigram hashing and TF-IDF matching with a multi-layer recurrent neural network model trained to detect answers in Wikipedia paragraphs, indicating that both modules are highly competitive with respect to existing counterparts.
Domain Adaptation for Large-Scale Sentiment Classification: A Deep Learning Approach
- Xavier Glorot, Antoine Bordes, Yoshua Bengio
- Computer ScienceInternational Conference on Machine Learning
- 28 June 2011
A deep learning approach is proposed which learns to extract a meaningful representation for each review in an unsupervised fashion and clearly outperform state-of-the-art methods on a benchmark composed of reviews of 4 types of Amazon products.
Large-scale Simple Question Answering with Memory Networks
- Antoine Bordes, Nicolas Usunier, S. Chopra, J. Weston
- Computer ScienceArXiv
- 5 June 2015
This paper studies the impact of multitask and transfer learning for simple question answering; a setting for which the reasoning required to answer is quite easy, as long as one can retrieve the correct evidence given a question, which can be difficult in large-scale conditions.
Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks
- J. Weston, Antoine Bordes, S. Chopra, Tomas Mikolov
- Computer ScienceInternational Conference on Learning…
- 19 February 2015
This work argues for the usefulness of a set of proxy tasks that evaluate reading comprehension via question answering, and classify these tasks into skill sets so that researchers can identify (and then rectify) the failings of their systems.
Memory Networks
- J. Weston, S. Chopra, Antoine Bordes
- Computer ScienceInternational Conference on Learning…
- 14 October 2014
This work describes a new class of learning models called memory networks, which reason with inference components combined with a long-term memory component; they learn how to use these jointly.
The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations
- Felix Hill, Antoine Bordes, S. Chopra, J. Weston
- Computer ScienceInternational Conference on Learning…
- 7 November 2015
There is a sweet-spot, not too big and not too small, between single words and full sentences that allows the most meaningful information in a text to be effectively retained and recalled, and models which store explicit representations of long-term contexts outperform state-of-the-art neural language models at predicting semantic content words.
Learning End-to-End Goal-Oriented Dialog
- Antoine Bordes, J. Weston
- Computer ScienceInternational Conference on Learning…
- 24 May 2016
It is shown that an end-to-end dialog system based on Memory Networks can reach promising, yet imperfect, performance and learn to perform non-trivial operations and be compared to a hand-crafted slot-filling baseline on data from the second Dialog State Tracking Challenge.
...
...