output
20052013
most citedNatural Language Processing (almost) from Scratch

5.2k citations

Showing cs.LGShow all

8 papers · 1 filter

cs.LG20132 cited

Optimal amortized regret in every interval

Rina Panigrahy, Preyas Popat

Consider the classical problem of predicting the next bit in a sequence of bits. A standard performance measure is {\em regret} (loss in payoff) with respect to a set of experts. F…

cs.LG20131 cited

Fractal structures in Adversarial Prediction

Rina Panigrahy, Preyas Popat

Fractals are self-similar recursive structures that have been used in modeling several real world processes. In this work we study how "fractal-like" processes arise in a predictio…

cs.LG201311 cited

Large-Scale Learning with Less RAM via Randomization

Daniel Golovin, D. Sculley, H. Brendan McMahan +1

We reduce the memory footprint of popular large-scale online learning methods by projecting our weight vector onto a coarse discrete set using randomized rounding. Compared to stan…

cs.LG201332 cited

A Semantic Matching Energy Function for Learning with Multi-relational Data

Xavier Glorot, Antoine Bordes, Jason Weston +1

Large-scale relational learning becomes crucial for handling the huge amounts of structured data generated daily in many application domains ranging from computational biology or i…

cs.LG20121 cited

Latent Structured Ranking

Jason Weston, John Blitzer

Many latent (factorized) models have been proposed for recommendation tasks like collaborative filtering and for ranking tasks like document or image retrieval and annotation. Comm…

cs.LG20115.2k cited

Natural Language Processing (almost) from Scratch

Ronan Collobert, Jason Weston, Leon Bottou +3

We propose a unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including: part-of-speech tagging, chunking…