Sparse Stochastic Zeroth-Order Optimization with an Application to Bandit Structured Prediction

no code implementations • 12 Jun 2018 • Artem Sokolov, Julian Hitschler, Mayumi Ohta, Stefan Riezler

Stochastic zeroth-order (SZO), or gradient-free, optimization allows to optimize arbitrary functions by relying only on function evaluations under parameter perturbations, however, the iteration complexity of SZO methods suffers a factor proportional to the dimensionality of the perturbed function.

Structured Prediction

Correction of OCR Word Segmentation Errors in Articles from the ACL Collection through Neural Machine Translation Methods

no code implementations • LREC 2018 • Vivi Nastase, Julian Hitschler

Grammatical Error Correction Keyword Extraction +4

A Dataset and Reranking Method for Multimodal MT of User-Generated Image Captions

no code implementations • WS 2018 • Shigehiko Schamoni, Julian Hitschler, Stefan Riezler

Image Captioning Multimodal Machine Translation

Authorship Attribution with Convolutional Neural Networks and POS-Eliding

no code implementations • WS 2017 • Julian Hitschler, Esther van den Berg, Ines Rehbein

We use a convolutional neural network to perform authorship identification on a very homogeneous dataset of scientific publications.

Authorship Attribution POS

Nematus: a Toolkit for Neural Machine Translation

4 code implementations • EACL 2017 • Rico Sennrich, Orhan Firat, Kyunghyun Cho, Alexandra Birch, Barry Haddow, Julian Hitschler, Marcin Junczys-Dowmunt, Samuel Läubli, Antonio Valerio Miceli Barone, Jozef Mokry, Maria Nădejde

We present Nematus, a toolkit for Neural Machine Translation.

Machine Translation Translation

Multimodal Pivots for Image Caption Translation

no code implementations • ACL 2016 • Julian Hitschler, Shigehiko Schamoni, Stefan Riezler

We present an approach to improve statistical machine translation of image descriptions by multimodal pivots defined in visual space.

Image Retrieval Machine Translation +2