164 citations · 291 across the 40 of their papers we have counts for
9 papers · 1 filter
Automatic Creation of Text Corpora for Low-Resource Languages from the Internet: The Case of Swiss German
Lucy Linder, Michael Jungo, Jean Hennebert +2
This paper presents SwissCrawl, the largest Swiss German text corpus to date. Composed of more than half a million sentences, it was generated using a customized web scraping tool…
Alleviating Sequence Information Loss with Data Overlapping and Prime Batch Sizes
Noémien Kocher, Christian Scuito, Lorenzo Tarantino +3
In sequence modeling tasks the token order matters, but this information can be partially lost due to the discretization of the sequence into data points. In this paper, we study t…
Multi-Dimensional Explanation of Target Variables from Documents
Diego Antognini, Claudiu Musat, Boi Faltings
Automated predictions require explanations to be interpretable by humans. Past work used attention and rationale mechanisms to find words that predict the target variable of a docu…
Benefiting from Multitask Learning to Improve Single Image Super-Resolution
Mohammad Saeed Rad, Behzad Bozorgtabar, Claudiu Musat +4
Despite significant progress toward super resolving more realistic images by deeper convolutional neural networks (CNNs), reconstructing fine and natural textures still remains a c…
Resilient Combination of Complementary CNN and RNN Features for Text Classification through Attention and Ensembling
Athanasios Giannakopoulos, Maxime Coriou, Andreea Hossmann +2
State-of-the-art methods for text classification include several distinct steps of pre-processing, feature extraction and post-processing. In this work, we focus on end-to-end neur…
Expanding the Text Classification Toolbox with Cross-Lingual Embeddings
Meryem M'hamdi, Robert West, Andreea Hossmann +2
Most work in text classification and Natural Language Processing (NLP) focuses on English or a handful of other languages that have text corpora of hundreds of millions of words. T…
Overcoming Multi-Model Forgetting
Yassine Benyahia, Kaicheng Yu, Kamil Bennani-Smires +4
We identify a phenomenon, which we refer to as multi-model forgetting, that occurs when sequentially training multiple deep networks with partially-shared parameters; the performan…
Interpretable Structure-aware Document Encoders with Hierarchical Attention
Khalil Mrini, Claudiu Musat, Michael Baeriswyl +1
We propose a method to create document representations that reflect their internal structure. We modify Tree-LSTMs to hierarchically merge basic elements such as words and sentence…
Evaluating the Search Phase of Neural Architecture Search
Kaicheng Yu, Christian Sciuto, Martin Jaggi +2
Neural Architecture Search (NAS) aims to facilitate the design of deep networks for new tasks. Existing techniques rely on two stages: searching over the architecture space and val…