6 citations · 20 across the 30 of their papers we have counts for
9 papers · 1 filter
Don't Touch My Diacritics
Kyle Gorman, Yuval Pinter
The common practice of preprocessing text before feeding it into NLP models introduces many decision points which have unintended consequences on model performance. In this opinion…
OMPar: Automatic Parallelization with AI-Driven Source-to-Source Compilation
Tal Kadosh, Niranjan Hasabnis, Prema Soundararajan +5
Manual parallelization of code remains a significant challenge due to the complexities of modern software systems and the widespread adoption of multi-core architectures. This pape…
Protecting Privacy in Classifiers by Token Manipulation
Re'em Harel, Yair Elboher, Yuval Pinter
Using language models as a remote service entails sending private information to an untrusted provider. In addition, potential eavesdroppers can intercept the messages, thereby exp…
Evaluating Subword Tokenization: Alien Subword Composition and OOV Generalization Challenge
Khuyagbaatar Batsuren, Ekaterina Vylomova, Verna Dankers +4
The popular subword tokenizers of current language models, such as Byte-Pair Encoding (BPE), are known not to respect morpheme boundaries, which affects the downstream performance…
An Analysis of BPE Vocabulary Trimming in Neural Machine Translation
Marco Cognetta, Tatsuya Hiraoka, Naoaki Okazaki +2
We explore threshold vocabulary trimming in Byte-Pair Encoding subword tokenization, a postprocessing step that replaces rare subwords with their component subwords. The technique…
BiVert: Bidirectional Vocabulary Evaluation using Relations for Machine Translation
Carinne Cherf, Yuval Pinter
Neural machine translation (NMT) has progressed rapidly in the past few years, promising improvements and quality translations for different languages. Evaluation of this task is c…