وصف النظم التي طورها مجلس البحوث القومي كندا للمهمة المشتركة لتحديد اللغة اليوراليك في حملة التقييم الفاديم 2021.قمنا بتقييم طريقتين مختلفتين لهذه المهمة: مصنف احتمالية استغلال حرف 5 غرامات فقط كميزات، وشبكة عصبية قائمة على الطابع مدربة مسبقا من خلال الإشراف الذاتي، ثم ضبطها على مهمة تحديد اللغة.تحولت الطريقة السابقة إلى أداء أفضل، مما يؤدي إلى الشك على فائدة أساليب التعلم العميق لتحديد اللغة، حيث لم يتمكنوا بعد بشكل مقنع وتفوقوا باستمرار على خوارزميات التصنيف أكثر بساطة وأقل تكلفة استغلال ميزات N-Gram.
We describe the systems developed by the National Research Council Canada for the Uralic language identification shared task at the 2021 VarDial evaluation campaign. We evaluated two different approaches to this task: a probabilistic classifier exploiting only character 5-grams as features, and a character-based neural network pre-trained through self-supervision, then fine-tuned on the language identification task. The former method turned out to perform better, which casts doubt on the usefulness of deep learning methods for language identification, where they have yet to convincingly and consistently outperform simpler and less costly classification algorithms exploiting n-gram features.
References used
https://aclanthology.org/
Coarse-grained linguistic information, such as named entities or phrases, facilitates adequately representation learning in pre-training. Previous works mainly focus on extending the objective of BERT's Masked Language Modeling (MLM) from masking ind
We describe our neural machine translation systems for the 2021 shared task on Unsupervised and Very Low Resource Supervised MT, translating between Upper Sorbian and German (low-resource) and between Lower Sorbian and German (unsupervised). The syst
High-performance neural language models have obtained state-of-the-art results on a wide range of Natural Language Processing (NLP) tasks. However, results for common benchmark datasets often do not reflect model reliability and robustness when appli
Saliency methods are widely used to interpret neural network predictions, but different variants of saliency methods often disagree even on the interpretations of the same prediction made by the same model. In these cases, how do we identify when are
We describe our participation in all the subtasks of the Germeval 2021 shared task on the identification of Toxic, Engaging, and Fact-Claiming Comments. Our system is an ensemble of state-of-the-art pre-trained models finetuned with carefully enginee