يمكن أن نطاقات اللغة العصبية التي تدركها القبض على العلاقة بين الكلمات من خلال استغلال معلومات مستوى الطابع وهي فعالة بشكل خاص للغات مع التشكل الغني.ومع ذلك، عادة ما تكون هذه النماذج متحيزة باتجاه المعلومات من أشكال السطح.لتخفيف هذه المشكلة، نقترح طريقة بسيطة وفعالة لتحسين نموذج اللغة العصبي على الحرف من خلال إجبار ترميز الأحرف لإنتاج شرائح قائمة على الكلمات تحت بنية Skip-Gram في خطوة الاحماء دون بيانات تدريب إضافية.نظرا لإيبربريكيا أن نموذج اللغة العصبي الإدراك على الطابع الناتج يحقق تحسينات واضحة لدرجات الحيرة على لغات متنوعة من النطبية، والتي تحتوي على العديد من الكلمات منخفضة التردد أو غير المرئي.
Character-aware neural language models can capture the relationship between words by exploiting character-level information and are particularly effective for languages with rich morphology. However, these models are usually biased towards information from surface forms. To alleviate this problem, we propose a simple and effective method to improve a character-aware neural language model by forcing a character encoder to produce word-based embeddings under Skip-gram architecture in a warm-up step without extra training data. We empirically show that the resulting character-aware neural language model achieves obvious improvements of perplexity scores on typologically diverse languages, that contain many low-frequency or unseen words.
References used
https://aclanthology.org/
Recent impressive improvements in NLP, largely based on the success of contextual neural language models, have been mostly demonstrated on at most a couple dozen high- resource languages. Building language mod- els and, more generally, NLP systems fo
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 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 explo
Aspect detection is a fundamental task in opinion mining. Previous works use seed words either as priors of topic models, as anchors to guide the learning of aspects, or as features of aspect classifiers. This paper presents a novel weakly-supervised
This paper explores character-driven story continuation, in which the story emerges through characters' first- and second-person narration as well as dialogue---requiring models to select language that is consistent with a character's persona and the