في هذه الورقة مقارنة أداء ثلاث نماذج: SGNS (أخذ العينات السلبية Skip-Gram) والإصدارات المعززة من SVD (تحلل القيمة المفرد) و PPMI (معلومات متبادلة إيجابية) على مهمة تشابه كلمة.نحن نركز بشكل خاص على دور ضبط فرط التشعيم من أجل الهندية القائمة على التوصيات المقدمة في العمل السابق (على اللغة الإنجليزية).تظهر نتائجنا أن هناك تفضيلات محددة للغة لهذه الفرط.نحن نقدم أفضل إعدادات للهيكلية إلى مجموعة من اللغات ذات العلاقة: البنجابية، الغوجاراتية والمريثي مع نتائج مواتية.نجد أيضا أن نموذج SVD يتم ضبطه بشكل مناسب يتفوق على SGNS لمعظم لغاتنا وهو أيضا أكثر قوة في إعداد الموارد المنخفضة.
In this paper we compare the performance of three models: SGNS (skip-gram negative sampling) and augmented versions of SVD (singular value decomposition) and PPMI (Positive Pointwise Mutual Information) on a word similarity task. We particularly focus on the role of hyperparameter tuning for Hindi based on recommendations made in previous work (on English). Our results show that there are language specific preferences for these hyperparameters. We extend the best settings for Hindi to a set of related languages: Punjabi, Gujarati and Marathi with favourable results. We also find that a suitably tuned SVD model outperforms SGNS for most of our languages and is also more robust in a low-resource setting.
References used
https://aclanthology.org/
We present an extended version of a tool developed for calculating linguistic distances and asymmetries in auditory perception of closely related languages. Along with evaluating the metrics available in the initial version of the tool, we introduce
The most successful approach to Neural Machine Translation (NMT) when only monolingual training data is available, called unsupervised machine translation, is based on back-translation where noisy translations are generated to turn the task into a su
Temporal language grounding (TLG) aims to localize a video segment in an untrimmed video based on a natural language description. To alleviate the expensive cost of manual annotations for temporal boundary labels,we are dedicated to the weakly superv
Pre-trained language models (PrLM) have to carefully manage input units when training on a very large text with a vocabulary consisting of millions of words. Previous works have shown that incorporating span-level information over consecutive words i
This paper reports the Machine Translation (MT) systems submitted by the IIITT team for the English→Marathi and English⇔Irish language pairs LoResMT 2021 shared task. The task focuses on getting exceptional translations for rather low-resourced langu