مؤخرا، تستخدم الترجمة الآلية العصبية على نطاق واسع لدقة الترجمة عالية، ولكن من المعروف أيضا أن تظهر أداء ضعيف في ترجمة جماعية طويلة.الى جانب ذلك، يظهر هذا الاتجاه بشكل بارز لغات الموارد المنخفضة.نحن نفترض أن هذه المشاكل ناتجة عن جمل طويلة كونها قليلة في بيانات القطار.لذلك، نقترح طريقة تكبير البيانات للتعامل مع جمل طويلة.طريقتنا بسيطة؛نحن نستخدم فقط شركة موازية معينة كبيانات تدريب وتوليد جمل طويلة من خلال تسليط جملتين.بناء على تجاربنا، نؤكد تحسينات في ترجمة جماعية طويلة من خلال تكبير البيانات المقترح على الرغم من البساطة.علاوة على ذلك، تقوم الطريقة المقترحة بتحسين جودة الترجمة أكثر عندما تقترن بالترجمة الخلفية.
Recently, neural machine translation is widely used for its high translation accuracy, but it is also known to show poor performance at long sentence translation. Besides, this tendency appears prominently for low resource languages. We assume that these problems are caused by long sentences being few in the train data. Therefore, we propose a data augmentation method for handling long sentences. Our method is simple; we only use given parallel corpora as train data and generate long sentences by concatenating two sentences. Based on our experiments, we confirm improvements in long sentence translation by proposed data augmentation despite the simplicity. Moreover, the proposed method improves translation quality more when combined with back-translation.
References used
https://aclanthology.org/
We propose a data augmentation method for neural machine translation. It works by interpreting language models and phrasal alignment causally. Specifically, it creates augmented parallel translation corpora by generating (path-specific) counterfactua
Data augmentation, which refers to manipulating the inputs (e.g., adding random noise,masking specific parts) to enlarge the dataset,has been widely adopted in machine learning. Most data augmentation techniques operate on a single input, which limit
We observe that the development cross-entropy loss of supervised neural machine translation models scales like a power law with the amount of training data and the number of non-embedding parameters in the model. We discuss some practical implication
In this paper, we investigate the driving factors behind concatenation, a simple but effective data augmentation method for low-resource neural machine translation. Our experiments suggest that discourse context is unlikely the cause for concatenatio
We present a simple method for extending transformers to source-side trees. We define a number of masks that limit self-attention based on relationships among tree nodes, and we allow each attention head to learn which mask or masks to use. On transl