نقترح هندسة محول الرسم البياني المتكرر للرسوم البيانية التلقائي (Rngtr) من أجل تحسين الرسوم البيانية التعسفية من خلال التطبيق العسكري لمحول الرسم البياني غير التلقائي إلى الرسم البياني وتطبيقه على تحليل التبعية النحوية.نوضح قوة وفعالية Rngtr على العديد من شركات التبعية، باستخدام نموذج التقييم المدرب مسبقا مع بيرت.نقدم أيضا محولات محول النحوية (Sytr)، وهي محلل غير متكرر مشابهة لنموذج التقييم الخاص بنا.يمكن Rngtr تحسين دقة مجموعة متنوعة من المحللين الأوليين في 13 لغة من التبعيات الشاملة TreeBanks والإنجليزية والصينية Benn Treebanks، والجوربوس الألماني Conll2009، وحتى تحسين النتائج الجديدة على النتائج الجديدة التي حققتها Systr، بشكل كبيرتحسين أحدث حديثة لجميع الشركات التي تم اختبارها.
We propose the Recursive Non-autoregressive Graph-to-Graph Transformer architecture (RNGTr) for the iterative refinement of arbitrary graphs through the recursive application of a non-autoregressive Graph-to-Graph Transformer and apply it to syntactic dependency parsing. We demonstrate the power and effectiveness of RNGTr on several dependency corpora, using a refinement model pre-trained with BERT. We also introduce Syntactic Transformer (SynTr), a non-recursive parser similar to our refinement model. RNGTr can improve the accuracy of a variety of initial parsers on 13 languages from the Universal Dependencies Treebanks, English and Chinese Penn Treebanks, and the German CoNLL2009 corpus, even improving over the new state-of-the-art results achieved by SynTr, significantly improving the state-of-the-art for all corpora tested.
References used
https://aclanthology.org/
Complex natural language applications such as speech translation or pivot translation traditionally rely on cascaded models. However,cascaded models are known to be prone to error propagation and model discrepancy problems. Furthermore, there is no p
Event detection (ED) task aims to classify events by identifying key event trigger words embedded in a piece of text. Previous research have proved the validity of fusing syntactic dependency relations into Graph Convolutional Networks(GCN). While ex
Non-Autoregressive machine Translation (NAT) models have demonstrated significant inference speedup but suffer from inferior translation accuracy. The common practice to tackle the problem is transferring the Autoregressive machine Translation (AT) k
In cross-lingual text classification, it is required that task-specific training data in high-resource source languages are available, where the task is identical to that of a low-resource target language. However, collecting such training data can b
Unsupervised cross-domain dependency parsing is to accomplish domain adaptation for dependency parsing without using labeled data in target domain. Existing methods are often of the pseudo-annotation type, which generates data through self-annotation