Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDo Transformer Modifications Transfer Across Implementations and Applications?
هل تحويل تعديلات المحولات عبر التطبيقات والتطبيقات؟
194
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
اقترح مجتمع البحث تعديلات غزيرة على بنية المحولات منذ تقديمها منذ أكثر من ثلاث سنوات، قلة قليلة نسبيا والتي شهدت اعتماد واسع النطاق.في هذه الورقة، نقوم بتقييم العديد من هذه التعديلات بشكل شامل في بيئة تجريبية مشتركة تغطي معظم الاستخدامات المشتركة للمحول في معالجة اللغة الطبيعية.من المستغرب، نجد أن معظم التعديلات لا تحسن بشكل مفيد الأداء.علاوة على ذلك، تم تطوير معظم المتغيرات المحولات التي وجدناها مفيدة في نفس الكود التي استخدمناها أو أنها تغييرات طفيفة نسبيا.نحن نقم التخمين أن تحسينات الأداء قد تعتمد بشدة على تفاصيل التنفيذ وتقديم بعض التوصيات في المقابل لتحسين عمومية النتائج التجريبية.
The research community has proposed copious modifications to the Transformer architecture since it was introduced over three years ago, relatively few of which have seen widespread adoption. In this paper, we comprehensively evaluate many of these modifications in a shared experimental setting that covers most of the common uses of the Transformer in natural language processing. Surprisingly, we find that most modifications do not meaningfully improve performance. Furthermore, most of the Transformer variants we found beneficial were either developed in the same codebase that we used or are relatively minor changes. We conjecture that performance improvements may strongly depend on implementation details and correspondingly make some recommendations for improving the generality of experimental results.
References used
https://aclanthology.org/
rate research
Read More
Pretraining techniques leveraging enormous datasets have driven recent advances in text summarization. While folk explanations suggest that knowledge transfer accounts for pretraining's benefits, little is known about why it works or what makes a pre
training task or dataset suitable. In this paper, we challenge the knowledge transfer story, showing that pretraining on documents consisting of character n-grams selected at random, we can nearly match the performance of models pretrained on real corpora. This work holds the promise of eliminating upstream corpora, which may alleviate some concerns over offensive language, bias, and copyright issues. To see whether the small residual benefit of using real data could be accounted for by the structure of the pretraining task, we design several tasks motivated by a qualitative study of summarization corpora. However, these tasks confer no appreciable benefit, leaving open the possibility of a small role for knowledge transfer.
Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potential for zero-shot cross-lingual transfer. However, these multilingual encoders do not precisely align words and phrases across languages. Especially, le
arning alignments in the multilingual embedding space usually requires sentence-level or word-level parallel corpora, which are expensive to be obtained for low-resource languages. An alternative is to make the multilingual encoders more robust; when fine-tuning the encoder using downstream task, we train the encoder to tolerate noise in the contextual embedding spaces such that even if the representations of different languages are not aligned well, the model can still achieve good performance on zero-shot cross-lingual transfer. In this work, we propose a learning strategy for training robust models by drawing connections between adversarial examples and the failure cases of zero-shot cross-lingual transfer. We adopt two widely used robust training methods, adversarial training and randomized smoothing, to train the desired robust model. The experimental results demonstrate that robust training improves zero-shot cross-lingual transfer on text classification tasks. The improvement is more significant in the generalized cross-lingual transfer setting, where the pair of input sentences belong to two different languages.
The success of language models based on the Transformer architecture appears to be inconsistent with observed anisotropic properties of representations learned by such models. We resolve this by showing, contrary to previous studies, that the represe
ntations do not occupy a narrow cone, but rather drift in common directions. At any training step, all of the embeddings except for the ground-truth target embedding are updated with gradient in the same direction. Compounded over the training set, the embeddings drift and share common components, manifested in their shape in all the models we have empirically tested. Our experiments show that isotropy can be restored using a simple transformation.
In order to improve the performance of transformers in highvoltage
networks and re-electrical characteristics of insulation
materials for these transformers to the nominal accepted value,
methods of technical and new process are appeared to re-qua
lify
insulation transformers in their work sites in electrical transfer
stations without having to transport them to workshops or to
laboratories factory .
Previous work on crosslingual Relation and Event Extraction (REE) suffers from the monolingual bias issue due to the training of models on only the source language data. An approach to overcome this issue is to use unlabeled data in the target langua
ge to aid the alignment of crosslingual representations, i.e., via fooling a language discriminator. However, as this approach does not condition on class information, a target language example of a class could be incorrectly aligned to a source language example of a different class. To address this issue, we propose a novel crosslingual alignment method that leverages class information of REE tasks for representation learning. In particular, we propose to learn two versions of representation vectors for each class in an REE task based on either source or target language examples. Representation vectors for corresponding classes will then be aligned to achieve class-aware alignment for crosslingual representations. In addition, we propose to further align representation vectors for language-universal word categories (i.e., parts of speech and dependency relations). As such, a novel filtering mechanism is presented to facilitate the learning of word category representations from contextualized representations on input texts based on adversarial learning. We conduct extensive crosslingual experiments with English, Chinese, and Arabic over REE tasks. The results demonstrate the benefits of the proposed method that significantly advances the state-of-the-art performance in these settings.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
