Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userRecurrent Attention for the Transformer
الانتباه المتكرر للمحول
346
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في هذا العمل، نقوم بإجراء تحقيق شامل على إحدى المركزيات من أنظمة الترجمة الآلية الحديثة: آلية اهتمام مفوض الترم التشفير.بدافع من مفهوم محاذاة الدرجة الأولى، فإننا نقدم آلية الاهتمام (الصليب) من خلال اتصال متكرر، مما يسمح بالوصول المباشر إلى قرارات الانتباه / المحاذاة السابقة.نقترح عدة طرق لتضمين مثل هذا التكرار في آلية الاهتمام.التحقق من أدائها عبر مهام ترجمة مختلفة نستنتج أن هذه الملحقات والتبعية ليست مفيدة لأداء الترجمة من بنية المحولات.
In this work, we conduct a comprehensive investigation on one of the centerpieces of modern machine translation systems: the encoder-decoder attention mechanism. Motivated by the concept of first-order alignments, we extend the (cross-)attention mechanism by a recurrent connection, allowing direct access to previous attention/alignment decisions. We propose several ways to include such a recurrency into the attention mechanism. Verifying their performance across different translation tasks we conclude that these extensions and dependencies are not beneficial for the translation performance of the Transformer architecture.
References used
https://aclanthology.org/
rate research
Read More
Recent research questions the importance of the dot-product self-attention in Transformer models and shows that most attention heads learn simple positional patterns. In this paper, we push further in this research line and propose a novel substitute
mechanism for self-attention: Recurrent AtteNtion (RAN) . RAN directly learns attention weights without any token-to-token interaction and further improves their capacity by layer-to-layer interaction. Across an extensive set of experiments on 10 machine translation tasks, we find that RAN models are competitive and outperform their Transformer counterpart in certain scenarios, with fewer parameters and inference time. Particularly, when apply RAN to the decoder of Transformer, there brings consistent improvements by about +0.5 BLEU on 6 translation tasks and +1.0 BLEU on Turkish-English translation task. In addition, we conduct extensive analysis on the attention weights of RAN to confirm their reasonableness. Our RAN is a promising alternative to build more effective and efficient NMT models.
Many sequence-to-sequence tasks in natural language processing are roughly monotonic in the alignment between source and target sequence, and previous work has facilitated or enforced learning of monotonic attention behavior via specialized attention
functions or pretraining. In this work, we introduce a monotonicity loss function that is compatible with standard attention mechanisms and test it on several sequence-to-sequence tasks: grapheme-to-phoneme conversion, morphological inflection, transliteration, and dialect normalization. Experiments show that we can achieve largely monotonic behavior. Performance is mixed, with larger gains on top of RNN baselines. General monotonicity does not benefit transformer multihead attention, however, we see isolated improvements when only a subset of heads is biased towards monotonic behavior.
To identefi the Bacterials agents in Meningitis resulting from basal skull
Fractures, The antibiotics sensitivity, and The benefit of pneumo 23 vaccine to prevent the occurrence of
meningitis in these cases.
Self-supervised learning has recently attracted considerable attention in the NLP community for its ability to learn discriminative features using a contrastive objective. This paper investigates whether contrastive learning can be extended to Transf
omer attention to tackling the Winograd Schema Challenge. To this end, we propose a novel self-supervised framework, leveraging a contrastive loss directly at the level of self-attention. Experimental analysis of our attention-based models on multiple datasets demonstrates superior commonsense reasoning capabilities. The proposed approach outperforms all comparable unsupervised approaches while occasionally surpassing supervised ones.
The Transformer translation model is based on the multi-head attention mechanism, which can be parallelized easily. The multi-head attention network performs the scaled dot-product attention function in parallel, empowering the model by jointly atten
ding to information from different representation subspaces at different positions. In this paper, we present an approach to learning a hard retrieval attention where an attention head only attends to one token in the sentence rather than all tokens. The matrix multiplication between attention probabilities and the value sequence in the standard scaled dot-product attention can thus be replaced by a simple and efficient retrieval operation. We show that our hard retrieval attention mechanism is 1.43 times faster in decoding, while preserving translation quality on a wide range of machine translation tasks when used in the decoder self- and cross-attention networks.
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
