Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userEfficient Content-Based Sparse Attention with Routing Transformers
الاهتمام المستند إلى المحتوى المستند إلى المحتوى مع محولات التوجيه
387
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تم اعتماد اهتمام الذات مؤخرا لمجموعة واسعة من مشاكل النمذجة التسلسلية. على الرغم من فعاليته، فإن اهتمام الذات يعاني من حساب التربيعي ومتطلبات الذاكرة فيما يتعلق بطول التسلسل. تركز النهج الناجحة للحد من هذا التعقيد على حضور النوافذ المنزلق المحلية أو مجموعة صغيرة من المواقع مستقلة عن المحتوى. يقترح عملنا تعلم أنماط الانتباه ديناميكية متناثرة تتجنب تخصيص الحساب والذاكرة لحضور المحتوى غير المرتبط باستعلام الفائدة. يبني هذا العمل على سطرين من الأبحاث: فهو يجمع بين مرونة النمذجة للعمل المسبق على اهتمام متمرد للمحتوى مع مكاسب الكفاءة من الأساليب القائمة على الاهتمام المحلي والزموني المتناثر. نموذجنا، محول التوجيه، ينفذ عن النفس مع وحدة توجيه متناثرة تعتمد على الوسائل K عبر الإنترنت مع تقليل التعقيد العام للانتباه إلى O (N1.5D) من O (N2D) لطول التسلسل N وبعد المخفي D. نظرا لأن نموذجنا يتفوق على نماذج انتباه متناثرة قابلة للمقارنة على نمذجة اللغة على Wikitext-103 (15.8 مقابل 18.3 حيرة)، وكذلك على جيل الصورة على Imagenet-64 (3.43 مقابل 3.44 بت / خافت) أثناء استخدام طبقات أقل من الاهتمام الذاتي. بالإضافة إلى ذلك، وضعنا مجموعة جديدة من مجموعة جديدة من مجموعة بيانات PG-19 التي تم إصدارها حديثا، والحصول على اختبار حيرة من 33.2 مع نموذج محول توجيه 22 طبقة مدرب على تسلسل الطول 8192. نحن نفتح المصدر لتحويل التوجيه في Tensorflow.1
Self-attention has recently been adopted for a wide range of sequence modeling problems. Despite its effectiveness, self-attention suffers from quadratic computation and memory requirements with respect to sequence length. Successful approaches to reduce this complexity focused on attending to local sliding windows or a small set of locations independent of content. Our work proposes to learn dynamic sparse attention patterns that avoid allocating computation and memory to attend to content unrelated to the query of interest. This work builds upon two lines of research: It combines the modeling flexibility of prior work on content-based sparse attention with the efficiency gains from approaches based on local, temporal sparse attention. Our model, the Routing Transformer, endows self-attention with a sparse routing module based on online k-means while reducing the overall complexity of attention to O(n1.5d) from O(n2d) for sequence length n and hidden dimension d. We show that our model outperforms comparable sparse attention models on language modeling on Wikitext-103 (15.8 vs 18.3 perplexity), as well as on image generation on ImageNet-64 (3.43 vs 3.44 bits/dim) while using fewer self-attention layers. Additionally, we set a new state-of-the-art on the newly released PG-19 data-set, obtaining a test perplexity of 33.2 with a 22 layer Routing Transformer model trained on sequences of length 8192. We open-source the code for Routing Transformer in Tensorflow.1
References used
https://aclanthology.org/
rate research
Read More
Passage retrieval and ranking is a key task in open-domain question answering and information retrieval. Current effective approaches mostly rely on pre-trained deep language model-based retrievers and rankers. These methods have been shown to effect
ively model the semantic matching between queries and passages, also in presence of keyword mismatch, i.e. passages that are relevant to a query but do not contain important query keywords. In this paper we consider the Dense Retriever (DR), a passage retrieval method, and the BERT re-ranker, a popular passage re-ranking method. In this context, we formally investigate how these models respond and adapt to a specific type of keyword mismatch -- that caused by keyword typos occurring in queries. Through empirical investigation, we find that typos can lead to a significant drop in retrieval and ranking effectiveness. We then propose a simple typos-aware training framework for DR and BERT re-ranker to address this issue. Our experimental results on the MS MARCO passage ranking dataset show that, with our proposed typos-aware training, DR and BERT re-ranker can become robust to typos in queries, resulting in significantly improved effectiveness compared to models trained without appropriately accounting for typos.
Fully understanding narratives often requires identifying events in the context of whole documents and modeling the event relations. However, document-level event extraction is a challenging task as it requires the extraction of event and entity core
ference, and capturing arguments that span across different sentences. Existing works on event extraction usually confine on extracting events from single sentences, which fail to capture the relationships between the event mentions at the scale of a document, as well as the event arguments that appear in a different sentence than the event trigger. In this paper, we propose an end-to-end model leveraging Deep Value Networks (DVN), a structured prediction algorithm, to efficiently capture cross-event dependencies for document-level event extraction. Experimental results show that our approach achieves comparable performance to CRF-based models on ACE05, while enjoys significantly higher computational efficiency.
Current benchmark tasks for natural language processing contain text that is qualitatively different from the text used in informal day to day digital communication. This discrepancy has led to severe performance degradation of state-of-the-art NLP m
odels when fine-tuned on real-world data. One way to resolve this issue is through lexical normalization, which is the process of transforming non-standard text, usually from social media, into a more standardized form. In this work, we propose a sentence-level sequence-to-sequence model based on mBART, which frames the problem as a machine translation problem. As the noisy text is a pervasive problem across languages, not just English, we leverage the multi-lingual pre-training of mBART to fine-tune it to our data. While current approaches mainly operate at the word or subword level, we argue that this approach is straightforward from a technical standpoint and builds upon existing pre-trained transformer networks. Our results show that while word-level, intrinsic, performance evaluation is behind other methods, our model improves performance on extrinsic, downstream tasks through normalization compared to models operating on raw, unprocessed, social media text.
Despite the recent successes of transformer-based models in terms of effectiveness on a variety of tasks, their decisions often remain opaque to humans. Explanations are particularly important for tasks like offensive language or toxicity detection o
n social media because a manual appeal process is often in place to dispute automatically flagged content. In this work, we propose a technique to improve the interpretability of these models, based on a simple and powerful assumption: a post is at least as toxic as its most toxic span. We incorporate this assumption into transformer models by scoring a post based on the maximum toxicity of its spans and augmenting the training process to identify correct spans. We find this approach effective and can produce explanations that exceed the quality of those provided by Logistic Regression analysis (often regarded as a highly-interpretable model), according to a human study.
هدفنا من خلال هذه الدراسة في إطار المشروع الفصلي للسنة الرابعة إلى إلقاء الضوء على استرجاع الصور من مجموعة كبيرة بالاعتماد على محتوى صورة هدف , و قمنا بتدعيم هذه الدراسة بتطبيق ضمن بيئة الماتلاب لبرنامج بحث عن الصور المشابهة لصورة مدخلة .
و قد تركز
بحثنا على ميزتين هامتين يكاد لا يخلو منها أي نظام بحث عن الصور بالاعتماد على المحتوى و هما ميزتي الهيستوغرام اللوني و بنية الصورة texture , ووضحنا الخطوات التي يتم في ضوئها عملية الاسترجاع بدءاً من تحليل الصورة و استخلاص شعاع الواصفات الخاص فيها , و مطابقته مع أشعة الميزات الخاصة بالصور الموجودة في قاعدة البيانات ليتم ترتيب الصور بحسب مدى تشابهها من الصورة الهدف .
و تطرقت الدراسة إلى استخدام الفضاء اللوني HMMD كبديل للفضاء اللوني RGB لاستخراج واصفات البنية اللونية على اعتبار أنه نموذج لوني موجه بالمستخدم user oriented و بالتالي نضمن أن نحصل على نتائج أفضل ترضي المستخدم .
وقمنا بتدعيم الدراسة بعدد من الأشكال و الأمثلة و المخططات التي توضح محتوى الدراسة النظرية و ما قمنا بعمله في التطبيق ضمن بيئة الماتلاب .
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
