Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userLayoutReader: Pre-training of Text and Layout for Reading Order Detection
Layoutreader: ما قبل التدريب للنص والتخطيط لكشف عن ترتيب القراءة
317
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
كشف ترتيب القراءة هو حجر الزاوية لفهم المستندات البصرية (على سبيل المثال، الإيصالات والأشكال). لسوء الحظ، أي عمل موجود استفاد من نماذج التعلم العميقة المتقدمة لأنها شاقة للغاية للتعليق على مجموعة بيانات كبيرة بما فيه الكفاية. نلاحظ أن ترتيب القراءة من مستندات Word مضمن في بيانات تعريف XML الخاصة بهم؛ وفي الوقت نفسه، من السهل تحويل مستندات Word إلى ملفات PDF أو الصور. لذلك، في طريقة تلقائية، نقوم ببناء Redlybank، مجموعة بيانات معيار تحتوي على ترتيب القراءة والنصوص والتخطيط لمعلومات 500000 صورة وثيقة تغطي مجموعة واسعة من أنواع المستندات. هذه مجموعة بيانات كبيرة على نطاق واسع يطلق تشغيل قوة الشبكات العصبية العميقة لكشف عن الطلب. على وجه التحديد، يلتقط LayoTreader المقترح معلومات النص والتخطيط لتوقعات ترتيب القراءة باستخدام نموذج SEQ2SEQ. يؤدي ذلك بشكل مثالي تقريبا في اكتشاف أمر القراءة ويحسن بشكل كبير من محركات الحرية الخارجية المفتوحة والمصادر الحرارية في ترتيب خطوط نصية في نتائجها في تجاربنا. يتم توفير مجموعة البيانات والنماذج علنا في https://aka.ms/layouoTreader.
Reading order detection is the cornerstone to understanding visually-rich documents (e.g., receipts and forms). Unfortunately, no existing work took advantage of advanced deep learning models because it is too laborious to annotate a large enough dataset. We observe that the reading order of WORD documents is embedded in their XML metadata; meanwhile, it is easy to convert WORD documents to PDFs or images. Therefore, in an automated manner, we construct ReadingBank, a benchmark dataset that contains reading order, text, and layout information for 500,000 document images covering a wide spectrum of document types. This first-ever large-scale dataset unleashes the power of deep neural networks for reading order detection. Specifically, our proposed LayoutReader captures the text and layout information for reading order prediction using the seq2seq model. It performs almost perfectly in reading order detection and significantly improves both open-source and commercial OCR engines in ordering text lines in their results in our experiments. The dataset and models are publicly available at https://aka.ms/layoutreader.
References used
https://aclanthology.org/
rate research
Read More
A possible explanation for the impressive performance of masked language model (MLM) pre-training is that such models have learned to represent the syntactic structures prevalent in classical NLP pipelines. In this paper, we propose a different expla
nation: MLMs succeed on downstream tasks almost entirely due to their ability to model higher-order word co-occurrence statistics. To demonstrate this, we pre-train MLMs on sentences with randomly shuffled word order, and show that these models still achieve high accuracy after fine-tuning on many downstream tasks---including tasks specifically designed to be challenging for models that ignore word order. Our models perform surprisingly well according to some parametric syntactic probes, indicating possible deficiencies in how we test representations for syntactic information. Overall, our results show that purely distributional information largely explains the success of pre-training, and underscore the importance of curating challenging evaluation datasets that require deeper linguistic knowledge.
Advances in English language representation enabled a more sample-efficient pre-training task by Efficiently Learning an Encoder that Classifies Token Replacements Accurately (ELECTRA). Which, instead of training a model to recover masked tokens, it
trains a discriminator model to distinguish true input tokens from corrupted tokens that were replaced by a generator network. On the other hand, current Arabic language representation approaches rely only on pretraining via masked language modeling. In this paper, we develop an Arabic language representation model, which we name AraELECTRA. Our model is pretrained using the replaced token detection objective on large Arabic text corpora. We evaluate our model on multiple Arabic NLP tasks, including reading comprehension, sentiment analysis, and named-entity recognition and we show that AraELECTRA outperforms current state-of-the-art Arabic language representation models, given the same pretraining data and with even a smaller model size.
We present VideoCLIP, a contrastive approach to pre-train a unified model for zero-shot video and text understanding, without using any labels on downstream tasks. VideoCLIP trains a transformer for video and text by contrasting temporally overlappin
g positive video-text pairs with hard negatives from nearest neighbor retrieval. Our experiments on a diverse series of downstream tasks, including sequence-level text-video retrieval, VideoQA, token-level action localization, and action segmentation reveal state-of-the-art performance, surpassing prior work, and in some cases even outperforming supervised approaches. Code is made available at https://github.com/pytorch/fairseq/examples/MMPT.
Code summarization and generation empower conversion between programming language (PL) and natural language (NL), while code translation avails the migration of legacy code from one PL to another. This paper introduces PLBART, a sequence-to-sequence
model capable of performing a broad spectrum of program and language understanding and generation tasks. PLBART is pre-trained on an extensive collection of Java and Python functions and associated NL text via denoising autoencoding. Experiments on code summarization in the English language, code generation, and code translation in seven programming languages show that PLBART outperforms or rivals state-of-the-art models. Moreover, experiments on discriminative tasks, e.g., program repair, clone detection, and vulnerable code detection, demonstrate PLBART's effectiveness in program understanding. Furthermore, analysis reveals that PLBART learns program syntax, style (e.g., identifier naming convention), logical flow (e.g., if block inside an else block is equivalent to else if block) that are crucial to program semantics and thus excels even with limited annotations.
In this work, we focus on a more challenging few-shot intent detection scenario where many intents are fine-grained and semantically similar. We present a simple yet effective few-shot intent detection schema via contrastive pre-training and fine-tun
ing. Specifically, we first conduct self-supervised contrastive pre-training on collected intent datasets, which implicitly learns to discriminate semantically similar utterances without using any labels. We then perform few-shot intent detection together with supervised contrastive learning, which explicitly pulls utterances from the same intent closer and pushes utterances across different intents farther. Experimental results show that our proposed method achieves state-of-the-art performance on three challenging intent detection datasets under 5-shot and 10-shot 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
