Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userBootstrapping Large-Scale Fine-Grained Contextual Advertising Classifier from Wikipedia
Bootstraping مصنف الإعلانات السياقية المحبوس على نطاق واسع من ويكيبيديا
262
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يوفر الإعلان السياقي للمعلنين الفرصة لاستهداف السياق الأكثر صلة بإعلاناتهم. يجعل مجموعة متنوعة كبيرة من الموضوعات المحتملة تحديا للغاية لجمع وثائق التدريب لبناء نموذج تصنيف إشراف أو يؤلف قواعد مكتوبة للخبراء في نظام تصنيف قائم على القواعد. علاوة على ذلك، في التصنيف الفائق الحبيبات، غالبا ما تتداخل فئات مختلفة أو تعايشها، مما يجعل من الصعب تصنيفها بدقة. في هذا العمل، نقترح Wiki2CAT، وهي طريقة لمعالجة تصنيف نصي كبير الحجم من خلال النقر على الرسم البياني للفئة Wikipedia. يتم تعيين الفئات في تصنيف IAB أولا إلى فئة العقد في الرسم البياني. ثم يتم نشر الملصق عبر الرسم البياني للحصول على قائمة بمستندات Wikipedia المسمى للحث على نصوص النصوص. تعد الطريقة مثالية لمشاكل التصنيف واسعة النطاق لأنها لا تتطلب أي مستند يدويا أو قواعد يدويا أو كلمات أساسية. يتم قياس الطريقة المقترحة مع مختلف خطوط الأساس القائمة على التعلم والكلمات الرئيسية وتجسد أداء تنافسي على مجموعات البيانات المتوفرة للجمهور ومجموعة بيانات جديدة تحتوي على أكثر من 300 فئة واحدة من الفئات الجميلة.
Contextual advertising provides advertisers with the opportunity to target the context which is most relevant to their ads. The large variety of potential topics makes it very challenging to collect training documents to build a supervised classification model or compose expert-written rules in a rule-based classification system. Besides, in fine-grained classification, different categories often overlap or co-occur, making it harder to classify accurately. In this work, we propose wiki2cat, a method to tackle large-scaled fine-grained text classification by tapping on the Wikipedia category graph. The categories in the IAB taxonomy are first mapped to category nodes in the graph. Then the label is propagated across the graph to obtain a list of labeled Wikipedia documents to induce text classifiers. The method is ideal for large-scale classification problems since it does not require any manually-labeled document or hand-curated rules or keywords. The proposed method is benchmarked with various learning-based and keyword-based baselines and yields competitive performance on publicly available datasets and a new dataset containing more than 300 fine-grained categories.
References used
https://aclanthology.org/
rate research
Read More
We present the ongoing NorLM initiative to support the creation and use of very large contextualised language models for Norwegian (and in principle other Nordic languages), including a ready-to-use software environment, as well as an experience repo
rt for data preparation and training. This paper introduces the first large-scale monolingual language models for Norwegian, based on both the ELMo and BERT frameworks. In addition to detailing the training process, we present contrastive benchmark results on a suite of NLP tasks for Norwegian. For additional background and access to the data, models, and software, please see: http://norlm.nlpl.eu
We study the impact of using rich and diverse textual descriptions of classes for zero-shot learning (ZSL) on ImageNet. We create a new dataset ImageNet-Wiki that matches each ImageNet class to its corresponding Wikipedia article. We show that merely
employing these Wikipedia articles as class descriptions yields much higher ZSL performance than prior works. Even a simple model using this type of auxiliary data outperforms state-of-the-art models that rely on standard features of word embedding encodings of class names. These results highlight the usefulness and importance of textual descriptions for ZSL, as well as the relative importance of auxiliary data type compared to the algorithmic progress. Our experimental results also show that standard zero-shot learning approaches generalize poorly across categories of classes.
This paper illustrates our approach to the shared task on large-scale multilingual machine translation in the sixth conference on machine translation (WMT-21). In this work, we aim to build a single multilingual translation system with a hypothesis t
hat a universal cross-language representation leads to better multilingual translation performance. We extend the exploration of different back-translation methods from bilingual translation to multilingual translation. Better performance is obtained by the constrained sampling method, which is different from the finding of the bilingual translation. Besides, we also explore the effect of vocabularies and the amount of synthetic data. Surprisingly, the smaller size of vocabularies perform better, and the extensive monolingual English data offers a modest improvement. We submitted to both the small tasks and achieve the second place.
We use dialogue act recognition (DAR) to investigate how well BERT represents utterances in dialogue, and how fine-tuning and large-scale pre-training contribute to its performance. We find that while both the standard BERT pre-training and pretraini
ng on dialogue-like data are useful, task-specific fine-tuning is essential for good performance.
This paper describes TenTrans large-scale multilingual machine translation system for WMT 2021. We participate in the Small Track 2 in five South East Asian languages, thirty directions: Javanese, Indonesian, Malay, Tagalog, Tamil, English. We mainly
utilized forward/back-translation, in-domain data selection, knowledge distillation, and gradual fine-tuning from the pre-trained model FLORES-101. We find that forward/back-translation significantly improves the translation results, data selection and gradual fine-tuning are particularly effective during adapting domain, while knowledge distillation brings slight performance improvement. Also, model averaging is used to further improve the translation performance based on these systems. Our final system achieves an average BLEU score of 28.89 across thirty directions on the test set.
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
