Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userLarge-Scale Zero-Shot Image Classification from Rich and Diverse Textual Descriptions
تصنيف الصورة صفرية على نطاق واسع من الأوصاف النصية الغنية والمتنوعة
185
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
ندرس تأثير استخدام الأوصاف النصية الغنية والمتنوعة من الفصول الدراسية للتعلم الصفرية (ZSL) على ImageNet.نقوم بإنشاء مجموعة بيانات جديدة Imagenet-Wiki التي تتطابق مع كل فئة Imagenet إلى مقالها في ويكيبيديا المقابل.نظهر أن استخدام هذه المقالات في ويكيبيديا فقط كصامإصاف فئة يؤدي إلى ارتفاع أداء ZSL أعلى بكثير من الأعمال السابقة.حتى نموذج بسيط باستخدام هذا النوع من البيانات المساعدة تفوق النماذج الحديثة التي تعتمد على ميزات قياسية من Word تضمين ترميزات أسماء الفئة.تسليط الضوء على هذه النتائج فائدة وأهمية الأوصاف النصية ل ZSL، بالإضافة إلى الأهمية النسبية لنوع البيانات الإضافية مقارنة بالتقدم المحرز في الخوارزمية.تظهر نتائجنا التجريبية أيضا أن نهج التعلم المعيارية بالرصاص المعيارية تعميم بشكل سيء عبر فئات الطبقات.
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.
References used
https://aclanthology.org/
rate research
Read More
Large-Scale Multi-Label Text Classification (LMTC) includes tasks with hierarchical label spaces, such as automatic assignment of ICD-9 codes to discharge summaries. Performance of models in prior art is evaluated with standard precision, recall, and
F1 measures without regard for the rich hierarchical structure. In this work we argue for hierarchical evaluation of the predictions of neural LMTC models. With the example of the ICD-9 ontology we describe a structural issue in the representation of the structured label space in prior art, and propose an alternative representation based on the depth of the ontology. We propose a set of metrics for hierarchical evaluation using the depth-based representation. We compare the evaluation scores from the proposed metrics with previously used metrics on prior art LMTC models for ICD-9 coding in MIMIC-III. We also propose further avenues of research involving the proposed ontological representation.
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 classifica
tion 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.
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
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.
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
