Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userWikiNEuRal: Combined Neural and Knowledge-based Silver Data Creation for Multilingual NER
Wikineural: مجتمعة خلق بيانات الفضة المصنوعة من الفضة العصبي والمعرفة لتعدد اللغات
123
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
التعرف على الكيان المسمى متعدد اللغات (NER) هي مهمة متوسطة رئيسية مطلوبة في العديد من مجالات NLP.في هذه الورقة، نتعلم القضية المعروفة من ندرة البيانات في NER، خاصة ذات الصلة عند الانتقال إلى سيناريو متعدد اللغات، وتتجاوز النهج الحالية لإنشاء بيانات فضية متعددة اللغات للمهمة.نستفصل نصوص ويكيبيديا وإدخال منهجية جديدة تستند إلى المزيج الفعال من الأساليب القائمة على المعرفة والنماذج العصبية، إلى جانب تقنية تكيف مجال الرواية، لإنتاج شركة تدريبية عالية الجودة ل NER.نقوم بتقييم مجموعات البيانات الخاصة بنا على نطاق واسع على المعايير القياسية الخاصة ب NER، مما يؤدي إلى تحسينات كبيرة تصل إلى 6 نقاط F1-Score تستند إلى 6 نقاط على أنظمة الحالة السابقة لإنشاء البيانات.
Multilingual Named Entity Recognition (NER) is a key intermediate task which is needed in many areas of NLP. In this paper, we address the well-known issue of data scarcity in NER, especially relevant when moving to a multilingual scenario, and go beyond current approaches to the creation of multilingual silver data for the task. We exploit the texts of Wikipedia and introduce a new methodology based on the effective combination of knowledge-based approaches and neural models, together with a novel domain adaptation technique, to produce high-quality training corpora for NER. We evaluate our datasets extensively on standard benchmarks for NER, yielding substantial improvements up to 6 span-based F1-score points over previous state-of-the-art systems for data creation.
References used
https://aclanthology.org/
rate research
Read More
Most of the previous Rhetorical Structure Theory (RST) parsing methods are based on supervised learning such as neural networks, that require an annotated corpus of sufficient size and quality. However, the RST Discourse Treebank (RST-DT), the benchm
ark corpus for RST parsing in English, is small due to the costly annotation of RST trees. The lack of large annotated training data causes poor performance especially in relation labeling. Therefore, we propose a method for improving neural RST parsing models by exploiting silver data, i.e., automatically annotated data. We create large-scale silver data from an unlabeled corpus by using a state-of-the-art RST parser. To obtain high-quality silver data, we extract agreement subtrees from RST trees for documents built using the RST parsers. We then pre-train a neural RST parser with the obtained silver data and fine-tune it on the RST-DT. Experimental results show that our method achieved the best micro-F1 scores for Nuclearity and Relation at 75.0 and 63.2, respectively. Furthermore, we obtained a remarkable gain in the Relation score, 3.0 points, against the previous state-of-the-art parser.
Porous glasses were produced using sheet glass cullet with added
magnesium carbonate MgCO3 as foams agents .The structure of glasses
tinged with silver bromide by porous glasses, was studied by UV–VIS
spectroscopy,transmission of light and X-ray diffraction XRD
techniques. glasses plates were obtained by impregnation of porous
glasses at first with AgNO3 aqueous solution , next in the KBr aqueous
solution. Then the samples was sintered at temperatures 950°C up to
closing of the pores. The results of spectroscopy study have shown that
the glasses tinged plates, according to XRD data, the glasses tinged
contain the AgBr phase.
In most of neural machine translation distillation or stealing scenarios, the highest-scoring hypothesis of the target model (teacher) is used to train a new model (student). If reference translations are also available, then better hypotheses (with
respect to the references) can be oversampled and poor hypotheses either removed or undersampled. This paper explores the sampling method landscape (pruning, hypothesis oversampling and undersampling, deduplication and their combination) with English to Czech and English to German MT models using standard MT evaluation metrics. We show that careful oversampling and combination with the original data leads to better performance when compared to training only on the original or synthesized data or their direct combination.
In this study we used electro spinning technology to obtain
nonwoven webs of Nano fibers of poly vinyl alcohol and Nano
particles of silver . we dissolve the polymer poly vinyl alcohol in
it's solvent (water) to form a polymeric solution that we c
harged it
by positive charge and ejected it to leaving it on a collector that
we charged it by negative charge and used a high voltage. and
we mixed the polymer poly vinyl alcohol with silver nitrate with
different concentrations and electro spinning the mixture to obtain
Nano fibers and Nano particles of silver then we applied heat
treatment for the whole samples at 155°c for 5 minutes for tow
aims the first one is to make crosslinking between series of PVA
and the second is for the stability of silver nanoparticles , finally
we analyze samples on Scanning Electron Microscopy SEM .
Silver nano- particles (NPs) are used in many fields because of
their unique electrical, optical, chemical and biological (antibacterial)
properties. Recently, inkjet technology has been used
to produce flexible electronic circuit at low cost.
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
