Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userExploring German Multi-Level Text Simplification
استكشاف التبسيط الألماني متعدد المستويات
220
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
نبلغ عن التجارب في تبسيط النص التلقائي (ATS) للألمانية مع مستويات تبسيط متعددة على طول الإطار الأوروبي المشترك المرجعي لغات (CEFR)، وتبسيط اللغة الألمانية القياسية إلى مستويات A1 و A2 و B1.لهذا الغرض، نحقق في استخدام تسميات المصدر وإحاطاء اللغة الألمانية القياسية، مما يسمح لنا بتبسيط اللغة القياسية إلى مستوى CEFR محدد.نظرا لأن هذه الأساليب فعالة بشكل خاص في سيناريوهات الموارد المنخفضة، حيث يمكننا أن نتفوق على خط الأساس المحول القياسي.علاوة على ذلك، نقدم نسخ ملصقات، والتي نظهرها يمكن أن تساعد النموذج في إجراء تمييز بين الجمل التي تتطلب مزيدا من التعديلات والجمل التي يمكن نسخها كما هو.
We report on experiments in automatic text simplification (ATS) for German with multiple simplification levels along the Common European Framework of Reference for Languages (CEFR), simplifying standard German into levels A1, A2 and B1. For that purpose, we investigate the use of source labels and pretraining on standard German, allowing us to simplify standard language to a specific CEFR level. We show that these approaches are especially effective in low-resource scenarios, where we are able to outperform a standard transformer baseline. Moreover, we introduce copy labels, which we show can help the model make a distinction between sentences that require further modifications and sentences that can be copied as-is.
References used
https://aclanthology.org/
rate research
Read More
The task of document-level text simplification is very similar to summarization with the additional difficulty of reducing complexity. We introduce a newly collected data set of German texts, collected from the Swiss news magazine 20 Minuten (20 Minu
tes') that consists of full articles paired with simplified summaries. Furthermore, we present experiments on automatic text simplification with the pretrained multilingual mBART and a modified version thereof that is more memory-friendly, using both our new data set and existing simplification corpora. Our modifications of mBART let us train at a lower memory cost without much loss in performance, in fact, the smaller mBART even improves over the standard model in a setting with multiple simplification levels.
Due to efficient end-to-end training and fluency in generated texts, several encoder-decoder framework-based models are recently proposed for data-to-text generations. Appropriate encoding of input data is a crucial part of such encoder-decoder model
s. However, only a few research works have concentrated on proper encoding methods. This paper presents a novel encoder-decoder based data-to-text generation model where the proposed encoder carefully encodes input data according to underlying structure of the data. The effectiveness of the proposed encoder is evaluated both extrinsically and intrinsically by shuffling input data without changing meaning of that data. For selecting appropriate content information in encoded data from encoder, the proposed model incorporates attention gates in the decoder. With extensive experiments on WikiBio and E2E dataset, we show that our model outperforms the state-of-the models and several standard baseline systems. Analysis of the model through component ablation tests and human evaluation endorse the proposed model as a well-grounded system.
Document-level event extraction is critical to various natural language processing tasks for providing structured information. Existing approaches by sequential modeling neglect the complex logic structures for long texts. In this paper, we leverage
the entity interactions and sentence interactions within long documents and transform each document into an undirected unweighted graph by exploiting the relationship between sentences. We introduce the Sentence Community to represent each event as a subgraph. Furthermore, our framework SCDEE maintains the ability to extract multiple events by sentence community detection using graph attention networks and alleviate the role overlapping issue by predicting arguments in terms of roles. Experiments demonstrate that our framework achieves competitive results over state-of-the-art methods on the large-scale document-level event extraction dataset.
Text simplification is a valuable technique. However, current research is limited to sentence simplification. In this paper, we define and investigate a new task of document-level text simplification, which aims to simplify a document consisting of m
ultiple sentences. Based on Wikipedia dumps, we first construct a large-scale dataset named D-Wikipedia and perform analysis and human evaluation on it to show that the dataset is reliable. Then, we propose a new automatic evaluation metric called D-SARI that is more suitable for the document-level simplification task. Finally, we select several representative models as baseline models for this task and perform automatic evaluation and human evaluation. We analyze the results and point out the shortcomings of the baseline models.
After the global financial crisis and the subsequent sovereign debt crisis that hit European economies in 2010, the German economy was able to recover faster than the others, achieving what has been called the "second German miracle". While some rese
archers had attributed this miracle to the monetary policy of the European Central Bank which is largely biased towards Germany (as the strongest economy in the region), others attributed it to the German economy’s reliance on the export sector and its successful strategy before and during the 2010 crisis. Accordingly, This study aimed to determine the extent of the contribution of the German export policy to achieve that miracle in order to extract some lessons. To this end, the impact of the export growth rate on the German economy has been analyzed since the outbreak of the European sovereign debt crisis in 2010 until the end of 2019; This is done by analyzing the changes in both the export growth rate and the main indicators of the German economy (growth, inflation, and unemployment rates) graphically and statistically depending on ARDL methodology in order to test the existence of a relationship in the long and short term.The research concluded that there was a significant effect of the export growth rate on growth and unemployment rates, while it didn’t have any effect on the inflation rates. That is, the German export-dependent growth model has relatively contributed to the recovery of the economy and the improvement of its indicators, depending on its export strategy on the one hand, the strength and resilience of the economy on the other hand, and on German’s benefit from the European crisis on the third hand.
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
