تعرض المحاضرة شرح عن علم البيانات وعلاقته بعلم الإحصاء والتعلم الآلي وحالتين دراسيتين عن دور عالم البيانات في تصميم حلول تعتمد على استخراج المعرفة من حجم كبير من البيانات المتوفرة, كما يتم عرض أهم المهام في المؤتمرات العلمية التي يمكن المشاركة بها لطلاب المعلوماتية المهتمين بهذا المجال
In recent years, time-critical processing or real-time processing and analytics of bid data have received a significant amount of attentions. There are many areas/domains where real-time processing of data and making timely decision can save thousand
s of human lives, minimizing the risks of human lives and resources, enhance the quality of human lives, enhance the chance of profitability, efficient resources management etc. This paper has presented such type of real-time big data analytic applications and a classification of those applications. In addition, it presents the time requirements of each type of these applications along with its significant benefits. Also, a general overview of big data to describe a background knowledge on this scope.
This paper explores three simple data manipulation techniques (synthesis, augmentation, curriculum) for improving abstractive summarization models without the need for any additional data. We introduce a method of data synthesis with paraphrasing, a
data augmentation technique with sample mixing, and curriculum learning with two new difficulty metrics based on specificity and abstractiveness. We conduct experiments to show that these three techniques can help improve abstractive summarization across two summarization models and two different small datasets. Furthermore, we show that these techniques can improve performance when applied in isolation and when combined.
This survey/position paper discusses ways to improve coverage of resources such as WordNet. Rapp estimated correlations, rho, between corpus statistics and pyscholinguistic norms. rho improves with quantity (corpus size) and quality (balance). 1M wor
ds is enough for simple estimates (unigram frequencies), but at least 100x more is required for good estimates of word associations and embeddings. Given such estimates, WordNet's coverage is remarkable. WordNet was developed on SemCor, a small sample (200k words) from the Brown Corpus. Knowledge Graph Completion (KGC) attempts to learn missing links from subsets. But Rapp's estimates of sizes suggest it would be more profitable to collect more data than to infer missing information that is not there.
We present a systematic study on multilingual and cross-lingual intent detection (ID) from spoken data. The study leverages a new resource put forth in this work, termed MInDS-14, a first training and evaluation resource for the ID task with spoken d
ata. It covers 14 intents extracted from a commercial system in the e-banking domain, associated with spoken examples in 14 diverse language varieties. Our key results indicate that combining machine translation models with state-of-the-art multilingual sentence encoders (e.g., LaBSE) yield strong intent detectors in the majority of target languages covered in MInDS-14, and offer comparative analyses across different axes: e.g., translation direction, impact of speech recognition, data augmentation from a related domain. We see this work as an important step towards more inclusive development and evaluation of multilingual ID from spoken data, hopefully in a much wider spectrum of languages compared to prior work.
Pre-trained neural language models give high performance on natural language inference (NLI) tasks. But whether they actually understand the meaning of the processed sequences is still unclear. We propose a new diagnostics test suite which allows to
assess whether a dataset constitutes a good testbed for evaluating the models' meaning understanding capabilities. We specifically apply controlled corruption transformations to widely used benchmarks (MNLI and ANLI), which involve removing entire word classes and often lead to non-sensical sentence pairs. If model accuracy on the corrupted data remains high, then the dataset is likely to contain statistical biases and artefacts that guide prediction. Inversely, a large decrease in model accuracy indicates that the original dataset provides a proper challenge to the models' reasoning capabilities. Hence, our proposed controls can serve as a crash test for developing high quality data for NLI tasks.