Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userCrisisBERT: a Robust Transformer for Crisis Classification and Contextual Crisis Embedding
170
0
0.0
(
0
)
Added by
Junhua Liu
Publication date
2020
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Classification of crisis events, such as natural disasters, terrorist attacks and pandemics, is a crucial task to create early signals and inform relevant parties for spontaneous actions to reduce overall damage. Despite crisis such as natural disasters can be predicted by professional institutions, certain events are first signaled by civilians, such as the recent COVID-19 pandemics. Social media platforms such as Twitter often exposes firsthand signals on such crises through high volume information exchange over half a billion tweets posted daily. Prior works proposed various crisis embeddings and classification using conventional Machine Learning and Neural Network models. However, none of the works perform crisis embedding and classification using state of the art attention-based deep neural networks models, such as Transformers and document-level contextual embeddings. This work proposes CrisisBERT, an end-to-end transformer-based model for two crisis classification tasks, namely crisis detection and crisis recognition, which shows promising results across accuracy and f1 scores. The proposed model also demonstrates superior robustness over benchmark, as it shows marginal performance compromise while extending from 6 to 36 events with only 51.4% additional data points. We also proposed Crisis2Vec, an attention-based, document-level contextual embedding architecture for crisis embedding, which achieve better performance than conventional crisis embedding methods such as Word2Vec and GloVe. To the best of our knowledge, our works are first to propose using transformer-based crisis classification and document-level contextual crisis embedding in the literature.
rate research
Read More
The role of social media, in particular microblogging platforms such as Twitter, as a conduit for actionable and tactical information during disasters is increasingly acknowledged. However, time-critical analysis of big crisis data on social media streams brings challenges to machine learning techniques, especially the ones that use supervised learning. The Scarcity of labeled data, particularly in the early hours of a crisis, delays the machine learning process. The current state-of-the-art classification methods require a significant amount of labeled data specific to a particular event for training plus a lot of feature engineering to achieve best results. In this work, we introduce neural network based classification methods for binary and multi-class tweet classification task. We show that neural network based models do not require any feature engineering and perform better than state-of-the-art methods. In the early hours of a disaster when no labeled data is available, our proposed method makes the best use of the out-of-event data and achieves good results.
In this work we suggest a simple theoretical model of the proton able to effectively solve proton spin crisis. Within domain of applicability of this simple model proton consists only of two u quarks and one d quarks (two of which have spin opposite to proton and one identical to proton) and one neutral vector phi meson (with spin two times larger than proton spin and directed identically to proton spin). This model is in full agreement not only with existing DIS experiments, but also with spin and electric charge conservation as well as in a satisfactory agreement with rest mass-energy conservation (since phi meson mass is close to proton rest mass). Our model opens an interesting possibility of the solution of the quarks and leptons families problem (proton is not an absolutely non-strange particle, but only a particle with almost totally effectively hidden strange). Also we suggest a possible first step toward the solution of the supersymmetry crisis using so-called superexclusion principle. According to this principle usual particles (electron, neutrino,...) can exist actually and virtually, while their supersymmetric partners, s-particles (selectron, neutralino, ...) can exist (super)exclusively virtually but not actually.
Crises such as natural disasters, global pandemics, and social unrest continuously threaten our world and emotionally affect millions of people worldwide in distinct ways. Understanding emotions that people express during large-scale crises helps inform policy makers and first responders about the emotional states of the population as well as provide emotional support to those who need such support. We present CovidEmo, ~1K tweets labeled with emotions. We examine how well large pre-trained language models generalize across domains and crises in the task of perceived emotion prediction in the context of COVID-19. Our results show that existing models do not directly transfer from one disaster type to another but using labeled emotional corpora for domain adaptation is beneficial.
The so-called textit{China crisis}, well documented in textit{History of the IAU} by Adriaan Blaauw and in textit{Under the Same Starry Sky: History of the IAU} by Chengqi Fu and Shuhua Ye, refers to the withdrawal in 1960 of the Peoples Republic of China (PRC) from the Union. The crisis stemmed from the admission by the IAU, amidst strong protest from PRC and some other member countries, of the Republic of China (ROC) to the Union, creating the so-called `textit{Two Chinas} -- or `textit{One China, one Taiwan} problem. The crisis directly led to the absence of mainland Chinese astronomers from the stage of international collaborations and exchanges, and was only solved two decades later. The solution, accepted by all the parties involved, is that China is to have two adhering organizations, with mainland China astronomers represented by the Chinese Astronomical Society located in Nanjing (China Nanjing) and China Taiwan astronomers represented by the Academia Sinica located in Taipei (China Taipei). The denominations `textit{China Nanjing} and `textit{China Taipei} represent the IAU official resolution and should be used in all IAU events. The China crisis, probably the most serious one in IAU history, was a painful lesson in the 100-year development of the Union. Yet, with its eventual solution, the Union has emerged stronger, upholding its spirit of promoting astronomical development through international collaboration of astronomers from all regions and countries, regardless of the political systems, religion, ethnicity, gender or level of astronomical development.
Astronomers in CANDELS outline changes for the academic system to promote a smooth transition for junior scientists from academia to industry.
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
