Towards energy aware object-oriented development of android applications

Sahar, Hareem; Bangash, Abdul Ali; Beg, Mirza Omer

doi:10.1016/j.suscom.2018.10.005

Cited by 15 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This section explains the data gathering (Sahar et al, 2019) process and the preprocessing steps applied to transform the data in a suitable form to enable the pretraining cycles of BERT and multlingual BERT (Qamar et al).…”

Section: Datasetmentioning

confidence: 99%

RUBERT: A Bilingual Roman Urdu BERT Using Cross Lingual Transfer Learning

Khalid,

Beg,

Arshad

2021

Preprint

View full text Add to dashboard Cite

In recent studies it has been shown that Multilingual language models under perform their monolingual counterparts (Conneau et al., 2020). It is also a well known fact that training and maintaining monolingual models for each language is a costly and time consuming process. Roman Urdu is a resource starved language used popularly on social media platforms and chat apps. In this research we propose a novel dataset of scraped tweets containing 54M tokens and 3M sentences. Additionally we also propose RUBERT a bilingual Roman Urdu model created by additional pretraining of English BERT (Devlin et al., 2019). We compare its performance with a monolingual Roman Urdu BERT trained from scratch and a multilingual Roman Urdu BERT created by additional pretraining of Multilingual BERT (mBERT (Devlin et al., 2019)). We show through our experiments that additional pretraining of the English BERT produces the most notable performance improvement.

show abstract

Section: Datasetmentioning

confidence: 99%

RUBERT: A Bilingual Roman Urdu BERT Using Cross Lingual Transfer Learning

Khalid,

Beg,

Arshad

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In [12] they have presented a method level energy estimation MELTA for android applications to compute the energy consumed by android applications. [27] has proposed a methodology for computation of energy consumption by structural information related to energy consumption. As Energy is one of the main concerns of the developers these days.…”

Section: Related Workmentioning

confidence: 99%

Urdu Handwritten Text Recognition Using ResNet18

Kashif

2021

Preprint

View full text Add to dashboard Cite

Handwritten text recognition is an active research area in the field of deep learning and artificial intelligence to convert handwritten text into machine-understandable. A lot of work has been done for other languages, especially for English, but work for the Urdu language is very minimal due to the cursive nature of Urdu characters. The need for Urdu HCR systems is increasing because of the advancement of technology. In this paper, we propose a ResNet18 model for handwritten text recognition using Urdu Nastaliq Handwritten Dataset (UNHD) which contains 3,12000 words written by 500 candidates.

show abstract

“…To handle ambiguity in document titles NSMN [45] technique is used. These ambiguous documents amount to about 10% of all documents for a particular claim [50]. Documents with unambiguous titles are therefore allotted higher scores.…”

Section: Evidence Sentence Selectionmentioning

confidence: 99%

Few Shot Learning for Information Verification

Khalid,

Beg

2021

Preprint

View full text Add to dashboard Cite

Information verification is quite a challenging task, this is because many times verifying a claim can require picking pieces of information from multiple pieces of evidence which can have a hierarchy of complex semantic relations. Previously a lot of researchers have mainly focused on simply concatenating multiple evidence sentences to accept or reject claims. These approaches are limited as evidence can contain hierarchical information and dependencies. In this research, we aim to verify facts based on evidence selected from a list of articles taken from Wikipedia. Pretrained language models such as XLNET are used to generate meaningful representations and graph-based attention and convolutions are used in such a way that the system requires little additional training to learn to verify facts.

show abstract

Towards energy aware object-oriented development of android applications

Cited by 15 publications

References 11 publications

RUBERT: A Bilingual Roman Urdu BERT Using Cross Lingual Transfer Learning

RUBERT: A Bilingual Roman Urdu BERT Using Cross Lingual Transfer Learning

Urdu Handwritten Text Recognition Using ResNet18

Few Shot Learning for Information Verification

Contact Info

Product

Resources

About