Search

Applying DevOps practices to machine learning system is termed as MLOps and machine learning systems evolve on new data unlike traditional systems on requirements. The objective of MLOps is to establish a connection between different open-source tools to construct a pipeline that can automatically perform steps to construct a dataset, train the machine learning model and deploy the model to the production as well as store different versions of model and dataset. Benefits of MLOps is to make sure the fast delivery of the new trained models to the production to have accurate results. Furthermore, MLOps practice impacts the overall quality of the software products and is completely dependent on open-source tools and selection of relevant open-source tools is considered as challenged while a generalized method to select an appropriate open-source tools is desirable. In this paper, we present a framework for recommendation system that processes the contextual information (e.g., nature of data, type of the data) of the machine learning project and recommends a relevant toolchain (tech-stack) for the operationalization of machine learning systems. To check the applicability of the proposed framework, four different approaches i.e., rule-based, random forest, decision trees and k-nearest neighbors were investigated where precision, recall and f-score is measured, the random forest out classed other approaches with highest f-score value of 0.66.

Measuring empathy in conversation can be challenging, as empathy is a complex and multifaceted psychological construct that involves both cognitive and emotional components. Human evaluations can be subjective, leading to inconsistent results. Therefore, there is a need for an automatic method for measuring empathy that reduces the need for human evaluations. In this paper, we proposed a novel approach EMP-EVAL, a simple yet effective automatic empathy evaluation method. The proposed technique takes the influence of Emotion, Cognitive and Emotional empathy. To the best knowledge, our work is the first to systematically measure empathy without the human-annotated provided scores. Experimental results demonstrate that our metrics can correlate with human preference, achieving comparable results with human judgments., Comment: 7 pages, 5 figures, 4 tables

In recent studies, it has been shown that Multilingual language models underperform their monolingual counterparts. 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. 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. We show through our experiments that additional pretraining of the English BERT produces the most notable performance improvement., Comment: arXiv admin note: substantial text overlap with arXiv:2102.10958

Urdu is a widely spoken language in South Asia. Though immoderate literature exists for the Urdu language still the data isn't enough to naturally process the language by NLP techniques. Very efficient language models exist for the English language, a high resource language, but Urdu and other under-resourced languages have been neglected for a long time. To create efficient language models for these languages we must have good word embedding models. For Urdu, we can only find word embeddings trained and developed using the skip-gram model. In this paper, we have built a corpus for Urdu by scraping and integrating data from various sources and compiled a vocabulary for the Urdu language. We also modify fasttext embeddings and N-Grams models to enable training them on our built corpus. We have used these trained embeddings for a word similarity task and compared the results with existing techniques.

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.

Pretrained language models are now of widespread use in Natural Language Processing. Despite their success, applying them to Low Resource languages is still a huge challenge. Although Multilingual models hold great promise, applying them to specific low-resource languages e.g. Roman Urdu can be excessive. In this paper, we show how the code-switching property of languages may be used to perform cross-lingual transfer learning from a corresponding high resource language. We also show how this transfer learning technique termed Bilingual Language Modeling can be used to produce better performing models for Roman Urdu. To enable training and experimentation, we also present a collection of novel corpora for Roman Urdu extracted from various sources and social networking sites, e.g. Twitter. We train Monolingual, Multilingual, and Bilingual models of Roman Urdu - the proposed bilingual model achieves 23% accuracy compared to the 2% and 11% of the monolingual and multilingual models respectively in the Masked Language Modeling (MLM) task.

Privacy Policies are the legal documents that describe the practices that an organization or company has adopted in the handling of the personal data of its users. But as policies are a legal document, they are often written in extensive legal jargon that is difficult to understand. Though work has been done on privacy policies but none that caters to the problem of verifying if a given privacy policy adheres to the data protection laws of a given country or state. We aim to bridge that gap by providing a framework that analyzes privacy policies in light of various data protection laws, such as the General Data Protection Regulation (GDPR). To achieve that, firstly we labeled both the privacy policies and laws. Then a correlation scheme is developed to map the contents of a privacy policy to the appropriate segments of law that a policy must conform to. Then we check the compliance of privacy policy's text with the corresponding text of the law using NLP techniques. By using such a tool, users would be better equipped to understand how their personal data is managed. For now, we have provided a mapping for the GDPR and PDPA, but other laws can easily be incorporated in the already built pipeline.

Graphics Processing Units (GPUs) were once used solely for graphical computation tasks but with the increase in the use of machine learning applications, the use of GPUs to perform general-purpose computing has increased in the last few years. GPUs employ a massive amount of threads, that in turn achieve a high amount of parallelism, to perform tasks. Though GPUs have a high amount of computation power, they face the problem of cache contention due to the SIMT model that they use. A solution to this problem is called "cache bypassing". This paper presents a predictive model that analyzes the access patterns of various machine learning algorithms and determines whether certain data should be stored in the cache or not. It presents insights on how well each model performs on different datasets and also shows how minimizing the size of each model will affect its performance The performance of most of the models were found to be around 90% with KNN performing the best but not with the smallest size. We further increase the features by splitting the addresses into chunks of 4 bytes. We observe that this increased the performance of the neural network substantially and increased the accuracy to 99.9% with three neurons.