RSSAmplifier

Blog

Peshmerge Morad

Cogito ergo sum

peshmerge.ioRSS feed ↗10 posts

Latest posts

My first lecture: What Python (and a student) taught me

I have been programming for 20 years. I write Python every single day for my job. So when I had to give my first ever lecture on Python basics, I thought: "How hard can this be?" Turns out, pretty hard.

How to solve the problem of mounting NTFS partitions on Ubuntu 22.04

Background In the previous post, I explained how I could restore all my files from a lost/wasted NTFS partition after trying to solve its mounting problem using fdisk. After restoring all files, I have formatted the partition and performed a chkdsk to ensure there are no errors. Then I booted into Ubuntu and tried to [ ]

How to restore a lost SSD/HDD partition with its folders structure using TestDisk on Windows 11

Background As you know, I use a dual-boot setup with Windows and Ubuntu. While I spend 95% of my time on Ubuntu Linux for development and daily tasks, I occasionally need Windows for specific purposes. This setup offers great flexibility but often comes with challenges, especially when mounting other partitions on my SSD in Ubuntu [ ]

Bibliography, References and Citations management for WordPress

Background As an ML researcher, I wanted to publish my work on this website, which is powered by WordPress. Publishing research means writing content with references and providing a bibliography at the end of your article. Therefore, you would need a powerful tool to make the re-publishing of the content easier. What I mean is [ ]

(Northern) Kurdish Linguistic Features – The Construct Case (Izafe)

In this post, we continue what we have started in the previous post. Now, we handle, the Construct Case (Izafe) in Northern Kurdish. The Construct Case (Izafe) The construct case, often referred to as the construct state, represents a grammatical phenomenon in some languages that occurs mostly in a noun phrase where a noun or [ ]

(Northern) Kurdish Linguistic Features

In the previous post, we gave an overview of the Kurdish language, its dialects, and the prevalent differences between the two main dialects. Before we delve deeper into more specific linguistic features, it is important to give an overview of nouns and their definitions in Northern Kurdish. Noun in Northern Kurdish The Nominative case Noun [ ]

Kurdish Language

Background The Kurdish language belongs to the Northwestern Iranic branch within the Indo-European languages family, spoken by more than 30 million people. People who speak the Kurdish language are called Kurds or Kurdish people \cite{ahmadi2019towards, ahmadi2020klpt, thackston2006kurmanji, ashti2021brief}. The Kurds are the world s largest ethnic group without a state of their own; they live in…

Tokenization & Part-of-Speech Tagging Evaluation Methods

Regardless of the employed tokenization and POS tagging methods, the evaluation of those methods can be expressed statistically using predefined evaluation metrics. The notion of evaluation in the context of POS tagging means evaluating the performance of a POS tagger by comparing its output to a ground truth or a gold standard. Both the output [ ]

Tokenization & its Methods

Just as part-of-speech tagging serves as a precursor for tasks like syntactic parsing, tokenization is a crucial task in NLP, and it is a prerequisite for POS tagging. Tokenization is the process of segmenting the input text into smaller, distinct units termed tokens. These tokens can encompass compound words, single words, sub-words, symbols, or other [ ]

Part-of-Speech Tagging & its Methods (5)

The Transformer The Transformer \cite{vaswani2017attention} was introduced in 2017 as the first sequence transduction model wholly based on self-attention. Transformers can be seen as a replacement for recurrent layers used in encoder-decoder architectures. They are the most robust approach for solving sequence-to-sequence tasks while handling long-range dependencies. In addition, the utilization…