Skip to main content

Posts

Document Vector Estimation using Partition Word Vector Averaging

Averaging vs Partition Averaging TLDR;  This post discusses my NLP research work on representing documents by weighted partition word vectors averaging . (15-minute read) tags: document representation, partition word vectors averaging Prologue Let's consider a corpus (C) with N documents with the corresponding most frequent words vocabulary (V). Figure1 represents the word-vectors space of V, where similar meaning words occur closer to each other (a partition of word vocabulary based on word vector similarity).  Few words are polysemic and belong to multiple topics with some proportion. In figure 1 we represent the topic number of the word in subscript and corresponding proportion in braces. Figure 1: Corpus C-word vocabulary partitioned using word2vec fuzzy clustering  Let's consider a text document (d):  "Data journalists deliver data science news to the general public. They often take part in interpreting the data m...
Recent posts

Special Interest Group Machine Learning, IIT Kanpur (SIGML)

With the current surge in attempts to emulate human "intelligence", the importance of Machine Learning cannot be downplayed in any way. Machine Learning is the science of creating algorithms that are adaptive to data features. In simpler terms, it involves algorithms that change itself according to the data it is presented with. Take, for example, the "familiar" task of recommending products to users on an e-commerce site. A very popular approach is to study user data and find other users similar to you and then recommend the products they have looked at, to you. It is essentially identifying similar users but it adapts itself to extract the "important" features in the user data. To achieve this, the algorithm must be able to identify what is important, extract hidden features (eg. pattern in the sequence of page visits) etc. This is where Machine Learning comes in. Machine Learning, today, is immensely capable of diving "deep" into hug...

My Internship Experience: Flipkart

Hi everyone! I am Vivek Gupta and I interned with Flipkart this summer in Bangalore and I wouldn’t be exaggerating if I said those were some truly awesome months. Hence, here goes my attempt to share some of those moments with you ! It was 9:30 AM, 21st of May. I had just stepped into Flipkart’s office at Mantri Commercial, Bangalore. I was familiar with the pleasant weather and insane traffic of Bangalore, as I have worked as an intern in this city in past. Confused about which building to enter among the two, I decided to call the HR assigned to me. She guided me to the right place - Tower B, 3rd floor. She asked me to wait over there. After half an hour, I saw other students entering. I enjoy having conversations with new people, and so I went ahead to speak with them. I got to know they were my co-interns from various colleges including - BITS Pilani, BITS Hyderabad, IISC Bangalore, IIT KGP and IIT Bombay. Soon, the HR arrived again and after completing some formalities, we...