Martin BoyanovLet’s Build Bg2Vec: Apply LLM2Vec on BgGPTWith the advent of RAG and text generation solutions, it is of utmost importance to have a model which can extract meaningful…3 min read·May 20, 2024----
Martin BoyanovK-means clustering for faster collaborative filteringThe classical collaborative filtering approach includes computing the cosine distance between all pairs of users or items. In the book…2 min read·Sep 11, 2021----
Martin BoyanovK-means Clustering for Vote AnalysisOn the 4th April 2021 we held elections in Bulgaria to choose the new parliament. This article will attempt to apply K-means clustering on…5 min read·May 16, 2021----
Martin Boyanov72 от сутрин до вечерНапоследък чета доста Edward Tufte в опити да си увелича data viz скиловете. Идеята е, че освен красиви, графиките трябва да са и полезни…3 min read·May 27, 2019----
Martin BoyanovinCommetricSemi-Frozen Embeddings for NLP Transfer LearningFinetuning only domain-specific words to reduce overfitting3 min read·Apr 19, 2019----
Martin BoyanovinCommetricDetecting Near-Duplicates in the NewsOverview and benchmark of data science methods for duplicate detection2 min read·Mar 21, 2019--1--1
Martin BoyanovForward & Backward Character Language Models for Conjoined Word Separation with fast.aiConjoined words are words that wrongly consist of two words. We’ll try to split them up to increase the data quality.4 min read·Dec 5, 2018--1--1
Martin BoyanovEmbeddings Transformations for Sentiment Lexicon EnrichmentThere exists a vector v, such that translating a negative word n by v leads to the vicinity of the antonym of n.4 min read·Sep 9, 2018----
Martin BoyanovinBecoming Human: Artificial Intelligence MagazineNeural Style TransferSurviving the Game Jam without artists5 min read·Feb 1, 2018----
