Name: Wilfredo Martel
Type: User
Company: FullStack Developer | Semantic Search | NLP
Bio: I am a passionate student in Artificial Intelligence, specializing in semantic search, NLP, transformers, and bio-inspired algorithms.
Location: Ecuador
Blog: www.linkedin.com/in/wilfredomartel
Wilfredo Martel's Projects
Semantic Segmentation of Legal texts that labels sentences with one of 7 rhetorical roles.
Context-enhanced question answering, local setup. GPT4ALL, HuggingFace Embeddings model, FAISS, LangChain
Korean Sentence Embedding Repository
Contrast the performance and results between different vector model representations in a multi-classification problem.
Sentence Embeddings with BERT & XLNet Sentence FineTune
Sentence-USE: Universal Sentence Encoder with Siamese Architecture
SentenceBERT training - ALL Code
SGPT: GPT Sentence Embeddings for Semantic Search
Sistema de información académica
Tensorflow Implementation of Siamese Neural Network for Learning Sentence Similarity
Quick semantic search using Siamese-BERT encodings
Video categorization with customized versions of SlowFast
Lightweight SMTP connection pool with clustering support, wait/release mechanism, connection lifecycle management, eager/lazy loading pool with load balancing and auto-expiry policy support
Pretrain RoBERTa for Spanish from scratch and perform NER on Spanish documents
The project consists in the creation of an automatic classifier of clinical cases in Spanish, with associate each case with the corresponding ICD-10 code. The classifier was trained through deep learning with three variants of the BERT model, for processing Spanish text: Multilingual BERT, BETO and RuPERTa.
A tutorial about NLP technologies available for the Spanish language
Spanish Q&A System based on BERT fine-tuned on SQuAD
Spanish word embeddings computed with different methods and from different corpora
Corpus y modelos entrenados para NLP en Español
Spanish Word Embeddings computed from large corpora and different sizes using fastText.
SPECTER: Document-level Representation Learning using Citation-informed Transformers
SPLADE: sparse neural search (SIGIR21, SIGIR22)
Source Code for 'Spring Boot Persistence Best Practices' by Anghel Leonard
WebDAV mapping for Spring Boot - Use an API like a network drive, open data as files, edit and save them.
This repository is an example of a performance issue with spring websocket and rabbitmq
A distributed approximate nearest neighborhood search (ANN) library which provides a high quality vector index build, search and distributed online serving toolkits for large scale vector search scenario.
Spanish version of SQuAD 1.1 and 2.0 obtained via machine translation
Successfully leveraged a pretrained BERT Transformer model for developing a question answering system.
Word2Vec encodings based search engine for Stackoverflow questions
algorithms specialization coursera