Evaluation of Summarization Tasks using Sentence Bert

A semantic search engine prototype, made with SentenceBERT, ontological definitions, and full-text search.

Classification pipeline based on sentenceTransformer and Facebook nearest-neighbor search library

Usage of BERT models for text clustering techniques using sentence embeddings

Initially implement Document-Retrieval-System with SBERT embeddings and evaluate it in CORD-19 dataset. Afterwards, fine tune BERT model with SQuAD.v2 dataset so as to evaluate it in Question Answering task.

This project is about developing a document retrieval system to return titles of scientific papers containing the answer to a given user question. Two different sentence embedding approaches have been implemented and compared.

Projects for the Artificial Intelligence 2 course at the University of Athens.

Sentence Bert for Question-Answering on COVID-19 Open Research Dataset (CORD-19)

Datasets and models for medical concept normalization (MCN) in English and German. Results of Bachelor Thesis about MCN using BERT / SBERT.

Build and train state-of-the-art natural language processing models using BERT

Плагин для SmartApp Framework, осуществляющий векторизацию (получение embedding'ов) текстов с помощью различных моделей

Linux manual search shell with natural language

In this project, I use sentence embeddings to identify question pairs

Generación de contestaciones a partir de la aproximación de sus preguntas

Built a news topic classification model using pre trained sentence BERT model and traditional ML models. Sentence bert is used to generate sentence embedding and sbert embedding are used to train various ML models.Achieved an accuracy of 94.3% using SVM and Sbert model.

Heterogenous, Task- and Domain-Specific Benchmark for Unsupervised Sentence Embeddings used in the TSDAE paper: https://arxiv.org/abs/2104.06979.

KoBERTopic은 BERTopic을 한국어 데이터에 적용할 수 있도록 토크나이저와 BERT를 수정한 코드입니다.

🗂️ A document retrieval system on CORD-19 dataset

Building a model to recognize incentives for landscape restoration in environmental policies from Latin America, the US and India. Bringing NLP to the world of policy analysis through an extensible framework that includes scraping, preprocessing, active learning and text analysis pipelines.

patent-sberta training with triplet data