yurikim2145 Goto Github PK

bert-as-service

Mapping a variable-length sentence to a fixed-length vector using BERT model

bert-korean-model

BERT with SentencePiece for Korean text

bert-vocab-builder

Builds wordpiece(subword) vocabulary compatible for Google Research's BERT

bond

BOND: BERT-Assisted Open-Domain Name Entity Recognition with Distant Supervision

bros

champollion

Import of https://sourceforge.net/projects/champollion

crawling_patents_from_kipris

dependency-paraphraser

A sentence paraphraser based on dependency parsing and word embedding similarity.

econlab-patent-network-centrality

Python code to generate network of patents over time and to process the centrality measures of the network.

fasttext

Library for fast text representation and classification.

glove

GloVe model for distributed word representation

is-bert

An Unsupervised Sentence Embedding Method by Mutual Information Maximization (EMNLP2020)

kipris-patent-downloader

downloading patent list from kipris using python

kobert

Korean BERT pre-trained cased (KoBERT)

korean-ocr-model-design-based-on-keras-cnn

Korean OCR Model Design(한글 OCR 모델 설계)

mastering-spacy

Mastering spaCy, published by Packt

muse

A library for Multilingual Unsupervised or Supervised word Embeddings

named-entity-recognition-bidirectionallstm-cnn-conll

Keras implementation of "Few-shot Learning for Named Entity Recognition in Medical Text"

naverblog_crawler_nlp

네이버 특정 검색어 블로그 내용 크롤러 & 자연어 처리

nlp-with-pytorch

<파이토치로 배우는 자연어 처리>(한빛미디어, 2021)의 소스 코드를 위한 저장소입니다.

nltk

NLTK Source

para-kor

Create paraphrasing korean sentence with GPT-3

paraphrase-generator

A paraphrase generator built using the T5 model which produces paraphrased English sentences.

paraphrasepy

Paraphrasing English Sentences

paraphraser

Sentence paraphrase generation at the sentence level

paraphraser-1

Tool to generate paraphrases of sentences in many languages.

parrot_paraphraser

A practical and feature-rich paraphrasing framework to augment human intents in text form to build robust NLU models for conversational engines. Created by Prithiviraj Damodaran. Open to pull requests and other forms of collaboration.

patentbigdataanalysis

South Korea internship - USPTO bibliographical data extraction

patentscope-database

Here we extract all patents database from 1990 to current year by type, country and institution

sentence-transformers

Multilingual Sentence & Image Embeddings with BERT