bjascob / amrlib

#自然语言处理#PYthon Automated Term Extraction

#计算机科学#The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

#自然语言处理#AMR Parsing as Sequence-to-Graph Transduction

#自然语言处理#Library for clinical NLP with spaCy.

spaCy REST API, wrapped in a Docker container.

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

#自然语言处理#Language, Knowledge, Cognition

A spaCy wrapper of OpenTapioca for named entity linking on Wikidata

#自然语言处理#SoTA Abstract Meaning Representation (AMR) parsing with word-node alignments in Pytorch. Includes checkpoints and other tools such as statistical significance Smatch.

#大语言模型#Retrieval and Retrieval-augmented LLMs

#自然语言处理#FACTUAL benchmark dataset, the pre-trained textual scene graph parser trained on FACTUAL.

#自然语言处理#SpanMarker for Named Entity Recognition

#计算机科学#LAVIS - A One-stop Library for Language-Vision Intelligence

A new codebase for popular Scene Graph Generation methods (2020). Visualization & Scene Graph Extraction on custom images/datasets are provided. It's also a PyTorch implementation of paper “Unbiased S...

#自然语言处理#Full text geoparsing as a Python library

#大语言模型#Open Interpreter（开放解释器） 可以让大语言模型（LLMs）在本地运行代码（比如 Python、JavaScript、Shell 等）。安装后，在终端上运行 $ interpreter 即可通过类似 ChatGPT 的界面与 Open Interpreter 聊天。