Open-source alternatives to TextEE

This project is a comprehensive machine learning interview guide and technical study resource designed for individuals preparing for machine learning and AI engineering roles. It provides a collection of materials and practice problems covering core algorithms, theoretical fundamentals, and the implementation of neural network architectures. The resource serves as a technical reference for generative AI development, focusing on the design and optimization of large language models and diffusion systems. It includes frameworks for system design, covering the architecture of production machine l

Boxmot is a multi-object tracking framework designed to follow multiple objects across video frames using motion and appearance algorithms to maintain consistent identities. It functions as a system for tracking objects with specific orientations using rotated bounding boxes and corresponding intersection-over-union computations. The project includes a re-identification model optimizer that converts neural networks into formats for hardware-accelerated execution. It also features an evolutionary hyperparameter tuner that iteratively mutates tracker settings to maximize accuracy for specific d

An implementation for ACL 2023 paper Learning In-context Learning for Named Entity Recognition

A list of NLP resources focused on event extraction task

Official code for VisProg (CVPR 2023 Best Paper!)

This is the github repository for the paper to be appeared at NAACL 2024 main conference: Self-Improving for Zero-Shot Named Entity Recognition with Large Language Models.

This is the github repository for the paper to be appeared at EMNLP 2023 main conference: Empirical Study of Zero-Shot NER with ChatGPT.

An Evaluation of ChatGPT on Information Extraction task, including Named Entity Recognition (NER), Relation Extraction (RE), Event Extraction (EE) and Aspect-based Sentiment Analysis (ABSA).

Assess, Guard, and Monitor Your LLM Applications Built by Future AGI | Docs | Platform

This repository provides the pipeline used in our work to benchmark GPT-3 in-context learning and BERT-sized model fine-tuning on biomedical information extraction tasks (NER and relation extraction) under the true few-shot setting.

Source code and data for ACL 2023 main conference paper DICE: Data-Efficient Clinical Event Extraction with Generative Models.

Emu Series: Generative Multimodal Models from BAAI

Zhao Zhang 3   Ziwei Liu &#x2709,1 1 S-Lab, Nanyang Technological University  2 Shanghai Jiao Tong University  3 SenseTime Research  4 Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, China   Equal Contribution  † Project Lead …

1,400+ curated trending AI image prompts from X, ranked by engagement. Works with NanoBanana, GPT Image 2, Midjourney

Please save your dataset in data folder. Note that CoNLL2003 and WNUT2017 are open-source datasets, ACE2004 and ACE2005 are not free. We keep our CoNLL2003 and WNUT2017 train and test JSON files in data folder.

This is the original code and dataset of the NERretrieve paper: NERetrieve: Dataset for Next Generation Named Entity Recognition and Retrieval.

This is a meta-model distilled from ChatGPT-3.5-turbo for information extraction. This is an intermediate checkpoint that can be well-transferred to all kinds of downstream information extraction tasks.

Code, data, and results described in the paper "Mining experimental data from materials science literature with large language models: an evaluation study", https://www.tandfonline.com/doi/full/10.1080/27660400.2024.2356506

A concept and obvious expression pattern collection of Chinese compound event extraction which then be evolved into ComplexEventGraph，本项目提出了中文复合事件的概念与显式模式，包括条件事件、因果事件、顺承事件、反转事件等事件抽取，并形成事理图谱。

An exploration for Eventline (important news Rank organized by pulic time)，针对某一事件话题下的新闻报道集合，通过使用docrank算法，对新闻报道进行重要性识别，并通过新闻报道时间挑选出时间线上重要新闻。

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

Codes for "Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models".

An implementation for Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction - Please contact Yaojie Lu (@luyaojie) for questions and suggestions.

Source code for Findings of ACL 2024 paper: Beyond Single-Event Extraction: Towards Efficient Document-Level Multi-Event Argument Extraction.

This repository contains the code for our paper: