Open-source alternatives to DeepKE

CHisIEC: An Information Extraction Corpus for Ancient Chinese History

Code for "Leveraging ChatGPT in Pharmacovigilance Event Extraction: An Empirical Study" (EACL 2024).

This repository contains code to run the inference and evaluation of NER as described in our NAACL 2024 paper: On-the-fly Definition Augmentation of LLMs for Biomedical NER

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

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.

KnowledgeGraphData is a collection of structured datasets and corpora designed to provide a foundational layer for cognitive intelligence and artificial intelligence systems. It primarily consists of large-scale Chinese knowledge graph datasets, including entity-relation data and NLP training sets used to drive semantic understanding and automated question answering. The project focuses on the construction and export of massive entity-attribute-value graphs, organizing knowledge into portable formats. It provides specialized domain partitioning to tailor information retrieval for professional

Knwl.js is a JavaScript named entity recognition library and rule-based text parser. It serves as an extensible information extraction tool designed to identify and pull structured entities, such as dates, times, and locations, from unstructured text strings. The library allows for the definition of specialized rules and custom plugins to identify and extract unique pieces of information. This extensibility enables the automation of information retrieval by converting human-readable text into structured formats for applications and databases. The system utilizes regular expression matching a

JioNLP is a Chinese natural language processing toolkit designed for cleaning, normalizing, and extracting structured information from unstructured text. It functions as a linguistic analyzer for Chinese characters and a rule-based named entity extractor, providing a specialized system for sentiment scoring and synthetic data generation for machine learning workflows. The project features a lexicon-based sentiment analysis engine that computes numerical emotional tone scores and a data augmentation library that uses back-translation and synonym replacement to expand training datasets. It incl

nlp-recipes is a collection of implementation guides and reference templates for applying natural language processing techniques to real-world tasks. It provides standardized workflows and code examples for developing NLP pipelines, from dataset preparation and model training to performance evaluation. The project focuses on the practical application of transformer-based models, offering patterns for fine-tuning pretrained architectures for tasks such as text classification, named entity recognition, and question answering. It also includes a toolkit for model interpretability, allowing users

Spark NLP is a toolkit for scalable text analysis and machine learning built on the Apache Spark distributed computing framework. It provides a multimodal machine learning framework and a distributed pipeline system for sequencing annotators to process large-scale linguistic data. The library includes a transformer text processor for generating contextual vector embeddings and a dedicated inference engine for managing large language models. The project distinguishes itself through its ability to process heterogeneous data types, including text, audio, and images, within a unified vision-langu

zero_nlp is a distributed framework for training and fine-tuning large language models and multimodal architectures. It provides a specialized toolkit for distributed model parallelism, allowing neural network layers and weights to be partitioned across multiple GPU devices to train models that exceed the memory capacity of a single processor. The project distinguishes itself through a combination of high-throughput data pipelines and parameter-efficient tuning. It utilizes multi-threading and memory mapping to preprocess and stream datasets exceeding 100GB and implements memory-saving adapta

DeepSpeedExamples is a collection of reference implementations and scripts for training, fine-tuning, and executing inference on large-scale AI models using DeepSpeed optimization. It provides a distributed model training guide and practical workflows for adapting large language models through memory-efficient techniques. The repository includes specialized implementations for pipeline parallelism to handle models exceeding single GPU memory and a suite of examples for ZeRO memory optimization to reduce per-device overhead. It also features standardized test suites for benchmarking the throug

Stanza is a Python natural language processing library designed for tokenization, lemmatization, and dependency parsing across many human languages using neural models. It provides a neural processing pipeline that converts raw text into structured linguistic data objects, alongside a specialized analyzer for extracting medical insights from clinical and biomedical language. The project includes a wrapper that connects Python scripts to Java-based natural language processing tools and remote annotation servers. This enables a bridge for extracting linguistic annotations and analysis data from

This is a Chinese natural language processing toolkit providing a suite of tools for word segmentation, part-of-speech tagging, and named entity recognition. It includes a neural dependency parser for analyzing syntactic and semantic relationships between words and a machine learning training suite for creating custom linguistic models using annotated datasets. The toolkit distinguishes itself through its deployment flexibility, offering a dockerized server and a web service interface that exposes processing capabilities via API. It supports the use of pretrained models and allows for the int

This project is a comprehensive instructional resource and course for building neural networks using PyTorch. It covers the fundamental building blocks of deep learning, including tensor manipulation, automatic differentiation, and the construction of modular neural network components. The repository serves as a technical guide for several specialized domains. It provides implementation details for computer vision tasks such as image classification, object detection, and semantic segmentation, as well as natural language processing workflows involving transformers, recurrent networks, and gen

This is the source code of the model RT (Retrieving and Thinking). For the full project, please check the file RTBC5CDR/3RT and RTNCBI/3RT, the implementation of GPT-NER and PromptNER is in the BC5CDR.zip and NCBI.zip. we refer to the source of code of GPT-NER and paper of GPT-NER in our project…

If you are just looking to download the LoRA weights directly, use this url: https://figshare.com/ndownloader/files/43044994 and view the data entry on Figshare.

This project is the codebase used for our weak supervision experiments using E3C dataset annotated with InstructGPT-3 and dictionary.

This is the implementation of filter-then-rerank pipeline in Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!. EMNLP'2023 (Findings).

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.

openai 0.27.4

Data and code for ACL 2023 Findings: Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation Extractors.

https://aclanthology.org/2023.emnlp-main.745.pdf

Tensor2Tensor is a deep learning library built on TensorFlow designed for training and evaluating complex machine learning models. It provides a unified framework for managing the entire model lifecycle, including data ingestion, training execution, and performance evaluation across diverse hardware environments. The library distinguishes itself through a modular architecture that supports multimodal data processing, allowing for the simultaneous analysis of text, audio, and image inputs. It features a central registry system that enables developers to extend the framework with custom models,

Named entity recognition is a natural language processing library that implements statistical and neural sequence labeling models to extract entities from text. The toolkit provides implementations for hidden Markov models, conditional random fields, and bidirectional recurrent neural networks combined with conditional random field layers. The library supports training machine learning models on annotated training corpora using maximum likelihood estimation for parameter and transition structure estimation. It includes ensemble majority voting consensus strategies to combine independent outpu

Duckling is a deterministic named entity recognizer and natural language entity extractor. It transforms unstructured text into machine-readable data by mapping language-specific input strings to universal structured formats. The system utilizes a rule-based engine and composable language rules to resolve entities without relying on probabilistic models. It supports multilingual text parsing across various regional locales, employing a logic-driven approach to normalize diverse natural language expressions into standardized numeric values. The project covers the extraction and normalization

Cocoindex is an incremental data processing engine that builds and maintains live indexes for AI agents, with a core focus on codebase indexing and knowledge graph extraction. The engine uses a function-graph execution model where user-defined Python functions are composed into a directed acyclic graph, and it processes data incrementally so only changed source records or code paths are re-computed, avoiding full recomputation at any scale. It supports automatic schema inference from transformation pipeline type annotations and provides full data lineage tracing, tagging every output record wi