Open Source Information Extraction

Pull structured facts out of unstructured text: relations, events, keywords and keyphrases, ready to feed into databases and knowledge graphs.

195
projects
135.9K ★
total stars
+208
stars this week
Python
top language

ranked by GitHub stars · updated Nov 12, 2026

🔥 Trending this week in Information Extraction

Information Extraction

cocacola-lab/ChatIE

▲ +55 ★ this week

The online version is temporarily unavailable because we cannot afford the key. You can clone and run it locally. Note: we set defaul openai key. If keys exceed plan and are invalid, please tell us. The response speed depends on openai. ( sometimes, the official is too crowded and slow)

🏷️ Named Entity Recognition🧠 Natural Language Processing
PythonOtherupdated May 28, 2024
GitHub ↗★ 897⑂ 67
Information Extraction

urchade/GLiNER🔥 active

▲ +41 ★ this week

Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts)

🏷️ Named Entity Recognition🤖 Language Models🧠 Natural Language Processing
PythonApache-2.0updated Nov 11, 2026
GitHub ↗★ 4.3K⑂ 328
Information Extraction

yifanfeng97/Hyper-Extract

▲ +28 ★ this week

Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.

🔍 Search & Retrieval
PythonOtherupdated Nov 5, 2026
GitHub ↗★ 4.2K⑂ 492
Information Extraction

shcherbak-ai/contextgem🔥 active

▲ +19 ★ this week

Extract structured data and insights from documents using LLMs and decision models

📄 OCR & Documents🧠 Natural Language Processing💎 Text Mining
PythonApache-2.0updated Nov 9, 2026
GitHub ↗★ 2.1K⑂ 190
Information Extraction

monarch-initiative/ontogpt

▲ +10 ★ this week

LLM-based ontological extraction tools, including SPIRES

🏷️ Named Entity Recognition🤖 Language Models🧠 Natural Language Processing
Jupyter NotebookBSD-3-Clauseupdated Sep 10, 2026
GitHub ↗★ 1.1K⑂ 126
Information Extraction

ail-project/ail-framework🔥 active

▲ +8 ★ this week

AIL framework - Analysis Information Leak framework

HTMLAGPL-3.0updated Nov 9, 2026
GitHub ↗★ 1.1K⑂ 149

Top 30 information extraction tools by stars

Information Extraction🥇#1

PaddlePaddle/PaddleNLP

▲ +6 ★ this week

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

🧠 Natural Language Processing💖 Sentiment Analysis❓ Question Answering
PythonApache-2.0updated May 23, 2026
GitHub ↗★ 13K⑂ 3K
Information Extraction🥈#2

vi3k6i5/flashtext

Extract Keywords from sentence or Replace keywords in sentences.

🧬 Embeddings🧠 Natural Language Processing
PythonMITupdated Apr 13, 2025
GitHub ↗★ 5.7K⑂ 595
Information Extraction🥉#3

zjunlp/DeepKE

[EMNLP 2022] An Open Toolkit for Knowledge Graph Extraction and Construction

🏷️ Named Entity Recognition🧠 Natural Language Processing
PythonMITupdated Jul 13, 2026
GitHub ↗★ 4.5K⑂ 747
Information Extraction#4

thunlp/OpenNRE

An Open-Source Package for Neural Relation Extraction (NRE)

PythonMITupdated Jan 10, 2024
GitHub ↗★ 4.5K⑂ 1K
Information Extraction#5

qq547276542/Agriculture_KnowledgeGraph

农业知识图谱(AgriKG):农业领域的信息检索,命名实体识别,关系抽取,智能问答,辅助决策

🏷️ Named Entity Recognition❓ Question Answering
PythonGPL-3.0updated Feb 11, 2025
GitHub ↗★ 4.4K⑂ 1.6K
Information Extraction#6

urchade/GLiNER🔥 active

▲ +41 ★ this week

Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts)

🏷️ Named Entity Recognition🤖 Language Models🧠 Natural Language Processing
PythonApache-2.0updated Nov 11, 2026
GitHub ↗★ 4.3K⑂ 328
Information Extraction#7

yifanfeng97/Hyper-Extract

▲ +28 ★ this week

Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.

🔍 Search & Retrieval
PythonOtherupdated Nov 5, 2026
GitHub ↗★ 4.2K⑂ 492
Information Extraction#8

MaartenGr/KeyBERT

Minimal keyword extraction with BERT

🧠 Natural Language Processing
PythonMITupdated Aug 25, 2026
GitHub ↗★ 4.2K⑂ 389
Information Extraction#9

km1994/nlp_paper_study

该仓库主要记录 NLP 算法工程师相关的顶会论文研读笔记

🧠 Natural Language Processing
C++no licenseupdated Oct 11, 2026
GitHub ↗★ 4K⑂ 637
Information Extraction#10

snipsco/snips-nlu

Snips Python library to extract meaning from text

🏷️ Named Entity Recognition🗂️ Text Classification🧠 Natural Language Processing
PythonApache-2.0updated May 22, 2023
GitHub ↗★ 4K⑂ 502
Information Extraction#11

letiantian/TextRank4ZH

:deciduous_tree:从中文文本中自动提取关键词和摘要

PythonMITupdated May 7, 2025
GitHub ↗★ 3.4K⑂ 828
Information Extraction#12

mit-nlp/MITIE

MITIE: library and tools for information extraction

🧠 Natural Language Processing
C++no licenseupdated Sep 28, 2025
GitHub ↗★ 3K⑂ 531
Information Extraction#13

naiveHobo/InvoiceNet

Deep neural network to extract intelligent information from invoice documents.

🔍 Search & Retrieval
PythonMITupdated May 3, 2024
GitHub ↗★ 2.7K⑂ 409
Information Extraction#14

blmoistawinde/HarvestText

文本挖掘和预处理工具(文本清洗、新词发现、情感分析、实体识别链接、关键词抽取、知识抽取、句法分析等),无监督或弱监督方法

💖 Sentiment Analysis🏷️ Named Entity Recognition📝 Text Summarization🧠 Natural Language Processing
PythonMITupdated May 13, 2024
GitHub ↗★ 2.6K⑂ 341
Information Extraction#15

HarderThenHarder/transformers_tasks

⭐️ NLP Algorithms with transformers lib. Supporting Text-Classification, Text-Generation, Information-Extraction, Text-Matching, RLHF, SFT etc.

🗂️ Text Classification🤖 Language Models🧠 Natural Language Processing
Jupyter Notebookno licenseupdated Sep 29, 2023
GitHub ↗★ 2.4K⑂ 399
Information Extraction#16

crownpku/Information-Extraction-Chinese

Chinese Named Entity Recognition with IDCNN/biLSTM+CRF, and Relation Extraction with biGRU+2ATT 中文实体识别与关系提取

🏷️ Named Entity Recognition🧠 Natural Language Processing
Pythonno licenseupdated Feb 1, 2024
GitHub ↗★ 2.3K⑂ 795
Information Extraction#17

shcherbak-ai/contextgem🔥 active

▲ +19 ★ this week

Extract structured data and insights from documents using LLMs and decision models

📄 OCR & Documents🧠 Natural Language Processing💎 Text Mining
PythonApache-2.0updated Nov 9, 2026
GitHub ↗★ 2.1K⑂ 190
Information Extraction#18

INESCTEC/yake

Single-document unsupervised keyword extraction

Jupyter NotebookOtherupdated Feb 11, 2026
GitHub ↗★ 1.9K⑂ 246
Information Extraction#19

shaoxiongji/knowledge-graphs

▲ +2 ★ this week

A collection of research on knowledge graphs

🏷️ Named Entity Recognition❓ Question Answering🔍 Search & Retrieval🧠 Natural Language Processing
JavaScriptno licenseupdated Oct 7, 2022
GitHub ↗★ 1.8K⑂ 298
Information Extraction#20

myhhub/KnowledgeGraph

▲ +6 ★ this week

knowledge graph知识图谱,从零开始构建知识图谱

🏷️ Named Entity Recognition❓ Question Answering
Pythonno licenseupdated Sep 18, 2023
GitHub ↗★ 1.7K⑂ 175
Information Extraction#21

eyurtsev/kor

LLM(😽)

🧠 Natural Language Processing
PythonMITupdated Feb 3, 2025
GitHub ↗★ 1.7K⑂ 93
Information Extraction#22

boudinfl/pke

▲ +1 ★ this week

Python Keyphrase Extraction module

🧠 Natural Language Processing🔍 Search & Retrieval
PythonGPL-3.0updated Jul 12, 2023
GitHub ↗★ 1.6K⑂ 294
Information Extraction#23

Tongjilibo/bert4torch

An elegent pytorch implement of transformers

🧠 Natural Language Processing🏷️ Named Entity Recognition🗂️ Text Classification🤖 Language Models
PythonMITupdated May 16, 2026
GitHub ↗★ 1.3K⑂ 166
Information Extraction#24

yuanxiaosc/Entity-Relation-Extraction

Entity and Relation Extraction Based on TensorFlow and BERT. 基于TensorFlow和BERT的管道式实体及关系抽取,2019语言与智能技术竞赛信息抽取任务解决方案。Schema based Knowledge Extraction, SKE 2019

🏷️ Named Entity Recognition
Pythonno licenseupdated Jun 1, 2020
GitHub ↗★ 1.2K⑂ 269
Information Extraction#25

monarch-initiative/ontogpt

▲ +10 ★ this week

LLM-based ontological extraction tools, including SPIRES

🏷️ Named Entity Recognition🤖 Language Models🧠 Natural Language Processing
Jupyter NotebookBSD-3-Clauseupdated Sep 10, 2026
GitHub ↗★ 1.1K⑂ 126
Information Extraction#26

csurfer/rake-nltk

Python implementation of the Rapid Automatic Keyword Extraction algorithm using NLTK.

🧠 Natural Language Processing💎 Text Mining
PythonMITupdated Dec 9, 2022
GitHub ↗★ 1.1K⑂ 150
Information Extraction#27

ail-project/ail-framework🔥 active

▲ +8 ★ this week

AIL framework - Analysis Information Leak framework

HTMLAGPL-3.0updated Nov 9, 2026
GitHub ↗★ 1.1K⑂ 149
Information Extraction#28

thunlp/NREPapers

Must-read papers on neural relation extraction (NRE)

TeXno licenseupdated Nov 10, 2020
GitHub ↗★ 1K⑂ 150
Information Extraction#29

cocacola-lab/ChatIE

▲ +55 ★ this week

The online version is temporarily unavailable because we cannot afford the key. You can clone and run it locally. Note: we set defaul openai key. If keys exceed plan and are invalid, please tell us. The response speed depends on openai. ( sometimes, the official is too crowded and slow)

🏷️ Named Entity Recognition🧠 Natural Language Processing
PythonOtherupdated May 28, 2024
GitHub ↗★ 897⑂ 67
Information Extraction#30

smilelight/lightNLP

▲ +1 ★ this week

基于Pytorch和torchtext的自然语言处理深度学习框架。

🗂️ Text Classification🧬 Embeddings🤖 Language Models🧠 Natural Language Processing
PythonApache-2.0updated Dec 14, 2020
GitHub ↗★ 831⑂ 208

📄 New research on Information Extraction

📄 arXiv:2611.14050 · cs.IR2d ago

Ontology-Guided Knowledge Graph Construction and Robust Evidence Retrieval for Indian Knowledge Systems

Anand Kaniyaar Sriranga Prasad, Avinash Holenarasipur Nagendra, Mohan Raghavan

💬 22 pages, 15 figures, 4 tables

Retrieving evidence from Indian Knowledge Systems is complicated by transliteration variants, ambiguous names, and relations distributed across passages. We present an ontology-guided knowledge graph (KG) pipeline that links typed entities and relations extracted with Qwen3-32B to original textual evidence. Retrieval combines sense-aware grounding, bounded graph traversal, lexical anchors, relationship-vector search, and passage reranking. We evaluate KG alone, single-vector retrieval (SV), and KG unions with SV and Entity Notes on 320 questions from Dhara Bench, matching the per-question candidate count across internal systems under BGE and Qwen rerankers. Standalone KG has the highest Precision@5 under both rerankers and the highest MRR@20 in Counting, Composite, and Multi-hop among the evaluated internal configurations. With Qwen, KG achieves Multi-hop MRR@20 of 0.8722, compared with 0.7622 for the fully reranked KG + SV union. The KG + SV + Entity Notes union instead provides the highest overall Recall@20 (0.5134), compared with 0.4347 for KG. On the 15 Multi-hop questions, Qwen KG achieves complete-evidence MRR@20 of 0.4651 versus 0.3372 for SV, while both full unions complete ten questions within twenty results compared with nine for KG. Gemini 3.7 Flash, evaluated through manually reviewed source mappings, re mains stronger on overall MRR and nDCG, while internal systems have category-specific advantages. All comparisons are descriptive. A separate deployment timing study measures mean retrieval times of 20.374 s for KG and 0.646 s for SV. The findings support selecting KG or its unions according to the required balance of early relevance, evidence completeness, and retrieval cost.▼ more
⛏️ Information Extraction🔍 Search & Retrieval
📄 arXiv:2611.14037 · cs.IR2d ago

From Show Programs to Linked Data

Clarisse Bardiot, Bernard Jacquemin, Jacob Hart +5

Many heritage institutions hold extensive collections of show programs. Too numerous to be cataloged individually, they remain difficult to access and are still largely undigitized. This paper presents a workflow for transforming such documents into structured, interoperable data by combining vision-language models (VLMs), a custom extension of the Linked Art ontology for the performing arts, and different approaches for automatic semantic data annotation. Using the Festival d'Avignon programs (1947--present), preserved at the Biblioth{è}que nationale de France, as a case study, we demonstrate how VLMs achieve more than 98% text transcription accuracy from heterogeneous heritage document images and how constraining large language model generation through a knowledge graph significantly reduces hallucinations in semantic annotation. We argue that this workflow opens new possibilities for large-scale, interoperable performing arts historiography, including the creation of catalogues raisonn{é}s for performing artists, a form of scholarship common in visual arts but absent in performing arts studies.▼ more
⛏️ Information Extraction🤖 Language Models
📄 arXiv:2611.11886 · cs.IR3d ago

Multi-Modal Agricultural Document Understanding at the DAGRI Task

Zhefan Wang, Da Li, Keping Bi +1

Agricultural documents, such as prefectural technical reports and crop calendars, are critical knowledge resources. However, their complex table layouts, significant variations in document length, and dense multi-modal elements pose substantial challenges for automated understanding. To address these issues, the NTCIR-19 DAGRI (Data Analytics for aGRicultural Information) task introduced three subtasks focusing on different dimensions of document intelligence. In the Table Information Extraction (TableIE) task, we developed a multi-stage pipeline combining structure-preserving parsing via MinerU, region-adaptive segmentation for long documents, and a dual-modal (vision-text) extraction strategy for complex work schedules. This approach achieved first place with an exact match score of 0.6566. For Multi-Table Multi-Hop Question Answering (MTMH-QA) over interrelated JSON tables, we adopted an agentic search framework utilizing DCI-Agent to iteratively explore directories via bash commands, reinforced by a cross-model validation mechanism. This yielded a revised accuracy of 0.8444, initially ranked first. In the Figure and Table Question Answering (FiT-QA) task, which requires comprehending single large composite images, we implemented a dual-modal VLM pipeline enhanced by deterministic answer normalization, securing the highest BLEU score. Together, our system effectively addresses regional structural variations, dynamic cross-file evidence discovery, and multi-modal alignment, providing a robust framework for complex agricultural document understanding.▼ more
⛏️ Information Extraction❓ Question Answering📄 OCR & Documents
📄 arXiv:2611.11802 · cs.CL4d ago

HiddenPathQA: A Benchmark for Knowledge Graph Question Answering When Questions Hide Their Paths

Sumin Jo, Edward Choi

Knowledge graph question answering (KGQA) systems are typically evaluated on questions whose surface tokens lexically expose the gold KG path. Users, however, may ask questions without knowing the underlying schema: "Which condition could Andrew have due to family history?" compresses a 4-hop chain "Andrew --[father]--> parent --[father]--> grandparent --[medical condition]--> disease --[subclass of]--> hereditary disorder" into a single phrase (family history) that names none of those relations. We identify this collapse of path-question alignment as a blind spot in existing KGQA evaluation. Three major LLM-KG paradigms, hop-by-hop exploration, plan-then-retrieve, and similarity-based retrieval, implicitly rely on such lexical cues, an assumption rarely tested in practice. We make three contributions. (i) We introduce HiddenPathQA, a manually verified benchmark of 1,055 questions spanning 2-6 hops and multiple domains, constructed so that question wording does not reveal the gold path's relations. (ii) We propose Holistic Path Selection, which compares questions against candidate relation chains in the local subgraph as complete units, replacing irreversible per-hop relation scoring with globally informed chain-level reasoning. We develop two implementations, TieredHolistic and FlatHolistic. (iii) We conduct a pseudoword stress test that replaces entity names with meaningless placeholders to distinguish KG-grounded reasoning from entity-level memorization. Holistic Path Selection outperforms six strong KGQA baselines (ToG, PoG, FiDeLiS, R2-KG, KAPING, and KARPA) by 8.8-17.9 accuracy points across two LLM backbones and both original and pseudoword settings. Its advantage under pseudoword replacement shows that the gains cannot be explained by entity-level memorization alone.▼ more
⛏️ Information Extraction❓ Question Answering🔍 Search & Retrieval🤖 Language Models