# OpenHowNet: An Open Sememe-based Lexical Knowledge Base

arXiv: https://arxiv.org/abs/1901.09957 · HTML: https://mlsanity.com/paper/1901.09957/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jan 2019.

## Built on by (most cited first, 21 of 21)

- [Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models](https://mlsanity.com/paper/2111.02840/) (2021)
- [Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution](https://mlsanity.com/paper/2106.06361/) (2021)
- [TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization](https://mlsanity.com/paper/2212.09254/) (2022)
- [LET: Linguistic Knowledge Enhanced Graph Transformer for Chinese Short Text Matching](https://mlsanity.com/paper/2102.12671/) (2021)
- [Robust Natural Language Processing: Recent Advances, Challenges, and Future Directions](https://mlsanity.com/paper/2201.00768/) (2022)
- [Improving Commonsense Causal Reasoning by Adversarial Training and Data Augmentation](https://mlsanity.com/paper/2101.04966/) (2021)
- [Less is More: Understanding Word-level Textual Adversarial Attack via n-gram Frequency Descend](https://mlsanity.com/paper/2302.02568/) (2023)
- [aiXamine: Simplified LLM Safety and Security](https://mlsanity.com/paper/2504.14985/) (2025)
- [Expanding Scope: Adapting English Adversarial Attacks to Chinese](https://mlsanity.com/paper/2306.04874/) (2023)
- [K-AID: Enhancing Pre-trained Language Models with Domain Knowledge for Question Answering](https://mlsanity.com/paper/2109.10547/) (2021)
- [Chinese Word Sense Embedding with SememeWSD and Synonym Set](https://mlsanity.com/paper/2206.14388/) (2022)
- [TKDP: Threefold Knowledge-enriched Deep Prompt Tuning for Few-shot Named Entity Recognition](https://mlsanity.com/paper/2306.03974/) (2023)
- [Towards Equipping Transformer with the Ability of Systematic Compositionality](https://mlsanity.com/paper/2312.07280/) (2023)
- [Automatic Construction of Sememe Knowledge Bases via Dictionaries](https://mlsanity.com/paper/2105.12585/) (2021)
- [A Concept Knowledge Graph for User Next Intent Prediction at Alipay](https://mlsanity.com/paper/2301.00503/) (2023)
- [Dynamic Multi-View Fusion Mechanism For Chinese Relation Extraction](https://mlsanity.com/paper/2303.05082/) (2023)
- [Text analysis and deep learning: A network approach](https://mlsanity.com/paper/2110.04151/) (2021)
- [A Knowledge-Injected Curriculum Pretraining Framework for Question Answering](https://mlsanity.com/paper/2403.09712/) (2024)
- [Reversible Jump Attack to Textual Classifiers with Modification Reduction](https://mlsanity.com/paper/2403.14731/) (2024)
- [SEE: Sememe Entanglement Encoding for Transformer-bases Models Compression](https://mlsanity.com/paper/2412.12204/) (2024)
- [LexReward: A Taxonomy-Driven Reward Framework for Legal Language Models](https://mlsanity.com/paper/2609.39071/) (2026)

## Abstract (arXiv)

In this paper, we present an open sememe-based lexical knowledge base OpenHowNet. Based on well-known HowNet, OpenHowNet comprises three components: core data which is composed of more than 100 thousand senses annotated with sememes, OpenHowNet Web which gives a brief introduction to OpenHowNet as well as provides online exhibition of OpenHowNet information, and OpenHowNet API which includes several useful APIs such as accessing OpenHowNet core data and drawing sememe tree structures of senses. In the main text, we first give some backgrounds including definition of sememe and details of HowNet. And then we introduce some previous HowNet and sememe-based research works. Last but not least, we detail the constituents of OpenHowNet and their basic features and functionalities. Additionally, we briefly make a summary and list some future works.