本仓库是基于bert4keras实现的古文-现代文翻译模型。具体使用了基于掩码自注意力机制的UNILM(Li al., 2019)预训练模型作为翻译系统的backbone。我们首先使用了普通的中文（现代文）BERT、Roberta权重作为UNILM的初始权重以训练UNILM模型（具体在文中分别为B-UNILM以及R-UNILM）。为了更好的使UNILM模型适应古文的特性，我们尝试使用了在古文预训练模型Guwen-BERT，作为UNILM的初始权重，并且获得了最优的效果。
☆54May 3, 2022Updated 4 years ago
Alternatives and similar repositories for Guwen-UNILM
Users that are interested in Guwen-UNILM are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆21Oct 6, 2023Updated 3 years ago
- 基于ChineseAlpaca微调的，专精与古汉语翻译、古汉语断句的大语言模型☆21Aug 20, 2023Updated 3 years ago
- An educational Chinese-to-English NMT project featuring the classic encoder-decoder Transformer and a configurable modern decoder-only GP…☆19Jun 7, 2026Updated 4 months ago
- The repository for the paper: Rethinking Document-level Neural Machine Translation☆25Dec 20, 2022Updated 3 years ago
- microsoft unilm-v1 compatible with huggingface transformers☆21Apr 5, 2023Updated 3 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- GuwenBERT: 古文预训练语言模型（古文BERT） A Pre-trained Language Model for Classical Chinese (Literary Chinese)☆569Aug 31, 2021Updated 5 years ago
- 非常全的文言文（古文）-现代文平行语料☆1,499Apr 21, 2024Updated 2 years ago
- Pretrained BERT for Ancient (Classical) Chinese, with an expanded vocabulary for rare characters.☆48Feb 20, 2023Updated 3 years ago
- 文言文信息抽取（实体识别+关系抽取）☆10Feb 24, 2023Updated 3 years ago
- This is an interpreter which translate classical Chinese to modern Chinese. 该项目是一个把文言文翻译成现代文的翻译器☆36May 5, 2023Updated 3 years ago
- Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA)☆38May 19, 2026Updated 5 months ago
- 使用UniLM实现中文文本摘要☆43Mar 25, 2020Updated 6 years ago
- 分别使用TextRank、BiLSTM和UniLM实现中文文章标题自动生成☆28Sep 22, 2020Updated 6 years ago
- ☆10Jan 17, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- 本项目使用云问科技训练的中文版UniLM模型对微博数据集进行自动标题生成。☆38Apr 4, 2024Updated 2 years ago
- 甲言，专注于古代汉语(古汉语/古文/文言文/文言)处理的NLP工具包，支持文言词库构建、分词、词性标注、断句和标点。Jiayan, the 1st NLP toolkit designed for Classical Chinese, supports lexicon co…☆682Nov 2, 2021Updated 5 years ago
- 中文版unilm预训练模型☆82Feb 22, 2021Updated 5 years ago
- SikuBERT：四库全书的预训练语言模型（四库BERT） Pre-training Model of Siku Quanshu☆173Jul 30, 2023Updated 3 years ago
- 古诗词爬虫和文本挖掘，含13个朝代的3万多条诗人数据、85万多条诗词数据，包括主题聚类、相关诗词推荐、藏头诗生成、诗词翻译等算法实现☆36Nov 3, 2022Updated 3 years ago
- Dataset and Source code of paper 'Enhancing Keyphrase Extraction from Academic Articles with their Reference Information'.☆18Dec 26, 2022Updated 3 years ago
- Official code of our work, Syntax-augmented Multilingual BERT for Cross-lingual Transfer [ACL 2021].☆16Dec 2, 2021Updated 4 years ago
- CHisIEC An Information Extraction Corpus for Ancient Chinese History☆27Nov 25, 2025Updated 11 months ago
- The repository for the paper: Multilingual Translation via Grafting Pre-trained Language Models☆24Sep 22, 2021Updated 5 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Tokenizer POS-tagger and Dependency-parser for Classical Chinese☆21Oct 26, 2026Updated last week
- An evaluation bentchmark for classical Chinese☆22Dec 13, 2023Updated 2 years ago
- A demonstration of Jupyter Book functionality using QuantEcon Python programming source material.☆14Oct 30, 2020Updated 6 years ago
- ☆11May 28, 2024Updated 2 years ago
- 新闻人物言论自动提取---->得到说话的人和说话的内容☆10Jan 17, 2020Updated 6 years ago
- 斗破苍穹小说的新词发现☆13May 12, 2022Updated 4 years ago
- ☆21Apr 30, 2023Updated 3 years ago
- Code for "Context-Aware Recurrent Encoder for Neural Machine Translation" (TASLP 2017)☆12Oct 29, 2018Updated 8 years ago
- 中英文神经网络机器翻译☆14Jan 17, 2021Updated 5 years ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Open-source repository for the OOPSLA'24 paper "CYCLE: Learning to Self-Refine Code Generation"☆10Mar 8, 2024Updated 2 years ago
- Python scripts and datasets of the "Extremely Low-Resource Neural Machine Translation: A Case Study of Cantonese" project☆16Oct 28, 2022Updated 4 years ago
- ☆13May 15, 2021Updated 5 years ago
- 基于深度学习的对话系统、语音识别、机器翻译和语音合成等。☆13Jan 3, 2021Updated 5 years ago
- 抽取式NLP模型（阅读理解模型，MRC）实现词义消歧（WSD）☆14May 10, 2022Updated 4 years ago
- ☆11Sep 26, 2022Updated 4 years ago
- NJUNMT for docNMT☆16Sep 9, 2020Updated 6 years ago