2021搜狐校园文本匹配算法大赛baseline
分享了一个搜狐文本匹配的baseline，主要是通过条件LayerNorm来增加模型的多样性，以实现同一模型处理不同类型的数据、形成不同输出的目的。
线下验证集F1约0.74，线上测试集F1约0.73。预训练模型是RoFormer，也欢迎对比其他预训练模型的效果。
测试环境：tensorflow 1.14 + keras 2.3.1 + bert4keras 0.10.5，如果在其他环境组合下报错，请根据错误信息自行调整代码。
详情请看：https://kexue.fm/archives/8337
QQ交流群：808623966，微信群请加机器人微信号spaces_ac_cn
pyctcdecode A fast and feature-rich CTC beam search decoder for speech recognition written in Python, providing n-gram (kenlm) language model support
Chinese named entity recognization (bert/roberta/macbert/bert_wwm with Keras)
auto_code_complete is a auto word-completetion program which allows you to customize it on your needs. the model for this program is one of the deep-learning NLP(Natural Language Process) model struc
Parrot is a paraphrase based utterance augmentation framework purpose built to accelerate training NLU models. A paraphrase framework is more than just a paraphrasing model.
Welcome to the Transfer NLP library, a framework built on top of PyTorch to promote reproducible experimentation and Transfer Learning in NLP You can
TensorFlow Lattice TensorFlow Lattice is a library that implements constrained and interpretable lattice based models. It is an implementation of Mono
speech-recognition-py Speech recognition is the ability of computer software to identify words and phrases in spoken language and convert them to huma
ML-powered Music Recommendation Engine
Image2PCL Enter the metaverse with 2D image to 3D projections! This is an implem
Scattertext 0.1.0.0 A tool for finding distinguishing terms in corpora and displaying them in an interactive HTML scatter plot. Points corresponding t
TaskBench500 The TaskBench500 dataset and code for generating tasks. Data The TaskBench dataset is available under wget http://web.mit.edu/bzl/www/Tas
MLP Singer Official implementation of MLP Singer: Towards Rapid Parallel Korean Singing Voice Synthesis. Audio samples are available on our demo page.
BioLAMA BioLAMA is biomedical factual knowledge triples for probing biomedical LMs. The triples are collected and pre-processed from three sources: CT
Nystromformer: A Nystrom-based Algorithm for Approximating Self-Attention April 6, 2021 We extended segment-means to compute landmarks without requiri
Label Studio for Hugging Face's Transformers Website • Docs • Twitter • Join Slack Community Transfer learning for NLP models by annotating your textu
Web Scraping, Document Deduplication & GPT-2 Fine-tuning with a newly created scam dataset.
artificial intelligence cosmic love and attention fire in the sky a pyramid made of ice a lonely house in the woods marriage in the mountains lantern
English | 中文 Features 🌍 Chinese supported mandarin and tested with multiple datasets: aidatatang_200zh, magicdata, aishell3, data_aishell, and etc. ?
PORORO: Platform Of neuRal mOdels for natuRal language prOcessing pororo performs Natural Language Processing and Speech-related tasks. It is easy to
Official PyTorch code for ClipBERT, an efficient framework for end-to-end learning on image-text and video-text tasks. It takes raw videos/images + text as inputs, and outputs task predictions. ClipB
315 Dec 21, 2022
2 Jul 05, 2022
2 Feb 22, 2022
681 Jan 01, 2023
290 Dec 20, 2022
504 Dec 20, 2022
1 Apr 03, 2022
23 Oct 09, 2022
0 Feb 05, 2022
2k Dec 27, 2022
20 May 17, 2022
103 Dec 23, 2022
41 Nov 18, 2022
322 Jan 01, 2023
135 Dec 29, 2022
18 Nov 28, 2022
2.3k Jan 01, 2023
25.6k Dec 31, 2022
1.2k Dec 21, 2022
612 Jan 04, 2023