Use the Seq2Seq method to implement machine translation and use the Attention mechanism to improve the performence
NLP_translation.py: implement model training and testingAttention.py: Using Seq2Seq with attenionPlainSeq2Seq.py : Using Seq2Seq without attentionWe also store the model and the DataSets in the directory ./data/nmt
TruthfulQA: Measuring How Models Imitate Human Falsehoods
jel: Japanese Entity Linker jel - Japanese Entity Linker - is Bi-encoder based entity linker for japanese. Usage Currently, link and question methods
oppo-text-match 小布助手对话短文本语义匹配的一个baseline 模型 参考：https://kexue.fm/archives/8213 base版本线下大概0.952，线上0.866（单模型，没做K-flod融合）。 训练 测试环境：tensorflow 1.15 + keras
TextDistance TextDistance -- python library for comparing distance between two or more sequences by many algorithms. Features: 30+ algorithms Pure pyt
Negative Sampling for NER Unlabeled entity problem is prevalent in many NER scenarios (e.g., weakly supervised NER). Our paper in ICLR-2021 proposes u
Official Stanford NLP Python Library for Many Human Languages
clustering-laion400m Script and models for clustering LAION-400m CLIP embeddings. Models were fit on the first million or so image embeddings. A subje
Add support for the 65C816 to py65 Py65 (https://github.com/mnaberez/py65) is a
Line as a Visual Sentence with LineTR This repository contains the inference code, pretrained model, and demo scripts of the following paper. It suppo
Sinkhorn Transformer This is a reproduction of the work outlined in Sparse Sinkhorn Attention, with additional enhancements. It includes a parameteriz
BanglaBERT This repository contains the official release of the model "BanglaBERT" and associated downstream finetuning code and datasets introduced i
A Deep Learning NLP/NLU library by Intel® AI Lab Overview | Models | Installation | Examples | Documentation | Tutorials | Contributing NLP Architect
New & (hopefully) Improved CYGNUS with several API updates, user updates, and online/offline operations added!!!
- 基于标题的大规模商品实体检索top1 一、任务介绍 CCKS 2020：基于标题的大规模商品实体检索，任务为对于给定的一个商品标题，参赛系统需要匹配到该标题在给定商品库中的对应商品实体。 输入：输入文件包括若干行商品标题。 输出：输出文本每一行包括此标题对应的商品实体，即给定知识库中商品 ID，
patterns-finder Simple, Fast, Powerful and Easily extensible python package for extracting patterns from text, with over than 60 predefined Regular Ex
LeBenchmark: a reproducible framework for assessing SSL from speech Self-Supervised Learning (SSL) using huge unlabeled data has been successfully exp
Korean Stereotype Detector Korean stereotype sentence classifier using K-StereoSet with TUNiB-Electra Web demo you can test this model easily in demo
CPT This repository contains code and checkpoints for CPT. CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Gener
ChainKnowledgeGraph, 产业链知识图谱包括A股上市公司、行业和产品共3类实体，包括上市公司所属行业关系、行业上级关系、产品上游原材料关系、产品下游产品关系、公司主营产品、产品小类共6大类。 上市公司4,654家，行业511个，产品95,559条、上游材料56,824条，上级行业480条，下游产品390条，产品小类52,937条，所属行业3,946条。
Must-read papers on improving efficiency for pre-trained language models.
69 Dec 25, 2022
10 Jan 06, 2023
132 Dec 14, 2022
3k Jan 06, 2023
128 Dec 29, 2022
6.4k Jan 02, 2023
22 Oct 04, 2022
4 Jan 04, 2023
158 Dec 27, 2022
217 Nov 25, 2022
197 Dec 25, 2022
2.9k Jan 02, 2023
0 Mar 28, 2022
43 Nov 11, 2022
22 Dec 19, 2022
49 Aug 24, 2022
11 Feb 18, 2022
342 Jan 05, 2023
415 Jan 06, 2023
89 Jan 03, 2023