小布助手对话短文本语义匹配的一个baseline
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）。
测试环境：tensorflow 1.15 + keras 2.3.1 + bert4keras 0.10.0
跑完100epoch可能6小时左右（3090，建议跑完）
from baseline import *
predict_to_file('result.csv')
然后zip result.zip result.csv，最后把result.zip提交即可。
感谢主办方对本baseline的肯定～
toxic-spans-detection An attempt at the SemEval 2021 Task 5: Toxic Spans Detection. The Toxic Spans Detection task of SemEval2021 required participant
japanese-ebook-analysis This aim of this project is to make analysing the contents of a japanese ebook easy and streamline the process for non-technic
NL A Natural-Language programming language. Built using Codex. A few examples are inside the nl_projects directory. How it works Write any code in pur
What are the best Systems? New Perspectives on NLP Benchmarking In Machine Learning, a benchmark refers to an ensemble of datasets associated with one
NLP Best Practices In recent years, natural language processing (NLP) has seen quick growth in quality and usability, and this has helped to drive bus
Sentence Transformers: Multilingual Sentence Embeddings using BERT / RoBERTa / XLM-RoBERTa & Co. with PyTorch This framework provides an easy method t
Pre-Training with Whole Word Masking for Chinese BERT
UNITER: UNiversal Image-TExt Representation Learning This is the official repository of UNITER (ECCV 2020). This repository currently supports finetun
AdapterBias: Parameter-efficient Token-dependent Representation Shift for Adapters in NLP Tasks arXiv link: upcoming To be published in Findings of NA
Non-Autoregressive Transformer Code release for Non-Autoregressive Neural Machine Translation by Jiatao Gu, James Bradbury, Caiming Xiong, Victor O.K.
FastBomber Unlimited Call - Text Bombing Tool Installation On Termux
Score-Based Point Cloud Denoising (ICCV'21) [Paper] https://arxiv.org/abs/2107.10981 Installation Recommended Environment The code has been tested in
BioLAMA BioLAMA is biomedical factual knowledge triples for probing biomedical LMs. The triples are collected and pre-processed from three sources: CT
Meta learning algorithms to train cross-lingual NLI (multi-task) models
The KLEJ Benchmark Baselines The KLEJ benchmark (Kompleksowa Lista Ewaluacji Językowych) is a set of nine evaluation tasks for the Polish language und
Hungarian Preverb Corpus A gold standard corpus manually annotated with verb-preverb connections for Hungarian. corpus The corpus consist of the follo
simple_diarizer Simplified diarization pipeline using some pretrained models. Made to be a simple as possible to go from an input audio file to diariz
Need: Image Search The problem is that a user needs to search for a specific ima
Python-zhuyin - An open source Python library that provides a unified interface for converting between Chinese pinyin and Zhuyin (bopomofo)
Random Word Generator Generates meaningful words from dictionary with given no. of letters and words. This might be useful for generating short links
3 Jul 24, 2022
14 Jul 23, 2022
2 Jan 17, 2022
12 Nov 03, 2022
6.1k Dec 31, 2022
9.1k Jan 02, 2023
7.7k Dec 31, 2022
680 Dec 24, 2022
16 Nov 12, 2022
261 Nov 12, 2022
6 Nov 10, 2022
79 Dec 26, 2022
41 Nov 18, 2022
4 Nov 20, 2022
17 Oct 18, 2022
3 Jan 27, 2022
65 Dec 30, 2022
1 Dec 30, 2021
2 Dec 29, 2022
1 Jan 01, 2022