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～
chikkarpy chikkarpyはchikkarのPython版です。 chikkarpy is a Python version of chikkar. chikkarpy は Sudachi 同義語辞書を利用し、SudachiPyの出力に同義語展開を追加するために開発されたライブラリです。
Gourmet Models Overview The Gourmet project has released several machine translation models to translate low-resource languages. This repository conta
Information WARNING: No longer hosted If you would like to be on this repo's readme simply fork or star it! Forks 1 - Flowzii 2 - Errorcrafter 3 - vk-
LeBenchmark: a reproducible framework for assessing SSL from speech Self-Supervised Learning (SSL) using huge unlabeled data has been successfully exp
ConvBERT 目录 0. 仓库结构 1. 简介 2. 数据集和复现精度 3. 准备数据与环境 3.1 准备环境 3.2 准备数据 3.3 准备模型 4. 开始使用 4.1 模型训练 4.2 模型评估 4.3 模型预测 5. 模型推理部署 5.1 基于Inference的推理 5.2 基于Serv
OpenSpeech provides reference implementations of various ASR modeling papers and three languages recipe to perform tasks on automatic speech recogniti
Table of contents Introduction Using BARTpho with fairseq Using BARTpho with transformers Notes BARTpho: Pre-trained Sequence-to-Sequence Models for V
AI-BOT Bot to connect a real Telegram user, simulating responses with OpenAI's davinci GPT-3 model.
transformer-sequential This repo contains the code for two papers: Feedback Transformer Expire-Span The training code is structured for long sequentia
BioLAMA BioLAMA is biomedical factual knowledge triples for probing biomedical LMs. The triples are collected and pre-processed from three sources: CT
PG-19 Language Modelling Benchmark This repository contains the PG-19 language modeling benchmark. It includes a set of books extracted from the Proje
The project has set itself the goal of analyzing the thoughts and interaction of Italian users through the social posts expressed through the Twitter platform on the day of the entry into force of th
Github Profile README/ About Me Generator 💯 This webapp lets you build a cool README for your profile. A few inputs + ~15 mins = Your Github Profile
TextDistance TextDistance -- python library for comparing distance between two or more sequences by many algorithms. Features: 30+ algorithms Pure pyt
Snips NLU Snips NLU (Natural Language Understanding) is a Python library that allows to extract structured information from sentences written in natur
多标签文本分类任务 近年来随着深度学习的发展，模型参数的数量飞速增长。为了训练这些参数，需要更大的数据集来避免过拟合。然而，对于大部分NLP任务来说，构建大规模的标注数据集非常困难（成本过高），特别是对于句法和语义相关的任务。相比之下，大规模的未标注语料库的构建则相对容易。为了利用这些数据，我们可以
MCSE: Multimodal Contrastive Learning of Sentence Embeddings This repository contains code and pre-trained models for our NAACL-2022 paper MCSE: Multi
Refactored version of FastSpeech2. An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"
langid.py readme Introduction langid.py is a standalone Language Identification (LangID) tool. The design principles are as follows: Fast Pre-trained
Malware-Related Sentence Classification This repo contains the code for the ICTAI 2021 paper "Enrichment of Features for Malware-Related Sentence Clas
48 Dec 14, 2022
5 Dec 08, 2021
66 Dec 31, 2022
49 Aug 24, 2022
7 Apr 08, 2022
26 Dec 14, 2022
58 Dec 23, 2022
2 Dec 21, 2022
125 Dec 25, 2022
41 Nov 18, 2022
161 Oct 30, 2022
3 Nov 17, 2022
179 Jan 07, 2023
3k Jan 06, 2023
3.7k Dec 30, 2022
1 Nov 11, 2021
39 Nov 15, 2022
10 May 26, 2022
2k Jan 04, 2023
1 Mar 26, 2022