2021海华AI挑战赛·中文阅读理解·技术组·第三名

Overview

海华中文阅读理解比赛

队名:ATTOY排名:第三名

赛题背景

https://www.biendata.xyz/competition/haihua_2021

文字是人类用以记录和表达的最基本工具,也是信息传播的重要媒介。透过文字与符号,我们可以追寻人类文明的起源,可以传播知识与经验,读懂文字是认识与了解的第一步。对于人工智能而言,它的核心问题之一就是认知,而认知的核心则是语义理解。

机器阅读理解(Machine Reading Comprehension)是自然语言处理和人工智能领域的前沿课题,对于使机器拥有认知能力、提升机器智能水平具有重要价值,拥有广阔的应用前景。机器的阅读理解是让机器阅读文本,然后回答与阅读内容相关的问题,体现的是人工智能对文本信息获取、理解和挖掘的能力,在对话、搜索、问答、同声传译等领域,机器阅读理解可以产生的现实价值正在日益凸显,长远的目标则是能够为各行各业提供解决方案。

《2021海华AI挑战赛·中文阅读理解》大赛由中关村海华信息技术前沿研究院与清华大学交叉信息研究院联合主办,腾讯云计算协办。共设置题库16000条数据,总奖金池30万元,且腾讯云计算为中学组赛道提供独家算力资源支持。

本次比赛的数据来自小学/中高考语文阅读理解题库(其中,技术组的数据主要为中高考语文试题,中学组的数据主要来自小学语文试题)。相较于英文,中文阅读理解有着更多的歧义性和多义性,然而璀璨的中华文明得以绵延数千年,离不开每一个时代里努力钻研、坚守传承的人,这也正是本次大赛的魅力与挑战,让机器读懂文字,让机器学习文明。秉承着人才培养的初心,我们继续保留针对中学组以及技术组的两条平行赛道,科技创新,时代有我,期待你们的回响。

比赛任务

本次比赛技术组的数据来自中高考语文阅读理解题库。每条数据都包括一篇文章,至少一个问题和多个候选选项。参赛选手需要搭建模型,从候选选项中选出正确的一个。

2021海华AI挑战赛·中文阅读理解·技术组 第三名(ATTOY团队)解决方案

算法方案

1.预训练模型:MacBERT-Large

2.对抗训练

FreeLB ICLR 2020

3.知识蒸馏

Born Again Neural Networks ICML 2018

环境要求

tqdm==4.50.2 numpy==1.19.2 pandas==1.1.3 transformers==3.5.1 torch==1.7.0+cu110 scikit_learn==0.24.2

运行方法

bash bash.sh

超参数

FreeLB训练参数配置

'fold_num': 4, 
'seed': 42,
'model': 'hfl/chinese-macbert-large', 
'max_len': 512, 
'epochs': 12,
'train_bs': 4, 
'valid_bs': 4,
'lr': 2e-5,  
'lrSelf': 1e-4,  
'accum_iter': 8, 
'weight_decay': 1e-4, 
'adv_lr': 0.01,
'adv_norm_type': 'l2',
'adv_init_mag': 0.03,
'adv_max_norm': 1.0,
'ip': 2

EKD训练参数配置

'fold_num': 4, 
'seed': 42,
'model': 'hfl/chinese-macbert-large', 
'max_len': 256, 
'epochs': 12,
'train_bs': 4, 
'valid_bs': 4,
'lr': 2e-5,  
'lrSelf': 1e-4,  
'accum_iter': 8, 
'weight_decay': 1e-4, 
'adv_lr': 0.01,
'adv_norm_type': 'l2',
'adv_init_mag': 0.03,
'adv_max_norm': 1.0,
'ip': 2
Multilingual word vectors in 78 languages

Aligning the fastText vectors of 78 languages Facebook recently open-sourced word vectors in 89 languages. However these vectors are monolingual; mean

Babylon Health 1.2k Dec 17, 2022
基于pytorch+bert的中文事件抽取

pytorch_bert_event_extraction 基于pytorch+bert的中文事件抽取,主要思想是QA(问答)。 要预先下载好chinese-roberta-wwm-ext模型,并在运行时指定模型的位置。

西西嘛呦 31 Nov 30, 2022
문장단위로 분절된 나무위키 데이터셋. Releases에서 다운로드 받거나, tfds-korean을 통해 다운로드 받으세요.

Namuwiki corpus 문장단위로 미리 분절된 나무위키 코퍼스. 목적이 LM등에서 사용하기 위한 데이터셋이라, 링크/이미지/테이블 등등이 잘려있습니다. 문장 단위 분절은 kss를 활용하였습니다. 라이선스는 나무위키에 명시된 바와 같이 CC BY-NC-SA 2.0

Jeong Ukjae 16 Apr 02, 2022
Ukrainian TTS (text-to-speech) using Coqui TTS

title emoji colorFrom colorTo sdk app_file pinned Ukrainian TTS 🐸 green green gradio app.py false Ukrainian TTS 📢 🤖 Ukrainian TTS (text-to-speech)

Yurii Paniv 85 Dec 26, 2022
Simple Python script to scrape youtube channles of "Parity Technologies and Web3 Foundation" and translate them to well-known braille language or any language

Simple Python script to scrape youtube channles of "Parity Technologies and Web3 Foundation" and translate them to well-known braille language or any

Little Endian 1 Apr 28, 2022
SimCSE: Simple Contrastive Learning of Sentence Embeddings

SimCSE: Simple Contrastive Learning of Sentence Embeddings This repository contains the code and pre-trained models for our paper SimCSE: Simple Contr

Princeton Natural Language Processing 2.5k Jan 07, 2023
Deeply Supervised, Layer-wise Prediction-aware (DSLP) Transformer for Non-autoregressive Neural Machine Translation

Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervision Training Efficiency We show the training efficiency of our DSLP model b

Chenyang Huang 37 Jan 04, 2023
fastNLP: A Modularized and Extensible NLP Framework. Currently still in incubation.

fastNLP fastNLP是一款轻量级的自然语言处理(NLP)工具包,目标是快速实现NLP任务以及构建复杂模型。 fastNLP具有如下的特性: 统一的Tabular式数据容器,简化数据预处理过程; 内置多种数据集的Loader和Pipe,省去预处理代码; 各种方便的NLP工具,例如Embedd

fastNLP 2.8k Jan 01, 2023
Speach Recognitions

easy_meeting Добро пожаловать в интерфейс сервиса автопротоколирования совещаний Easy Meeting. Website - http://cf5c-62-192-251-83.ngrok.io/ Принципиа

Maksim 3 Feb 18, 2022
The guide to tackle with the Text Summarization

The guide to tackle with the Text Summarization

Takahiro Kubo 1.2k Dec 30, 2022
SciBERT is a BERT model trained on scientific text.

SciBERT is a BERT model trained on scientific text.

AI2 1.2k Dec 24, 2022
Code for evaluating Japanese pretrained models provided by NTT Ltd.

japanese-dialog-transformers 日本語の説明文はこちら This repository provides the information necessary to evaluate the Japanese Transformer Encoder-decoder dialo

NTT Communication Science Laboratories 216 Dec 22, 2022
Universal End2End Training Platform, including pre-training, classification tasks, machine translation, and etc.

背景 安装教程 快速上手 (一)预训练模型 (二)机器翻译 (三)文本分类 TenTrans 进阶 1. 多语言机器翻译 2. 跨语言预训练 背景 TrenTrans是一个统一的端到端的多语言多任务预训练平台,支持多种预训练方式,以及序列生成和自然语言理解任务。 安装教程 git clone git

Tencent Minority-Mandarin Translation Team 42 Dec 20, 2022
Integrating the Best of TF into PyTorch, for Machine Learning, Natural Language Processing, and Text Generation. This is part of the CASL project: http://casl-project.ai/

Texar-PyTorch is a toolkit aiming to support a broad set of machine learning, especially natural language processing and text generation tasks. Texar

ASYML 726 Dec 30, 2022
Python wrapper for Stanford CoreNLP tools v3.4.1

Python interface to Stanford Core NLP tools v3.4.1 This is a Python wrapper for Stanford University's NLP group's Java-based CoreNLP tools. It can eit

Dustin Smith 610 Sep 07, 2022
An open-source NLP research library, built on PyTorch.

An Apache 2.0 NLP research library, built on PyTorch, for developing state-of-the-art deep learning models on a wide variety of linguistic tasks. Quic

AI2 11.4k Jan 01, 2023
PhoNLP: A BERT-based multi-task learning toolkit for part-of-speech tagging, named entity recognition and dependency parsing

PhoNLP is a multi-task learning model for joint part-of-speech (POS) tagging, named entity recognition (NER) and dependency parsing. Experiments on Vietnamese benchmark datasets show that PhoNLP prod

VinAI Research 109 Dec 02, 2022
CLIPfa: Connecting Farsi Text and Images

CLIPfa: Connecting Farsi Text and Images OpenAI released the paper Learning Transferable Visual Models From Natural Language Supervision in which they

Sajjad Ayoubi 66 Dec 14, 2022
Generate custom detailed survey paper with topic clustered sections and proper citations, from just a single query in just under 30 mins !!

Auto-Research A no-code utility to generate a detailed well-cited survey with topic clustered sections (draft paper format) and other interesting arti

Sidharth Pal 20 Dec 14, 2022
Model for recasing and repunctuating ASR transcripts

Recasing and punctuation model based on Bert Benoit Favre 2021 This system converts a sequence of lowercase tokens without punctuation to a sequence o

Benoit Favre 88 Dec 29, 2022