DouYishun / Kb Qa
基于知识库的中文问答系统(biLSTM)
Stars: ✭ 195
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Kb Qa
Yolov3 Tf2
YoloV3 Implemented in Tensorflow 2.0
Stars: ✭ 2,327 (+1093.33%)
Mutual labels: tensorflow-examples
Awesome Kgqa
A collection of some materials of knowledge graph question answering
Stars: ✭ 188 (-3.59%)
Mutual labels: question-answering
Rat Sql
A relation-aware semantic parsing model from English to SQL
Stars: ✭ 169 (-13.33%)
Mutual labels: question-answering
Tensorflow In Practice Code
源码实现:《TensorFlow实战》黄文坚,唐源 著
Stars: ✭ 176 (-9.74%)
Mutual labels: tensorflow-examples
Awesomemrc
This repo is our research summary and playground for MRC. More features are coming.
Stars: ✭ 162 (-16.92%)
Mutual labels: question-answering
Openqa
The source code of ACL 2018 paper "Denoising Distantly Supervised Open-Domain Question Answering".
Stars: ✭ 188 (-3.59%)
Mutual labels: question-answering
Questgen.ai
Question generation using state-of-the-art Natural Language Processing algorithms
Stars: ✭ 169 (-13.33%)
Mutual labels: question-answering
Triviaqa
Code for the TriviaQA reading comprehension dataset
Stars: ✭ 184 (-5.64%)
Mutual labels: question-answering
Improved Dynamic Memory Networks Dmn Plus
Theano Implementation of DMN+ (Improved Dynamic Memory Networks) from the paper by Xiong, Merity, & Socher at MetaMind, http://arxiv.org/abs/1603.01417 (Dynamic Memory Networks for Visual and Textual Question Answering)
Stars: ✭ 165 (-15.38%)
Mutual labels: question-answering
Fed Note
我是Mokou, 📘 这里是写前端博客和备忘学习的地方。Vue3 源码解析连载中。喜欢请Star。
Stars: ✭ 180 (-7.69%)
Mutual labels: knowledge
Flowqa
Implementation of conversational QA model: FlowQA (with slight improvement)
Stars: ✭ 194 (-0.51%)
Mutual labels: question-answering
Simpletransformers
Transformers for Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI
Stars: ✭ 2,881 (+1377.44%)
Mutual labels: question-answering
Learn Anything
Organize world's knowledge, explore connections and curate learning paths
Stars: ✭ 13,532 (+6839.49%)
Mutual labels: knowledge
Knowledge-Based Question Answering
基于知识库的中文问答系统. 整体流程如下:
-
根据Background和Question寻找到最相关的K个Knowledge,
K Knowledge+Background+Question
构成一个大问题
. -
正确选项
分别与该问题中所有错误选项
组合,构成3个答案组合,分别与大问题
组合构成3个样例,采用余弦距离计算大问题
与正确选项
和错误选项
的相似度.正确选项相似度为t_sim, 错误选项相似度为f_sim,损失函数为
loss = max(0, margin - t_sim + f_sim)
Model
- 寻找相关Knowledge: LSI
- 训练: biLSTM
Requirement
- python3, tensorflow
- stop_words, 中文word2vec(a2u6)
Data Format
-
knowledge
地球是宇宙中的一颗行星,有自己的运动规律。 地球上的许多自然现象都与地球的运动密切相关。 地球具有适合生命演化和人类发展的条件,因此,它成为人类在宇宙中的唯一家园。 ...
-
train&test
问题为选择题,每个问题的格式为
Background, Question, Right, Wrong, Wrong, Wrong
.B:近年来,我国有些农村出现了“有院无人住,有地无人种”的空心化现象。 Q:“有院无人住,有地无人种”带来 R:土地资源浪费 W:农业发展水平提高 W:城乡协调发展 W:农村老龄化程度降低 B:广东省佛山市三水区被称为“中国饮料之都”。除青岛啤酒、伊利等国内著名饮料企业抢先布局外,百威、红牛、可口可乐、杨协成等国际巨头也先后落户于此,作为其在中国布局中的重要一环。 Q:众多国际饮料企业选址三水的主导区位因素是 R:市场 W:技术 W:劳动力 W:原料 B:凡是大气中因悬浮的水汽凝结,能见度低于1千米时,气象学称这种天气现象为雾 Q:深秋到第二年初春,晴朗的夜晚容易形成雾,这主要是因为 R:晴朗的夜晚大气逆辐射弱,近地面降温快 W:晴天大气中的水汽含量多 W:晴朗的夜晚地面水汽蒸发强 W:晴天大气中的凝结核物质较少 ...
Usage
python3 train.py
该数据集下最佳参数为
- dropout:0.45
- k:0.5
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].