All Projects → mingdachen → gated-attention-reader

mingdachen / gated-attention-reader

Licence: other
Tensorflow/Pytorch implementation of Gated Attention Reader

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to gated-attention-reader

backprop
Backprop makes it simple to use, finetune, and deploy state-of-the-art ML models.
Stars: ✭ 229 (+518.92%)
Mutual labels:  question-answering
dialogbot
dialogbot, provide search-based dialogue, task-based dialogue and generative dialogue model. 对话机器人,基于问答型对话、任务型对话、聊天型对话等模型实现,支持网络检索问答,领域知识问答,任务引导问答,闲聊问答,开箱即用。
Stars: ✭ 96 (+159.46%)
Mutual labels:  question-answering
calcipher
Calculates the best possible answer for multiple-choice questions using techniques to maximize accuracy without any other outside resources or knowledge.
Stars: ✭ 15 (-59.46%)
Mutual labels:  question-answering
KitanaQA
KitanaQA: Adversarial training and data augmentation for neural question-answering models
Stars: ✭ 58 (+56.76%)
Mutual labels:  question-answering
Dynamic-Coattention-Network-for-SQuAD
Tensorflow implementation of DCN for question answering on the Stanford Question Answering Dataset (SQuAD)
Stars: ✭ 14 (-62.16%)
Mutual labels:  question-answering
HHH-An-Online-Question-Answering-System-for-Medical-Questions
HBAM: Hierarchical Bi-directional Word Attention Model
Stars: ✭ 44 (+18.92%)
Mutual labels:  question-answering
hf-experiments
Experiments with Hugging Face 🔬 🤗
Stars: ✭ 37 (+0%)
Mutual labels:  question-answering
verseagility
Ramp up your custom natural language processing (NLP) task, allowing you to bring your own data, use your preferred frameworks and bring models into production.
Stars: ✭ 23 (-37.84%)
Mutual labels:  question-answering
strategyqa
The official code of TACL 2021, "Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies".
Stars: ✭ 27 (-27.03%)
Mutual labels:  question-answering
FreebaseQA
The release of the FreebaseQA data set (NAACL 2019).
Stars: ✭ 55 (+48.65%)
Mutual labels:  question-answering
pair2vec
pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference
Stars: ✭ 62 (+67.57%)
Mutual labels:  question-answering
Instahelp
Instahelp is a Q&A portal website similar to Quora
Stars: ✭ 21 (-43.24%)
Mutual labels:  question-answering
TransTQA
Author: Wenhao Yu ([email protected]). EMNLP'20. Transfer Learning for Technical Question Answering.
Stars: ✭ 12 (-67.57%)
Mutual labels:  question-answering
GrailQA
No description or website provided.
Stars: ✭ 72 (+94.59%)
Mutual labels:  question-answering
Shukongdashi
使用知识图谱,自然语言处理,卷积神经网络等技术,基于python语言,设计了一个数控领域故障诊断专家系统
Stars: ✭ 109 (+194.59%)
Mutual labels:  question-answering
django-simple-forum
full featured forum, easy to integrate and use.
Stars: ✭ 65 (+75.68%)
Mutual labels:  question-answering
TeBaQA
A question answering system which utilises machine learning.
Stars: ✭ 17 (-54.05%)
Mutual labels:  question-answering
explicit memory tracker
[ACL 2020] Explicit Memory Tracker with Coarse-to-Fine Reasoning for Conversational Machine Reading
Stars: ✭ 35 (-5.41%)
Mutual labels:  question-answering
QANet
A TensorFlow implementation of "QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension"
Stars: ✭ 31 (-16.22%)
Mutual labels:  question-answering
BERT-for-Chinese-Question-Answering
No description or website provided.
Stars: ✭ 75 (+102.7%)
Mutual labels:  question-answering

GA-Reader

Tensorflow implementation of Gated Attention Reader for Text Comprehension. The original code can be found from here. For pytorch implementation, please check pytorch branch.

Prerequisites

  • Python 3.5
  • TensorFlow 1.0+
  • tqdm

Preprocessed Data

You can get the preprocessed data files from here.

You can also get the pretrained Glove vectors from the above link.

Training

python main.py --data_dir ~/data/dailymail --embed_file ~/data/word2vec_glove.txt

You should see around 0.7 accuracy on training set after running 1000 iteration (total 27486 iterations) on dailymail with default setting.

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].