quyingqi / Kbqa Ar Smcnn
Licence: apache-2.0
Question answering over Freebase (single-relation)
Stars: ✭ 129
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Kbqa Ar Smcnn
Neural kbqa
Knowledge Base Question Answering using memory networks
Stars: ✭ 87 (-32.56%)
Mutual labels: question-answering
Ama
[[I'm slow at replying these days, but I hope to get back to answering questions eventually]] Ask me anything!
Stars: ✭ 102 (-20.93%)
Mutual labels: question-answering
Clicr
Machine reading comprehension on clinical case reports
Stars: ✭ 123 (-4.65%)
Mutual labels: question-answering
Sentence Similarity
PyTorch implementations of various deep learning models for paraphrase detection, semantic similarity, and textual entailment
Stars: ✭ 96 (-25.58%)
Mutual labels: question-answering
Flexneuart
Flexible classic and NeurAl Retrieval Toolkit
Stars: ✭ 99 (-23.26%)
Mutual labels: question-answering
Tableqa
AI Tool for querying natural language on tabular data.
Stars: ✭ 109 (-15.5%)
Mutual labels: question-answering
Dan Jurafsky Chris Manning Nlp
My solution to the Natural Language Processing course made by Dan Jurafsky, Chris Manning in Winter 2012.
Stars: ✭ 124 (-3.88%)
Mutual labels: question-answering
Reading Comprehension Question Answering Papers
Survey on Machine Reading Comprehension
Stars: ✭ 101 (-21.71%)
Mutual labels: question-answering
Haystack
🔍 Haystack is an open source NLP framework that leverages Transformer models. It enables developers to implement production-ready neural search, question answering, semantic document search and summarization for a wide range of applications.
Stars: ✭ 3,409 (+2542.64%)
Mutual labels: question-answering
Happy Transformer
A package built on top of Hugging Face's transformer library that makes it easy to utilize state-of-the-art NLP models
Stars: ✭ 97 (-24.81%)
Mutual labels: question-answering
Neuronblocks
NLP DNN Toolkit - Building Your NLP DNN Models Like Playing Lego
Stars: ✭ 1,356 (+951.16%)
Mutual labels: question-answering
Bi Att Flow
Bi-directional Attention Flow (BiDAF) network is a multi-stage hierarchical process that represents context at different levels of granularity and uses a bi-directional attention flow mechanism to achieve a query-aware context representation without early summarization.
Stars: ✭ 1,472 (+1041.09%)
Mutual labels: question-answering
Caseinterviewquestions
PHPer case interview questions
Stars: ✭ 96 (-25.58%)
Mutual labels: question-answering
Dynamic Memory Networks Plus Pytorch
Implementation of Dynamic memory networks plus in Pytorch
Stars: ✭ 123 (-4.65%)
Mutual labels: question-answering
Simple Qa Emnlp 2018
Code for my EMNLP 2018 paper "SimpleQuestions Nearly Solved: A New Upperbound and Baseline Approach"
Stars: ✭ 87 (-32.56%)
Mutual labels: question-answering
Medquad
Medical Question Answering Dataset of 47,457 QA pairs created from 12 NIH websites
Stars: ✭ 129 (+0%)
Mutual labels: question-answering
Knowledge Aware Reader
PyTorch implementation of the ACL 2019 paper "Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader"
Stars: ✭ 123 (-4.65%)
Mutual labels: question-answering
Dynamic Coattention Network Plus
Dynamic Coattention Network Plus (DCN+) TensorFlow implementation. Question answering using Deep NLP.
Stars: ✭ 117 (-9.3%)
Mutual labels: question-answering
kbqa-ar-smcnn
Question answering over Freebase (single-relation).
This is the source code for Question Answering over Freebase via Attentive RNN with Similarity Matrix based CNN.
Install packages
- Python 3.5
- PyTorch 0.2.0
- NLTK
- NLTK data (tokenizers, stopwords list)
- Virtuoso
After install Virtuoso, you should modify config file at freebase_data/dump_virtuoso_data/virtuoso.ini (or you could copy your virtuoso.ini file to this directory)
- You have to change the variables such as NumberOfBuffers and MaxDirtyBuffers depending on your RAM. For other variables you can follow the official documents.
- Add the absolute path of XXX/freebase_data/dump_virtuoso_data/ to DirsAllowed.
Start the Virtuoso server
This may need to be under the root user.
virtuoso-t +foreground +configfile freebase_data/dump_virtuoso_data/virtuoso.ini &
Set up
Run the setup script. This takes a long time. It fetches datasets, does some preprocesses, and dumps Freebase triples into Virtuoso.
sh data_setup.sh
Training
- entity detection model
cd entity_detection
sh process.sh
python predict.py --trained_model XXX --results_path results --save_qadata
- relation detection model
cd relation_ranking
python seqRankingLoader.py --batch_size 64 --neg_size 50 #Create training data for relation detection
sh process.sh
python predict.py --trained_model XXX --results_path results --predict
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].