zihangdai / cfo Goto Github PK

View Code? Open in Web Editor NEW

83.0 9.0 34.0 470 KB

Conditional Focused Neural Question Answering with Large-scale Knowledge Bases

Lua 63.70% Python 32.21% Shell 4.09%

cfo's Introduction

CFO

Code repo for Conditional Focused Neural Question Answering with Large-scale Knowledge Bases

Installation and Preprocessing

Refer to Virtuoso.md to install and confiture the software
Make sure torch7 is installed together with the following dependencies
- logroll: luarocks install logroll
- nngraph: luarocks install nngraph
After the installation and configuration of Virtuoso, run bash data_preprocess.sh to finish preprocessing

Training

Focused Lableing
```
cd FocusedLabeling
th train_crf.lua
```

Entity Type Vector

cd EntityTypeVec
th train_ent_typevec.lua

RNN based Relation Network
```
cd RelationRNN
th train_rel_rnn.lua
```

Inference

In the following, define SPLIT='valid' or 'test'.

Run focused labeling on validation/test data
```
cd FocusedLabeling

python generate_inference_data.py --split ${SPLIT}

th process_inference.lua -testSplit ${SPLIT}
th infer_crf.lua \
    -testData inference-data/label.${SPLIT}.t7 \
    -modelFile "path-to-pretrained-model"
```
- python generate_inference_data.py --split ${SPLIT} will create the file label.${SPLIT}.txt in the folder FocusedLabeling/inference-data;
- th process_inference.lua will turn the text file label.${SPLIT}.txt into label.${SPLIT}.t7 in torch format (both in the folder FocusedLabeling/inference-data);
- th infer_crf.lua ... will generate the file label.result.${SPLIT} in the folder FocusedLabeling.

Query candidates based on focused labeling

cd Inference
mkdir ${SPLIT} && cd ${SPLIT}
python ../query_candidates.py 6 \
       ../../PreprocessData/QAData.${SPLIT}.pkl \
       ../../FocusedLabeling/label.result.${SPLIT} \
       ../../KnowledgeBase/type.top-500.pkl

This step will generate the file QAData.label.${SPLIT}.cpickle in the folder Inference/${SPLIT}.

Generate score data based on the query results
```
cd Inference/${SPLIT}
python ../generate_score_data.py QAData.label.${SPLIT}.cpickle
```
This step will generate the following files in the same folder Inference/${SPLIT}:
- rel.single.${SPLIT}.txt (candidate relations for those with only a single candidate subject)
- rel.multi.${SPLIT}.txt (candidate relations for those with only multiple candidate subject)
- type.multi.${SPLIT}.txt (candidate entities for those with multiple candidate subjects)
- single.${SPLIT}.cpickle
- multi.${SPLIT}.cpickle

Run relation inference

cd RelationRNN
mkdir inference-data
th process_inference.lua -testSplit ${SPLIT}
th infer_rel_rnn.lua -testData inference-data/rel.single.${SPLIT}.t7
th infer_rel_rnn.lua -testData inference-data/rel.multi.${SPLIT}.t7

This step will generate the files score.rel.single.${SPLIT} and score.rel.multi.${SPLIT} in the folder RelationRNN.

Run entity inference

cd EntityTypeVec
mkdir inference-data
th process_inference.lua -testSplit ${SPLIT}
th infer_ent_typevec.lua -testData inference-data/ent.${SPLIT}.t7

This step will generate the file score.ent.multi.multi.${SPLIT} in the folder EntityTypeVec.

Run joint disambiguation

cd Inference/${SPLIT}
python ../joint_disambiguation.py multi.${SPLIT}.cpickle \
       ../../RelationRNN/score.rel.multi.${SPLIT} \
       ../../EntityTypeVec/score.ent.multi.multi.${SPLIT}

cfo's People

Contributors

Stargazers

Watchers

cfo's Issues

how to installation and configuration of Virtuoso

Cannot run train_crf.lua

After pre-processing, I have encountered a problem when I am trying to run train_crf.lua.

The feedback in the system is:

/home/sy/torch/install/bin/luajit: /home/sy/virtuoso-opensource/src/model/CRF.lua:192: invalid arguments: DoubleTensor number DoubleTensor
expected arguments: [DoubleTensor] DoubleTensor index LongTensor
stack traceback:
[C]: in function 'gather'
/home/sy/virtuoso-opensource/src/model/CRF.lua:192: in function 'forward'
train_crf.lua:130: in main chunk
[C]: in function 'dofile'
...e/sy/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: at 0x004064f0

Could you please help me figure it out?

problems about Inference

When running generate_score_data.py under Inference folder, it required cand_rel and can_sub attributes.

if hasattr(data, 'cand_sub') and hasattr(data, 'cand_rel') and len(data.cand_rel) > 0 and data.relation in data.cand_rel and data.subject in data.cand_sub:

So I found it can generate these two attributes by query_candidates.py in the same folder, but i requires these documents

print 'usage: python query_candidate_relation.py num_processes QAData_cpickle_file attention_score_file [[type_dict]]'

Could anyone tell me how to get attention _score_file ?
Or how to get pickle file containing cand_sub and cand_rel attribute?

Issues for RelationRNN training, maxSeqLen and zero loss or infinity loss

If using the default maxSeqLen, one will get the cublas runtime error

➜  RelationRNN git:(master) ✗ th train_rel_rnn.lua               
[INFO - 2018_05_02_20:11:11] - "--------------------------------------------------"
[INFO - 2018_05_02_20:11:11] - "SeqRankingLoader Configurations:"
[INFO - 2018_05_02_20:11:11] - "    number of batch : 296"
[INFO - 2018_05_02_20:11:11] - "    data batch size : 256"
[INFO - 2018_05_02_20:11:11] - "    neg sample size : 1024"
[INFO - 2018_05_02_20:11:11] - "    neg sample range: 7524"
[INFO - 2018_05_02_20:11:11] - "--------------------------------------------------"
[INFO - 2018_05_02_20:11:11] - "BiGRU Configuration:"
[INFO - 2018_05_02_20:11:11] - "    inputSize   :   300"
[INFO - 2018_05_02_20:11:11] - "    hiddenSize  :   256"
[INFO - 2018_05_02_20:11:11] - "    maxSeqLen   :    40"
[INFO - 2018_05_02_20:11:11] - "    maxBatch    :   256"
[INFO - 2018_05_02_20:11:11] - "--------------------------------------------------"
[INFO - 2018_05_02_20:11:11] - "BiGRU Configuration:"
[INFO - 2018_05_02_20:11:11] - "    inputSize   :   512"
[INFO - 2018_05_02_20:11:11] - "    hiddenSize  :   256"
[INFO - 2018_05_02_20:11:11] - "    maxSeqLen   :    40"
[INFO - 2018_05_02_20:11:11] - "    maxBatch    :   256"
/home/vimos/.torch/install/bin/luajit: /home/vimos/.torch/install/share/lua/5.1/nn/Container.lua:67: 
In 5 module of nn.Sequential:
/home/vimos/Data/git/QA/CFO/src/model/BiGRU.lua:241: cublas runtime error : an internal operation failed at /home/vimos/.torch/extra/cutorch/lib/THC/THCBlas.cu:246
stack traceback:
	[C]: in function 'mm'
	/home/vimos/Data/git/QA/CFO/src/model/BiGRU.lua:241: in function 'updateGradInput'
	/home/vimos/.torch/install/share/lua/5.1/nn/Module.lua:31: in function </home/vimos/.torch/install/share/lua/5.1/nn/Module.lua:29>
	[C]: in function 'xpcall'
	/home/vimos/.torch/install/share/lua/5.1/nn/Container.lua:63: in function 'rethrowErrors'
	/home/vimos/.torch/install/share/lua/5.1/nn/Sequential.lua:84: in function 'backward'
	train_rel_rnn.lua:174: in main chunk
	[C]: in function 'dofile'
	...mos/.torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
	[C]: at 0x559ae9bad710

WARNING: If you see a stack trace below, it doesn't point to the place where this error occurred. Please use only the one above.
stack traceback:
	[C]: in function 'error'
	/home/vimos/.torch/install/share/lua/5.1/nn/Container.lua:67: in function 'rethrowErrors'
	/home/vimos/.torch/install/share/lua/5.1/nn/Sequential.lua:84: in function 'backward'
	train_rel_rnn.lua:174: in main chunk
	[C]: in function 'dofile'
	...mos/.torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
	[C]: at 0x559ae9bad710
THCudaCheckWarn FAIL file=/home/vimos/.torch/extra/cutorch/lib/THC/THCStream.cpp line=50 error=77 : an illegal memory access was encountered
THCudaCheckWarn FAIL file=/home/vimos/.torch/extra/cutorch/lib/THC/THCStream.cpp line=50 error=77 : an illegal memory access was encountered

But this problem can be fixed by using a larger maxSeqLen

➜  RelationRNN git:(master) ✗ th train_rel_rnn.lua -maxSeqLen 42
[INFO - 2018_05_02_20:11:52] - "--------------------------------------------------"
[INFO - 2018_05_02_20:11:52] - "SeqRankingLoader Configurations:"
[INFO - 2018_05_02_20:11:52] - "    number of batch : 296"
[INFO - 2018_05_02_20:11:52] - "    data batch size : 256"
[INFO - 2018_05_02_20:11:52] - "    neg sample size : 1024"
[INFO - 2018_05_02_20:11:52] - "    neg sample range: 7524"
[INFO - 2018_05_02_20:11:52] - "--------------------------------------------------"
[INFO - 2018_05_02_20:11:52] - "BiGRU Configuration:"
[INFO - 2018_05_02_20:11:52] - "    inputSize   :   300"
[INFO - 2018_05_02_20:11:52] - "    hiddenSize  :   256"
[INFO - 2018_05_02_20:11:52] - "    maxSeqLen   :    42"
[INFO - 2018_05_02_20:11:52] - "    maxBatch    :   256"
[INFO - 2018_05_02_20:11:52] - "--------------------------------------------------"
[INFO - 2018_05_02_20:11:52] - "BiGRU Configuration:"
[INFO - 2018_05_02_20:11:52] - "    inputSize   :   512"
[INFO - 2018_05_02_20:11:52] - "    hiddenSize  :   256"
[INFO - 2018_05_02_20:11:52] - "    maxSeqLen   :    42"
[INFO - 2018_05_02_20:11:52] - "    maxBatch    :   256"
[INFO - 2018_05_02_20:11:56] - "iter  100, loss = 0.00198258"........] ETA: 3h29m | Step: 42ms       
[INFO - 2018_05_02_20:12:00] - "iter  200, loss = 0.00000000"........] ETA: 3h25m | Step: 41ms       
[INFO - 2018_05_02_20:12:04] - "epoch   1, loss 0.00066979"..........] ETA: 3h28m | Step: 42ms       
[INFO - 2018_05_02_20:12:04] - "iter  300, loss = 0.00000000"........] ETA: 3h27m | Step: 42ms       
[INFO - 2018_05_02_20:12:09] - "iter  400, loss = 0.00000000"........] ETA: 3h28m | Step: 42ms       
[INFO - 2018_05_02_20:12:13] - "iter  500, loss = 0.00000000"........] ETA: 3h25m | Step: 41ms       
[INFO - 2018_05_02_20:12:17] - "epoch   2, loss 0.00000000"..........] ETA: 3h26m | Step: 41ms       
[INFO - 2018_05_02_20:12:17] - "iter  600, loss = 0.00000000"........] ETA: 3h26m | Step: 41ms       
[INFO - 2018_05_02_20:12:21] - "iter  700, loss = 0.00000000"........] ETA: 3h28m | Step: 42ms       
[INFO - 2018_05_02_20:12:25] - "iter  800, loss = 0.00000000"........] ETA: 3h27m | Step: 42ms       
[INFO - 2018_05_02_20:12:29] - "epoch   3, loss 0.00000000"..........] ETA: 3h25m | Step: 41ms       
[INFO - 2018_05_02_20:12:30] - "iter  900, loss = 0.00000000"........] ETA: 3h25m | Step: 41ms       
[INFO - 2018_05_02_20:12:34] - "iter 1000, loss = 0.00000000"........] ETA: 3h27m | Step: 42ms

But the loss will be 0 after the 1 epoch or become infinity

➜  RelationRNN git:(master) ✗ th train_rel_rnn.lua -maxSeqLen 42 -seed 12
[INFO - 2018_05_02_20:26:49] - "--------------------------------------------------"
[INFO - 2018_05_02_20:26:49] - "SeqRankingLoader Configurations:"
[INFO - 2018_05_02_20:26:49] - "    number of batch : 296"
[INFO - 2018_05_02_20:26:49] - "    data batch size : 256"
[INFO - 2018_05_02_20:26:49] - "    neg sample size : 1024"
[INFO - 2018_05_02_20:26:49] - "    neg sample range: 7524"
[INFO - 2018_05_02_20:26:49] - "--------------------------------------------------"
[INFO - 2018_05_02_20:26:49] - "BiGRU Configuration:"
[INFO - 2018_05_02_20:26:49] - "    inputSize   :   300"
[INFO - 2018_05_02_20:26:49] - "    hiddenSize  :   256"
[INFO - 2018_05_02_20:26:49] - "    maxSeqLen   :    42"
[INFO - 2018_05_02_20:26:49] - "    maxBatch    :   256"
[INFO - 2018_05_02_20:26:49] - "--------------------------------------------------"
[INFO - 2018_05_02_20:26:49] - "BiGRU Configuration:"
[INFO - 2018_05_02_20:26:49] - "    inputSize   :   512"
[INFO - 2018_05_02_20:26:49] - "    hiddenSize  :   256"
[INFO - 2018_05_02_20:26:49] - "    maxSeqLen   :    42"
[INFO - 2018_05_02_20:26:49] - "    maxBatch    :   256"
[INFO - 2018_05_02_20:26:53] - "iter  100, loss = 81231552070126006809284050944.00000000" 41ms       
[INFO - 2018_05_02_20:26:57] - "iter  200, loss = 0.00000000"........] ETA: 3h15m | Step: 39ms       
[INFO - 2018_05_02_20:27:01] - "epoch   1, loss 27443091915583111597203128320.00000000"p: 40ms       
[INFO - 2018_05_02_20:27:01] - "iter  300, loss = 0.00000000"........] ETA: 3h17m | Step: 40ms

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.

zihangdai / cfo Goto Github PK

cfo's Introduction

CFO

Installation and Preprocessing

Training

Inference

cfo's People

Contributors

Stargazers

Watchers

Forkers

cfo's Issues

how to installation and configuration of Virtuoso

Is there a Python version?

Cannot run train_crf.lua

problems about Inference

Issues for RelationRNN training, maxSeqLen and zero loss or infinity loss

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent