README.md

## Temp2Vec
Master Thesis Project with Max Planck Institute for Informatik, Germany </br>
### Getting Started
These instructions will get you a copy of the project up and running on your local machine for development and testing purposes. </br>
### Prerequisites
Java 1.8 </br>
Apache Maven 3.3 </br>
IntelliJ IDEA 2016.3.4 </br>
MongoDB 3.2.1 </br>

### Installing
1. Install Java </br>
2. Install Maven </br>
3. IntelliJ IDEA </br>
4. Install MongoDB </br>

### Running the tests

#### Run BaseLine.AdamJatowt 
##### Steps: </br>
1. Metadata Collection </br>
example command line arguments : "local metadata true" </br>
2. Jaccard Distance Calculation </br> 
example command line arguments : "local jaccard" </br>
3. Context Association Calculation </br>
example command line arguments : "local conasso 1" </br>
4. Temporal Kurtosis Calculation </br>
example command line arguments : "local tempkurto 2" </br>
5. Focustime Calculation </br>
example command line arguments : "local focustime 3" </br>
In step 1</br>
-> args[0] = "local", if you want to run in your local machine. "global", if you want to run in server. Change properties file
to make necessary changes. </br>
-> args[1] = "metadata", the algorithmic step </br>
-> args[3] = "true/false", "true" if you want to run on only top 100,000 documents, "false" if you want to run on whole Gigaword</br> 
In steps, 2 to 5</br>
-> args[0] = "local", if you want to run in your local machine. "global", if you want to run in server. Change properties file
to make necessary changes. </br>
-> args[1] = "algorithmic step" </br>
-> args[2] = "query no." </br> 

#### Run BaseLine.AndreasSpitz 
##### Steps: </br>
1. Generate annotations for building a LOAD graph </br>
BaseLine.AndreasSpitz.Annotation.Annotation_App </br>
example command line arguments : "local" </br>
-> args[0] = "local", if you want to run in your local machine. "global", if you want to run in server. Change properties file
to make necessary changes.</br> 
2. Create a database in mongodb. Insert the generated sentence annotations and NER annotations in two different collections. Change the SystemSettings in Settings package.</br>
3. Build the LOAD graph </br> 
BaseLine.AndreasSpitz.Construction.ParallelExtractNetworkFromMongo </br>
-> Change folder location in BaseLine.AndreasSpitz.SystemSettings to point where you need to build the graph </br>
4. Query the graph </br>
BaseLine.AndreasSpitz.GraphQuery.GraphQueryInterface </br>
-> Point this program the location of your graph </br> 

#### Run ThesisWork
##### Steps: </br>
1. Generate vectors using Word2Vec from your corpus </br>
ThesisWork.WordVectorCreator.VectorCreator </br>
Example command line arguments : "local 300 part" </br>
-> args[0] = "local", if you want to run in your local machine. "global", if you want to run in server. Change config.properties file
to make necessary changes. </br> 
-> args[1] = "300" indicates the vector size you want. </br> 
-> args[2] = "part", if you want to create the vector on top 100,000 documents retrieved by 100 queries and args[2] = "full" if you want to run on total Gigaword corpus</br> 

2. Query temporal information </br> 
ThesisWork.PseudoRelevanceApp </br>
-> example command line arguments : "3 sumtfScore local LateFusion 300 0.2" </br>
-> args[0] = QueryNo </br>
-> args[1] = Craftmanship sub model </br>
-> args[2] = Environment (local/global depends on where you want to run local_machine/server) </br>
-> args[3] = Craftmanship model </br>
-> args[4] = Vector Size </br>
-> args[5] = lambda (weight on global vector in fraction to pseudo-relevant vector) </br>

### Authors </br>

#### Baseline: </br>
Package : BaseLine.AdamJatowt </br>
Author : Supratim Das </br>
Literature : "Estimating Document Focus Time" by Adam Jatowt et al. CIKM'13 </br>

#### Baseline: </br>
Package : BaseLine.AndreasSpitz </br>
Author : Andreas Spitz (Maven Packaging & BaseLine.Annotation package by Supratim Das) </br>
Literature : "Terms over LOAD: Leveraging Named Entities for Cross-Document Extraction and Summarization of Events" by Adam Jatowt et al. SIGIR'16 </br>

#### Main Thesis Project: </br>
Package : ThesisWork </br>
Author : Supratim Das </br>
Literature : Yet to be written ;)

### License
This project is licensed under the MIT License - see the [LICENSE.md](LICENSE.md) file for details </br>

### Acknowledgments
* Thesis Supervisor : Dr. Klaus Berberich <http://people.mpi-inf.mpg.de/~kberberi/> </br>
* Thesis Advisor : Arunav Mishra <http://people.mpi-inf.mpg.de/~amishra/> </br>
* Thesis Advisor : Vinay Setty <http://vbn.aau.dk/en/persons/vinay-jayarama-setty(b23ea8ea-1b2f-4d23-9908-693ac76d4be5).html> </br>