410 likes | 584 Views
Method Seminar. Tutorial : Using Stanford Topic Modeling Toolbox Lili Lin. Contents. Introduction Getting Started Prerequisites Installation Toolbox Running Latent Dirichlet Allocation Model (LDA Model) Labeled LDA Model. Contents. Introduction Getting Started
E N D
Method Seminar Tutorial : Using Stanford Topic Modeling Toolbox Lili Lin
Contents • Introduction • Getting Started • Prerequisites • Installation • Toolbox Running • Latent Dirichlet Allocation Model (LDA Model) • Labeled LDA Model
Contents • Introduction • Getting Started • Prerequisites • Installation • Toolbox Running • Latent Dirichlet Allocation Model (LDA Model) • Labeled LDA Model
Introduction • http://nlp.stanford.edu/software/tmt/tmt-0.4/ • The Stanford Topic Modeling Toolbox was written at the Stanford NLP group by: Daniel Ramage and Evan Rosen, first released in September 2009 • Topic models (e.g. LDA, Labeled LDA) training and inference to create summaries of the text
Introduction - LDA Model • LDA model is a unsupervised topic model • User need to define some important parameters, such as number of topics • It is hard to choose the number of topics • Even with some top terms for each topic, it is still difficult to interpret the content of the extracted topics
Introduction – Labeled LDA Model • Labeled LDA is a supervised topic model for credit attribution in multi-labeled corpora. • If one of the columns in your input text file contains labels or tags that apply to the document, you can use Labeled LDA to discover which parts of each document go with each label, and to learn accurate models of the words best associated with each label globally
Contents • Introduction • Getting Started • Prerequisites • Installation • Simple Testing • Toolbox Running • LDA Model • Labeled LDA Model
Prerequisites • A text editor (e.g. TextWrangler) for creating TMT processing scripts. • TMT scripts are written in Scala, but no knowledge of Scala is required to get started. • An installation of Java 6SE or greater: http://java.com/en/download/index.jsp. • Windows, Mac, and Linux are supported.
Installation • Download the TMT executable (tmt-0.4.0.jar) from http://nlp.stanford.edu/software/tmt/tmt-0.4/ • Double-click the jar file to open toolbox or run the toolbox with the command line : java -jar tmt-0.4.0.jar • You should see a simple GUI
SimpleTesting • Example data and scripts for simple testing • Download the example data file: pubmed-oa-subset.csv • Download the first testing script: example-0-test.scala • Note: the data file and the script should be put into the same folder
Simple Testing - GUI • Load script: File Open script
Simple Testing - GUI • Edit script: valpubmed = CSVFile("pubmed-oa-subset.csv”)
Simple Testing - GUI • Run the script: click the button ‘Run’
Contents • Introduction • Getting Started • Prerequisites • Installation • Toolbox Running • Latent Dirichlet Allocation Model (LDA Model) • Labeled LDA Model
LDA Model – Data Preparation • 173, 777 Astronomy papers were collected from the Web of Science (WOS) covering the period from 1992 to 2012 • In the file ‘astro_wos_lda.csv’, every record includes paper ID (the first column), title (the second column) and published year (the third column)
LDA Training – Script Loading • File Open script Navigate to example-2-lda-learn.scala Open
LDA Training – Data Loading • Edit Script : ‘valsource = CSVFile("astro_wos_lda.csv”)’ ‘Column(2) ~>’ • Note: if your text cover 2 columns or more than 2 columns, such as the third and forth columns, you can use ‘Columns(3,4) ~> Join(" ") ~>’ to replace ’Column(2) ~>’
LDA Training – Parameter Selection • Edit Script : valparams = LDAModelParams(numTopics = 30, dataset = dataset, topicSmoothing = 0.01, termSmoothing = 0.01)
LDA Training – Model Training • Run : Out of Memory due to the big data
LDA Training – Model Training • Change the size of Memory Run
LDA Training – Output Generation • lda-b2aa1797-30-751edefe • description.txt : A description of the model saved in this folder • document-topic-distributions.csv: A csv file containing the per-document topic distribution for each document in the training dataset • 00000-01000 : Snapshots of the model during training
LDA Training – Output Generation • /params.txt: Model parameters used during training • /tokenizer.txt: Tokenizer used to tokenize text for use with this model • /summary.txt: Human readable summary of the topic model, with top-20 terms per topic and how many words instances of each have occurred • /log-probability estimate.txt: Estimate of the log probability of the dataset at this iteration • /term-index.txt: Mapping from terms in the corpus to ID numbers • /description.txt: A description of the model saved in this iteration • /topic-termdistributions.csv.gz: For each topic, the probability of each term in that topic
LDA Training – Command Line • Java –Xmx4G –jar tmt-0.4.0.jar example-2-lda-learn.scala
LDA Inference – Script Loading • File Open script Navigate to example-3-lda-infer Open
LDA Inference – Trained Model Loading • Edit Script: valmodelPath = file("lda-b2aa1797-30-751edefe”)
LDA Inference – Data Loading • Edit Script: ‘val source = CSVFile("astro_wos_lda.csv”)’ ‘Column(2) ~>’ • Note: Here we just use the same dataset as the inference data, but actually it should be some new dataset
LDA Inference – Model Inference • Change the size of Memory Run
LDA Inference – Output Generation • Navigate to the folder ’lda-b2aa1797-30-751edefe’ • astro_wos_lda-document-topic-distributuions.csv : A csv file containing the per-document topic distribution for each document in the inference dataset • astro_wos_lda-top-terms.csv: A csv file containing the top terms in the inference dataset for each topic • astro_wos_lda-usage.csv
LDA Inference – Command Line • Java –Xmx4G –jar tmt-0.4.0.jar example-3-lda-infer.scala
LLDA Model – Data Preparation • 4,770 metformin papers were collected from pubMed covering the period from 1997 to 2011 • Training data : metformin_train_data_llda.csv(2798 papers), every record includes paper ID (the first column), bio-term list (the second column), title (the third column) and abstract (the forth column), the number of bio-terms in very record is at least 3 • Inference data:metformin_infer_data_llda.csv (4770 papers), every record includes paper ID (the first column), title (the second column) and abstract (the third column)
LLDA Training – Script Loading • File Open script Navigate to example-6-llda-learn.scala Open
LLDA Training – Data Loading • Edit Script : ‘valsource = CSVFile("metformin_train_data_llda.csv")’ ‘Columns(3,4) ~> Join(" ") ~>’ ’Column(2) ~>’
LLDA Training – Output Generation • llda-cvb0-bd54e9b6-176-1213c7f4-222a08a4 • description.txt: A description of the model saved in this folder • document-topic-distributions.csv: A csv file containing the per-document topic distribution for each document in the training dataset • 00000-01000 : Snapshots of the model during training
LLDA Training – Output Generation • /params.txt: Model parameters used during training • /tokenizer.txt: Tokenizer used to tokenize text for use with this model • /summary.txt: Human readable summary of the topic model, with top-20 terms per topic and how many words instances of each have occurred • /term-index.txt: Mapping from terms in the corpus to ID numbers • /description.txt: A description of the model saved in this iteration • /label-index.txt : Topics extracted after LLDA training • /topic-termdistributions.csv.gz: For each topic, the probability of each term in that topic
LLDA Training – Command Line • Java –Xmx4G –jar tmt-0.4.0.jar example-6-llda-learn.scala
LLDA Inference – Jar Script • The TMT toolbox doesn’t provide script for LLDA inference • A java script, packaged into ‘llda-infer.jar’, was generated in order to conduct LLDA inference
LLDA Inference – Command Line • java -jar llda-infer.jarmetformin_infer_data_llda.csv llda-cvb0-bd54e9b6-176-1213c7f4-222a08a4 metformin_infer_result.csv
LLDA Inference – Output Generation • A file named metformin_infer_result.csv will be generated after LLDA Inference
Thanks….. Any Question?