Go to Product
This node builds a dictionary from a pre-categorized list of text documents which can then be used to categorize new, uncategorized text documents. This learner builds a weighted term look up table, to learn how probable each n-gram is for a given category. This look up table is used by the corresponding predictor node.
This classifier won the first Research Garden competition where the goal was to classify product descriptions into eight different categories. See press release (on archive.org).
Feature Settings
Features are the input for a classifier. In text classification, we have a long string as an input from which we need to derive features during preprocessing. Palladian’s text classifier works with n-grams. n-grams are sets of tokens of the length n, which are created by sliding a “window” over the given text. The PalladianTextClassifierLearner node can create features using character- or word-based n-grams. As an example, consider the text “the quick brown fox”:- The set of word-based 2-grams would contain the following entries: {“the quick”, “quick brown”, “brown fox”}.
- The set of character-5-grams consists of the following entries: {“the q”, “he qu”, “e qui”, “ quic”, “quick”, …}.
- It is possible to combine n-grams of different lengths. For example, the set of character-4-6-grams contains the union of the sets of 4-, 5-, and 6-grams.
Options
Language-specific settings
Expert settings
Popular Predecessors
Joiner4 %- String Manipulation4 %
Column Rename3 %- Topic Extractor (Parallel LDA)3 %
- Concatenate3 %
- GroupBy3 %
- Sorter3 %
CSV Reader2 %- FeatureTextReader2 %
Cell Splitter2 %Row Splitter (deprecated)2 %- Missing Value2 %
Excel Reader (XLS)2 %Table Row to Variable2 %- Excel Reader2 %
File Reader2 %- Equal Size Sampling2 %
Row Filter (deprecated)2 %- Partitioning2 %
XLS Reader2 %- Text Classifier Model Pruner2 %
- Table Creator2 %
- Python Source (legacy)2 %
- Cell Splitter2 %
- Column Filter1 %
- Row Sampling1 %
Excel Reader (XLS)1 %- HTML Parser1 %
- SMOTE1 %
- CSV Reader1 %
- Constant Value Column< 1 %
- Column Splitter< 1 %
- DL4J Feedforward Predictor (Classification) (legacy)< 1 %
- Category to Class< 1 %
- Punctuation Erasure< 1 %
Strings To Document< 1 %- Strings to Document< 1 %
- Table Editor (JavaScript)< 1 %
Loop End< 1 %Counting Loop Start< 1 %Random Forest Learner< 1 %- Column Merger< 1 %
- Tika Language Detector< 1 %
- Snowball Stemmer< 1 %
- PDF Parser< 1 %
- URL Extractor< 1 %
Number To String< 1 %- Filter Apply< 1 %
- Ungroup< 1 %
- Replacer< 1 %
Stop Word Filter< 1 %- XPath< 1 %
- Text Classifier Predictor< 1 %
- AP Calculator< 1 %
- HTML Node to Text< 1 %
- Joiner< 1 %
- RegEx Filter< 1 %
Active Learn Loop Start< 1 %- Decision Tree Predictor< 1 %
K Nearest Neighbor< 1 %Scorer< 1 %- Auto-Binner< 1 %
- Case Converter< 1 %
- Cross Joiner< 1 %
- Reference Row Filter< 1 %
- Unpivot< 1 %
- Rule-based Row Filter< 1 %
- Cache< 1 %
- Similarity Search< 1 %
- Math Formula< 1 %
- Chi-Square Keyword Extractor< 1 %
- Keygraph Keyword Extractor< 1 %
- Dictionary Filter< 1 %
Document Data Extractor< 1 %- Document Data Extractor< 1 %
- Dataset Reader< 1 %
- Read Variables< 1 %
- Labeling View< 1 %
- Extract Variables (Data)< 1 %
Table Column to Variable< 1 %Table Row to Variable< 1 %Table Row To Variable Loop Start< 1 %Parameterized Database Query< 1 %List Files< 1 %Generic Loop Start< 1 %- X-Partitioner< 1 %
- Fuzzy c-Means< 1 %
- Hierarchical Clustering< 1 %
- Association Rule Learner< 1 %
- Random Forest Predictor< 1 %
- Create Bit Vector< 1 %
- Column Combiner< 1 %
- Duplicate Row Filter< 1 %
- Nominal Value Row Splitter< 1 %
- RowID< 1 %
- Numeric Row Splitter< 1 %
- Rule Engine< 1 %
Excel Reader (XLS)< 1 %- Porter Stemmer< 1 %
- Stop Word Filter< 1 %
- Tag Filter< 1 %
- Tika Parser< 1 %
- Word Parser< 1 %
RSS Feed Reader< 1 %- Bag Of Words Creator< 1 %
- Parameter Optimization Loop Start< 1 %
Twitter Streaming (legacy)< 1 %- Twitter Timeline (legacy)< 1 %
- Remove Empty Rows< 1 %
- Text Classifier Model to Table< 1 %
- Corpus Creator< 1 %
- IDF< 1 %
- Case Converter< 1 %
- JSON to XML< 1 %
- Python Script (legacy)< 1 %
- Web Page Content Extractor< 1 %
Views
- This node has no views
Workflows
- No workflows found
Links
- How to increase my acc scoreby qqilihq on 2022-04-18forum.knime.com/p/154154
- Text classification starting from excelby qqilihq on 2020-05-06forum.knime.com/p/90251
- Find the count of predicted categories.by armingrudd on 2019-08-26forum.knime.com/p/68711
Developers
You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.