The task of choosing the correct sense for a word is called word sense disambiguation (WSD). WSD algorithms take an input word w in its context with a fixed set of potential word senses Sw of that input word and produce an output chosen from Sw. In the isolated WSD task, one usually uses the set of senses from a dictionary or theasurus like WordNet.
In the literature, there are actually two variants of the generic WSD task. In the lexical sample task, a small selected set of target words is chosen, along with a set of senses for each target word. For each target word w, a number of corpus sentences (context sentences) are manually labeled with the correct sense of w. In all-words task, systems are given entire sentences and a lexicon with the set of senses for each word in each sentence. Annotators are then asked to disambiguate every word in the text.
In all-words WSD, a classifier is trained to label the words in the text with their set of potential word senses. After giving the sense labels to the words in our training data, the next step is to select a group of features to discriminate different senses for each input word.
The following Table shows an example for the word 'yüz', which can refer to the number '100', to the verb 'swim' or to the noun 'face'.
| Sense | Definition |
|---|---|
| yüz1 (hundred) | The number coming after ninety nine |
| yüz2 (swim) | move or float in water |
| yüz3 (face) | face, visage, countenance |
- Collect a set of sentences to annotate.
- Each sentence in the collection must be named as xxxx.yyyyy in increasing order. For example, the first sentence to be annotated will be 0001.train, the second 0002.train, etc.
- Put the sentences in the same folder such as Turkish-Phrase.
- Build the Java project and put the generated sentence-semantics.jar file into another folder such as Program.
- Put Turkish-Phrase and Program folders into a parent folder.
- Open sentence-semantics.jar file.
- Wait until the data load message is displayed.
- Click Open button in the Project menu.
- Choose a file for annotation from the folder Turkish-Phrase.
- For each word in the sentence, click the word, and choose correct sense for that word.
- Click one of the next buttons to go to other files.
After annotating sentences, you can use DataGenerator package to generate classification dataset for the Word Sense Disambiguation task.
After generating the classification dataset as above, one can use the Classification package to generate machine learning models for the Word Sense Disambiguation task.
You can also see Cython, Java, C++, Swift, Js, or C# repository.
To check if you have a compatible version of Python installed, use the following command:
python -V
You can find the latest version of Python here.
pip3 install NlpToolkit-WordSenseDisambiguation
Install the latest version of Git.
In order to work on code, create a fork from GitHub page. Use Git for cloning the code to your local or below line for Ubuntu:
git clone <your-fork-git-link>
A directory called Corpus will be created. Or you can use below link for exploring the code:
git clone https://github.com/olcaytaner/WordSenseDisambiguation-Py.git
Steps for opening the cloned project:
- Start IDE
- Select File | Open from main menu
- Choose
WordSenseDisambiguation-Pyfile - Select open as project option
- Couple of seconds, dependencies will be downloaded.
In order to sense annotate a parse tree, one can use autoSemantic method of the TurkishTreeAutoSemantic class.
parseTree = ...
wordNet = WordNet()
fsm = FsmMorphologicalAnalyzer()
turkishAutoSemantic = TurkishTreeAutoSemantic(wordnet, fsm)
turkishAutoSemantic.autoSemantic()
In order to sense annotate a parse tree, one can use autoSemantic method of the TurkishSentenceAutoSemantic class.
sentence = ...
wordNet = WordNet()
fsm = FsmMorphologicalAnalyzer()
turkishAutoSemantic = TurkishSentenceAutoSemantic(wordnet, fsm)
turkishAutoSemantic.autoSemantic()
@INPROCEEDINGS{8093442,
author={O. {Açıkgöz} and A. T. {Gürkan} and B. {Ertopçu} and O. {Topsakal} and B. {Özenç} and A. B. {Kanburoğlu} and İ. {Çam} and B. {Avar} and G. {Ercan} and O. T. {Yıldız}},
booktitle={2017 International Conference on Computer Science and Engineering (UBMK)},
title={All-words word sense disambiguation for Turkish},
year={2017},
volume={},
number={},
pages={490-495},
doi={10.1109/UBMK.2017.8093442}}
- Do not forget to set package list. All subfolders should be added to the package list.
packages=['Classification', 'Classification.Model', 'Classification.Model.DecisionTree',
'Classification.Model.Ensemble', 'Classification.Model.NeuralNetwork',
'Classification.Model.NonParametric', 'Classification.Model.Parametric',
'Classification.Filter', 'Classification.DataSet', 'Classification.Instance', 'Classification.Attribute',
'Classification.Parameter', 'Classification.Experiment',
'Classification.Performance', 'Classification.InstanceList', 'Classification.DistanceMetric',
'Classification.StatisticalTest', 'Classification.FeatureSelection'],
- Package name should be lowercase and only may include _ character.
name='nlptoolkit_math',
- Do not forget to comment each function.
def __broadcast_shape(self, shape1: Tuple[int, ...], shape2: Tuple[int, ...]) -> Tuple[int, ...]:
"""
Determines the broadcasted shape of two tensors.
:param shape1: Tuple representing the first tensor shape.
:param shape2: Tuple representing the second tensor shape.
:return: Tuple representing the broadcasted shape.
"""
- Function names should follow caml case.
def addItem(self, item: str):
- Local variables should follow snake case.
det = 1.0
copy_of_matrix = copy.deepcopy(self)
- Class variables should be declared in each file.
class Eigenvector(Vector):
eigenvalue: float
- Variable types should be defined for function parameters and class variables.
def getIndex(self, item: str) -> int:
- For abstract methods, use ABC package and declare them with @abstractmethod.
@abstractmethod
def train(self, train_set: list[Tensor]):
pass
- For private methods, use __ as prefix in their names.
def __infer_shape(self, data: Union[List, List[List], List[List[List]]]) -> Tuple[int, ...]:
- For private class variables, use __ as prefix in their names.
class Matrix(object):
__row: int
__col: int
__values: list[list[float]]
- Write __repr__ class methods as toString methods
- Write getter and setter class methods.
def getOptimizer(self) -> Optimizer:
return self.optimizer
def setValue(self, value: Optional[Tensor]) -> None:
self._value = value
- If there are multiple constructors for a class, define them as constructor1, constructor2, ..., then from the original constructor call these methods.
def constructor1(self):
self.__values = []
self.__size = 0
def constructor2(self, values: list):
self.__values = values.copy()
self.__size = len(values)
def __init__(self,
valuesOrSize=None,
initial=None):
if valuesOrSize is None:
self.constructor1()
elif isinstance(valuesOrSize, list):
self.constructor2(valuesOrSize)
- Extend test classes from unittest and use separate unit test methods.
class TensorTest(unittest.TestCase):
def test_inferred_shape(self):
a = Tensor([[1.0, 2.0], [3.0, 4.0]])
self.assertEqual((2, 2), a.getShape())
def test_shape(self):
a = Tensor([1.0, 2.0, 3.0])
self.assertEqual((3, ), a.getShape())
- Enumerated types should be used when necessary as enum classes.
class AttributeType(Enum):
"""
Continuous Attribute
"""
CONTINUOUS = auto()
"""
Discrete Attribute
"""
DISCRETE = auto()