scholarly journals Adapted TextRank for Term Extraction: A Generic Method of Improving Automatic Term Extraction Algorithms

2018 ◽  
Vol 137 ◽  
pp. 102-108 ◽  
Author(s):  
Ziqi Zhang ◽  
Johann Petrak ◽  
Diana Maynard
Keyword(s):  
Term Extraction ◽  
Automatic Term Extraction

Term extraction and management based on event templates

Terminology ◽  
2014 ◽  
Vol 20 (2) ◽  
pp. 151-170 ◽  
Author(s):  
Katia Peruzzo
Keyword(s):  
European Union ◽  
Knowledge Base ◽  
Legal System ◽  
Classification Criteria ◽  
The European Union ◽  
Additional Information ◽  
Term Extraction ◽  
Automatic Term Extraction ◽  
Multi Level ◽  
Victims Of Crime

The paper examines the possible usage of event templates derived from Frame-Based Terminology (Faber et al. 2005, 2006, 2007) as an aid to the extraction and management of legal terminology embedded in the multi-level legal system of the European Union. The method proposed here, which combines semi-automatic term extraction and a simplified event template containing six categories, is applied to an English corpus of EU texts focusing on victims of crime and their rights. Such a combination allows for the extraction of category-relevant terminological units and additional information, which can then be used for populating a terminological knowledge base organised on the basis of the same event template, but which also employs additional classification criteria to account for the multidimensionality encountered in the corpus.

Tagging terms in text

Terminology ◽  
2022 ◽  
Author(s):  
Ayla Rigouts Terryn ◽  
Véronique Hoste ◽  
Els Lefever
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Language Processing ◽  
Conditional Random Fields ◽  
Traditional Approach ◽  
Learning Approaches ◽  
Term Extraction ◽  
The Neural Network ◽  
Predicted Probability ◽  
Automatic Term Extraction

Abstract As with many tasks in natural language processing, automatic term extraction (ATE) is increasingly approached as a machine learning problem. So far, most machine learning approaches to ATE broadly follow the traditional hybrid methodology, by first extracting a list of unique candidate terms, and classifying these candidates based on the predicted probability that they are valid terms. However, with the rise of neural networks and word embeddings, the next development in ATE might be towards sequential approaches, i.e., classifying each occurrence of each token within its original context. To test the validity of such approaches for ATE, two sequential methodologies were developed, evaluated, and compared: one feature-based conditional random fields classifier and one embedding-based recurrent neural network. An additional comparison was added with a machine learning interpretation of the traditional approach. All systems were trained and evaluated on identical data in multiple languages and domains to identify their respective strengths and weaknesses. The sequential methodologies were proven to be valid approaches to ATE, and the neural network even outperformed the more traditional approach. Interestingly, a combination of multiple approaches can outperform all of them separately, showing new ways to push the state-of-the-art in ATE.

Sign in / Sign up

Export Citation Format

Share Document