A Pattern and POS Auto-Learning Method for Terminology Extraction from Scientific Text

Abstract

A lot of new scientific documents are being published on various platforms every day. It is more and more imperative to quickly and efficiently discover new words and meanings from these documents. However, most of the related works rely on labeled data, and it is quite difficult to deal with unlabeled new documents efficiently. For this, we have introduced an unsupervised method based on sentence patterns and part of speech (POS) sequences. Our method just needs a few initial learnable patterns to obtain the initial terminology tokens and their POS sequences. In this process, new patterns are constructed and can match more sentences to find more POS sequences of terminology. Finally, we use obtained POS sequences and sentence patterns to extract terminology terms in new scientific text. Experiments on paper abstracts from Web of Knowledge show that this method is practical and can achieve a good performance on our test data.

Application of neural network language models based on distributive semantics for ontological modeling of the domain

“…The creation of methods for extracting terms using unsupervised learning models is one of the topical contemporary issues. For example, in [19] the authors propose unsupervised technology for extracting concepts, while considering the context of using the concept in terms of parts of speech (POS), which makes it possible to make a model that is universal for different subject areas.…”

Chinese technical terminology extraction based on DC-value and information entropy

“…to match in the corpus and output multicharacter units that meet the established rules as terms. The common term extraction models mainly focus on language features 8 , 9 , syntactic patterns 10 – 12 , and retrieval strategies 13 . The advantages of the method include being concise, intuitive, and having a strong expressive ability.…”

Knowledge Entity Extraction and Text Mining in the Era of Big Data

“…The paper "A Pattern and POS Auto-Learning Method for Terminology Extraction from Scientific Text" (Shao, Hua, & Song, 2021) proposed an unsupervised method based on sentence patterns and part of speech (POS) sequences extracted from scientific texts. The proposed method only requires a few initial learnable patterns to obtain initial terminological tokens and their POS sequences.…”