Affiliation:
1. Carleton University, Canada
2. University of Ottawa, Canada
3. Western University, Canada
Abstract
Abstract
The present article explores two novel methods that integrate distributed representations with terminology extraction. Both methods assess the specificity of a word (unigram) to the target corpus by leveraging its distributed representation in the target domain as well as in the general domain. The first approach adopts this distributed specificity as a filter, and the second directly applies it to the corpus. The filter can be mounted on any other Automatic Terminology Extraction (ATE) method, allows merging any number of other ATE methods, and achieves remarkable results with minimal training. The direct approach does not perform as high as the filtering approach, but it reemphasizes that using distributed specificity as the words’ representation, very little data is required to train an ATE classifier. This encourages more minimally supervised ATE algorithms in the future.
Publisher
John Benjamins Publishing Company
Subject
Library and Information Sciences,Communication,Language and Linguistics
Reference37 articles.
1. Enriching Word Vectors with Subword Information
2. Terminology Extraction Approaches for Product Aspect Detection in Customer Reviews;Broß,2013
3. Automatic term detection
4. Automatic term detection
Cited by
35 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Computational Terminology;New Frontiers in Translation Studies;2024
2. CoastTerm: A Corpus for Multidisciplinary Term Extraction in Coastal Scientific Literature;Lecture Notes in Computer Science;2024
3. SessNet: A Deep Hybrid-state Session-based Recommender System;2022 IEEE 13th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON);2022-10-12
4. Context-Aware Attended-over Distributed Specificity for Information Extraction in Cybersecurity;2022 IEEE 13th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON);2022-10-12
5. NMF-based approach to automatic term extraction;Expert Systems with Applications;2022-08