文章基本信息

标题：On the Hidden Negative Transfer in Sequential Transfer Learning for Domain Adaptation from News to Tweets
本地全文：下载
作者：Sara Meftah ; Nasredine Semmar ; Youssef Tamaazousti 等
期刊名称：Conference on European Chapter of the Association for Computational Linguistics (EACL)
出版年度：2021
卷号：2021
页码：140-145
语种：English
出版社：ACL Anthology
摘要：Transfer Learning has been shown to be a powerful tool for Natural Language Processing (NLP) and has outperformed the standard supervised learning paradigm, as it takes benefit from the pre-learned knowledge. Nevertheless, when transfer is performed between less related domains, it brings a negative transfer, i.e. hurts the transfer performance. In this research, we shed light on the hidden negative transfer occurring when transferring from the News domain to the Tweets domain, through quantitative and qualitative analysis. Our experiments on three NLP taks: Part-Of-Speech tagging, Chunking and Named Entity recognition, reveal interesting insights.