Task-oriented Domain-specific Meta-Embedding for Text Classification

2020-11-01 · EMNLP 2020 11 · Xin Wu, Yi Cai, Yang Kai, Tao Wang, Qing Li

Meta-embedding learning, which combines complementary information in different word embeddings, have shown superior performances across different Natural Language Processing tasks. However, domain-specific knowledge is still ignored by existing meta-embedding methods, which results in unstable performances across specific domains. Moreover, the importance of general and domain word embeddings is related to downstream tasks, how to regularize meta-embedding to adapt downstream tasks is an unsolved problem. In this paper, we propose a method to incorporate both domain-specific and task-oriented information into meta-embeddings. We conducted extensive experiments on four text classification datasets and the results show the effectiveness of our proposed method.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Classification General Classification text-classification Text ClassificationWord Embeddings

Transfer-Meta Framework for Cross-domain Recommendation to Cold-Start Users

2021-05-11 · Yongchun Zhu, Kaikai Ge, Fuzhen Zhuang, Ruobing Xie 외

Cold-start problems are enormous challenges in practical recommender systems. One promising solution for this problem is cross-domain recommendation (CDR) which leverages rich information from an auxiliary (source) domai…

Meta-Learning Recommendation Systems

Personalized Transfer of User Preferences for Cross-domain Recommendation

2021-10-21 · Yongchun Zhu, Zhenwei Tang, Yudan Liu, Fuzhen Zhuang 외

Cold-start problem is still a very challenging problem in recommender systems. Fortunately, the interactions of the cold-start users in the auxiliary source domain can help cold-start recommendations in the target domain…

Recommendation Systems

metaCAT: A Metadata-based Task-oriented Chatbot Annotation Tool

2020-12-01 · Asian Chapter of the Association for Computational Linguistics 2020 · Ximing Liu, Wei Xue, Qi Su, Weiran Nie 외

Creating high-quality annotated dialogue corpora is challenging. It is essential to develop practical annotation tools to support humans in this time-consuming and error-prone task. We present metaCAT, which is an open-s…

Automatic Speech Recognition Automatic Speech Recognition (ASR)Chatbot speech-recognition+1

Lifelong Domain Word Embedding via Meta-Learning

2018-05-25 · Hu Xu, Bing Liu, Lei Shu, Philip S. Yu

Learning high-quality domain word embeddings is important for achieving good performance in many NLP tasks. General-purpose embeddings trained on large-scale corpora are often sub-optimal for domain-specific applications…

Lifelong learning Meta-Learning Word Embeddings

Lifelong Word Embedding via Meta-Learning

2018-01-01 · ICLR 2018 1 · Hu Xu, Bing Liu, Lei Shu, Philip S. Yu

Learning high-quality word embeddings is of significant importance in achieving better performance in many down-stream learning tasks. On one hand, traditional word embeddings are trained on a large scale corpus for gene…