TY - GEN
T1 - Task-oriented domain-specific meta-embedding for text classification
AU - Wu, Xin
AU - Cai, Yi
AU - Li, Qing
AU - Wang, Tao
AU - Yang, Kai
N1 - Funding Information:
This work was supported by the Fundamental Research Funds for the Central Universities, SCUT (No.2017ZD048, D2182480), the Science and Technology Planning Project of Guangdong Province (No.2017B050506004), the Science and Technology Programs of Guangzhou (No.201704030076, 201802010027, 201902010046), National Natural Science Foundation of China (62076100) and the Hong Kong Research Grants Council (project no. C1031-18G).
Publisher Copyright:
© 2020 Association for Computational Linguistics
PY - 2020
Y1 - 2020
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/85118435222
M3 - Conference article published in proceeding or book
AN - SCOPUS:85118435222
T3 - EMNLP 2020 - 2020 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
SP - 3508
EP - 3513
BT - EMNLP 2020 - 2020 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
PB - Association for Computational Linguistics (ACL)
T2 - 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020
Y2 - 16 November 2020 through 20 November 2020
ER -