TY - GEN
T1 - Incremental Few-shot Text Classification with Multi-round New Classes
T2 - 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2021
AU - Xia, Congying
AU - Yin, Wenpeng
AU - Feng, Yihao
AU - Yu, Philip
N1 - Funding Information:
We thank the reviewers for their valuable comments. This work is supported in part by NSF under grants III-1763325, III-1909323, and SaTC-1930941.
Publisher Copyright:
© 2021 Association for Computational Linguistics.
PY - 2021
Y1 - 2021
N2 - Text classification is usually studied by labeling natural language texts with relevant categories from a predefined set. In the real world, new classes might keep challenging the existing system with limited labeled data. The system should be intelligent enough to recognize upcoming new classes with a few examples. In this work, we define a new task in the NLP domain, incremental few-shot text classification, where the system incrementally handles multiple rounds of new classes. For each round, there is a batch of new classes with a few labeled examples per class. Two major challenges exist in this new task: (i) For the learning process, the system should incrementally learn new classes round by round without re-training on the examples of preceding classes; (ii) For the performance, the system should perform well on new classes without much loss on preceding classes. In addition to formulating the new task, we also release two benchmark datasets 1 in the incremental few-shot setting: intent classification and relation classification. Moreover, we propose two entailment approaches, ENTAILMENT and HYBRID, which show promise for solving this novel problem.
AB - Text classification is usually studied by labeling natural language texts with relevant categories from a predefined set. In the real world, new classes might keep challenging the existing system with limited labeled data. The system should be intelligent enough to recognize upcoming new classes with a few examples. In this work, we define a new task in the NLP domain, incremental few-shot text classification, where the system incrementally handles multiple rounds of new classes. For each round, there is a batch of new classes with a few labeled examples per class. Two major challenges exist in this new task: (i) For the learning process, the system should incrementally learn new classes round by round without re-training on the examples of preceding classes; (ii) For the performance, the system should perform well on new classes without much loss on preceding classes. In addition to formulating the new task, we also release two benchmark datasets 1 in the incremental few-shot setting: intent classification and relation classification. Moreover, we propose two entailment approaches, ENTAILMENT and HYBRID, which show promise for solving this novel problem.
UR - http://www.scopus.com/inward/record.url?scp=85108857759&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85108857759&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85108857759
T3 - NAACL-HLT 2021 - 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference
SP - 1351
EP - 1360
BT - NAACL-HLT 2021 - 2021 Conference of the North American Chapter of the Association for Computational Linguistics
PB - Association for Computational Linguistics (ACL)
Y2 - 6 June 2021 through 11 June 2021
ER -