Learning Label-Relational Output Structure for Adaptive Sequence Labeling

摘要

Sequence labeling is a fundamental task of natural language understanding. Recent neural models for sequence labeling task achieve significant success with the availability of sufficient training data. However, in practical scenarios, entity types to be annotated even in the same domain are continuously evolving. To transfer knowledge from the source model pre-trained on previously annotated data, we propose an approach which learns label-relational output structure to explicitly capturing label correlations in the latent space. Additionally, we construct the target-to-source interaction between the source model M S and the target model M T and apply a gate mechanism to control how much information in M S and M T should be passed down. Experiments show that our method consistently outperforms the state-of-the-art methods with a statistically significant margin and effectively facilitates to recognize rare new entities in the target data especially.

会议
IJCNN 2020
何可清
硕士研究生

对话系统,摘要,预训练

严渊蒙
严渊蒙
硕士研究生

自然语言理解,预训练

徐红
硕士研究生

自然语言处理,意图识别

刘思宏
硕士研究生

对话系统,策略学习

刘子君
刘子君
硕士研究生

任务导向型对话系统

徐蔚然
徐蔚然
副教授,硕士生导师,博士生导师

信息检索,模式识别,机器学习