Slot Transferability for Cross-domain Slot Filling

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 4970–4979 August 1–6, 2021. ©2021 Association for Computational Linguistics 4970 Slot Transferability for Cross-domain Slot Filling 1Hengtong Lu, 1Zhuoxin Han, 1Caixia Yuan, 1Xiaojie Wang, 2Shuyu Lei, 2Huixing Jiang, 2Wei wu 1Beijing University of Posts and Telecommunications, Beijing, China 2Meituan-Dianping Group, Beijing, China {luhengtong, hanzhuoxin, yuancx, xjwang}@bupt.edu.cn {leishuyu, jianghuixing, wuwei30}@meituan.com Abstract Cross-domain slot filling focuses on using la- beled data from source domains to train a slot filling model for target domains. It is of great significance for transferring a dialogue system into new domains. Most of the existing work focused on building a cross-domain transfer model. From the perspective of slots them- selves, this paper proposes a model-agnostic Slot Transferability Measure (STM) for evalu- ating the transferability from a source slot to a target slot, specifically, the degree that labeled data of the source slot is helpful to train the slot filling model for the target slot. We also give a STM-based method for a model to select helpful source slots and their labeled data for a given target slot. Experimental results on mul- tiple existing models and datasets show that our method significantly outperforms state-of- the-art baselines in cross-domain slot filling. The code is available at https://github. com/luhengtong/STM-for-cdsf.git. 1 Introduction As an important task in task-oriented dialog sys- tems, slot filling aims to identify task-related slot information in user utterances. When a task (or domain) has a large amount of labeled data, most existing slot filling models can achieve desired per- formance. However, there is usually little or even no labeled data for a new task. How to train the slot filling model in the new task (target task) with the labeled data of one or more existing tasks (source tasks) is of great significance for the rapid expan- sion of the application of task-oriented dialog sys- tems. Existing work can be mainly classified into two categories. The first is to establish implicit seman- tic alignment between slot representations of the source task and the target task, the model trained with the source task data is directly used for the target task (Bapna et al., 2017; Lee and Jha, 2019; Shah et al., 2019). The second is to use a two- stage strategy (Liu et al., 2020), which treats all slot values as entities. First, it trains a generic entity recognition model using source task labeled data to identify all candidate slot values in the target task. Then, the candidate slot value is classified into the target task slot by comparing the similarity between its representation and the target task slot information. Most of the existing work has focused on build- ing cross-task transferable models that leverage the association information between source tasks and target tasks, and the model is always trained using the labeled data of all the source tasks with- out distinction. However, not all the source task data will have transferable value to the target task, and the value of different source tasks data to a …

Content truncated to 500 words