Causal-aware Safe Policy Improvement for Task-oriented dialogue

Ramachandran, Govardana Sachithanandam; Hashimoto, Kazuma; Xiong, Caiming

doi:10.48550/arxiv.2103.06370

Cited by 1 publication

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sequicity [22] is an example of Seq2Seq-based models applied to dialogue systems; DAMD [23] extended a single-domain dialogue system to multiple domains; LABES-S2S [24] attempted semi-supervised learning. Third, several studies have explored the application of reinforcement learning in dialogue systems, including models such as JOUST [25], LAVA [26], DORA [27], SUMBT+LaRL [28], and CASPI [29]. With the advent of pre-trained language models, models such as DoTS [30] used Bidirectional Encoder Representations from Transformers (BERT) and Gated Recurrent Unit (GRU) for dialogue state tracking.…”

Section: Task-oriented Dialogue Systemmentioning

confidence: 99%

Parameter-Efficient Fine-Tuning Method for Task-Oriented Dialogue Systems

Yoo

Kang

2023

Mathematics

View full text Add to dashboard Cite

The use of Transformer-based pre-trained language models has become prevalent in enhancing the performance of task-oriented dialogue systems. These models, which are pre-trained on large text data to grasp the language syntax and semantics, fine-tune the entire parameter set according to a specific task. However, as the scale of the pre-trained language model increases, several challenges arise during the fine-tuning process. For example, the training time escalates as the model scale grows, since the complete parameter set needs to be trained. Furthermore, additional storage space is required to accommodate the larger model size. To address these challenges, we propose a new new task-oriented dialogue system called PEFTTOD. Our proposal leverages a method called the Parameter-Efficient Fine-Tuning method (PEFT), which incorporates an Adapter Layer and prefix tuning into the pre-trained language model. It significantly reduces the overall parameter count used during training and efficiently transfers the dialogue knowledge. We evaluated the performance of PEFTTOD on the Multi-WOZ 2.0 dataset, a benchmark dataset commonly used in task-oriented dialogue systems. Compared to the traditional method, PEFTTOD utilizes only about 4% of the parameters for training, resulting in a 4% improvement in the combined score compared to the existing T5-based baseline. Moreover, PEFTTOD achieved an efficiency gain by reducing the training time by 20% and saving up to 95% of the required storage space.

show abstract