Timezone: »

 
Attribute Controlled Dialogue Prompting
Runcheng Liu · Ahmad Rashid · Ivan Kobyzev · Mehdi Rezaghoizadeh · Pascal Poupart

Fri Dec 02 07:45 AM -- 07:56 AM (PST) @
in Second Workshop on Efficient Natural Language and Speech Processing (ENLSP-II) »

Prompt-tuning has become an increasingly popular parameter-efficient method for steering large pretrained language models to downstream tasks. However, both discrete prompting and continuous prompting assume fixed prompts for all data samples within a task, neglecting the fact that inputs vary greatly in some tasks such as open-domain dialogue generation. In this paper, we present a novel, instance-specific prompt-tuning algorithm for dialogue generation. Specifically, we generate prompts based on instance-level control code, rather than the conversation history, to explore their impact on controlled dialogue generation. Experiments on popular open-domain dialogue datasets, evaluated on both automated metrics and human evaluation, demonstrate that our method is superior to prompting baselines and comparable to fine-tuning with only 5%-6% of total parameters.

Keywords: ENLSP-Main
[ Poster] 

Author Information

Runcheng Liu (University of Waterloo)
Ahmad Rashid (Huawei Technologies)
Ivan Kobyzev (Huawei)
Mehdi Rezaghoizadeh (Huawei Technologies)
Pascal Poupart (University of Waterloo & Vector Institute)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors