Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2403.17636 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916179319193600 |
|---|---|
| author | Nie, Yuxiang Huang, Heyan Mao, Xian-Ling Liao, Lizi |
| author_facet | Nie, Yuxiang Huang, Heyan Mao, Xian-Ling Liao, Lizi |
| contents | Mixed initiative serves as one of the key factors in controlling conversation directions. For a speaker, responding passively or leading proactively would result in rather different responses. However, most dialogue systems focus on training a holistic response generation model without any distinction among different initiatives. It leads to the cross-contamination problem, where the model confuses different initiatives and generates inappropriate responses. Moreover, obtaining plenty of human annotations for initiative labels can be expensive. To address this issue, we propose a general mix-Initiative Dynamic Prefix Tuning framework (IDPT) to decouple different initiatives from the generation model, which learns initiative-aware prefixes in both supervised and unsupervised settings. Specifically, IDPT decouples initiative factors into different prefix parameters and uses the attention mechanism to adjust the selection of initiatives in guiding generation dynamically. The prefix parameters can be tuned towards accurate initiative prediction as well as mix-initiative response generation. Extensive experiments on two public dialogue datasets show that the proposed IDPT outperforms previous baselines on both automatic metrics and human evaluations. It also manages to generate appropriate responses with manipulated initiatives. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_17636 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Mix-Initiative Response Generation with Dynamic Prefix Tuning Nie, Yuxiang Huang, Heyan Mao, Xian-Ling Liao, Lizi Computation and Language Mixed initiative serves as one of the key factors in controlling conversation directions. For a speaker, responding passively or leading proactively would result in rather different responses. However, most dialogue systems focus on training a holistic response generation model without any distinction among different initiatives. It leads to the cross-contamination problem, where the model confuses different initiatives and generates inappropriate responses. Moreover, obtaining plenty of human annotations for initiative labels can be expensive. To address this issue, we propose a general mix-Initiative Dynamic Prefix Tuning framework (IDPT) to decouple different initiatives from the generation model, which learns initiative-aware prefixes in both supervised and unsupervised settings. Specifically, IDPT decouples initiative factors into different prefix parameters and uses the attention mechanism to adjust the selection of initiatives in guiding generation dynamically. The prefix parameters can be tuned towards accurate initiative prediction as well as mix-initiative response generation. Extensive experiments on two public dialogue datasets show that the proposed IDPT outperforms previous baselines on both automatic metrics and human evaluations. It also manages to generate appropriate responses with manipulated initiatives. |
| title | Mix-Initiative Response Generation with Dynamic Prefix Tuning |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2403.17636 |