{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/sidecontrol-controlled-open-domain-dialogue","title":"SideControl: Controlled Open-domain Dialogue Generation via Additive Side Networks","arxiv_id":"2109.01958","date":"2021-09-05","proceeding":"Findings (EMNLP) 2021 11","authors":["Wanyu Du","Yangfeng Ji"],"abstract":"Transformer-based pre-trained language models boost the performance of open-domain dialogue systems. Prior works leverage Transformer-based pre-trained language models to generate texts with desired attributes in two general approaches: (1) gradient-based methods: updating all latent representations of pre-trained models with gradients from attribute models; (2) weighted-decoding methods: re-ranking beam candidates from pre-trained models with attribute functions. However, gradient-based methods lead to high computation cost and can easily get overfitted on small training sets, while weighted-decoding methods are inherently constrained by the low-variance high-bias pre-trained model. In this work, we propose a novel approach to control the generation of Transformer-based pre-trained language models: the SideControl framework, which leverages a novel control attributes loss to incorporate useful control signals, and is shown to perform well with very limited training samples. We evaluate our proposed method on two benchmark open-domain dialogue datasets, and results show that the SideControl framework has better controllability, higher generation quality and better sample-efficiency than existing gradient-based and weighted-decoding baselines.","url_abs":"https://arxiv.org/abs/2109.01958v1","url_pdf":"https://arxiv.org/pdf/2109.01958v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"sidecontrol-controlled-open-domain-dialogue","repo_url":"https://github.com/wyu-du/controlled-dialogue-generation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"dialogue-generation","task_name":"Dialogue Generation"},{"task_slug":"re-ranking","task_name":"Re-Ranking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2109.01958","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}