Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics Volume 1: Long Papers, pages 401 - 415 May 22-27, 2022 c⃝2022 Association for Computational Linguistics Mix and Match: Learning-free Controllable Text Generation using Energy Language Models Fatemehsadat Mireshghallah1, Kartik Goyal2, Taylor Berg-Kirkpatrick1 1 University of California San Diego, 2 Toyota Technological Institute at Chicago (TTIC) [fatemeh, tberg]@ucsd.edu, kartikgo@ttic.edu Abstract Recent work on controlled text generation has either required attribute-based fine-tuning of the base language model (LM), or has restricted the parameterization of the attribute discriminator to be compatible with the base autoregressive LM. In this work, we propose Mix and Match LM, a global score-based alternative for con- trollable text generation that combines arbitrary pre-trained black-box models for achieving the desired attributes in the generated text without involving any fine-tuning or structural assump- tions about the black-box models. We interpret the task of controllable generation as drawing samples from an energy-based model whose energy values are a linear combination of scores from black-box models that are separately responsible for fluency, the control attribute, and faithfulness to any conditioning context. We use a Metropolis-Hastings sampling scheme to sample from this energy-based model using bidirectional context and global attribute features. We validate the effectiveness of our approach on various controlled generation and style-based text revision tasks by outperforming recently proposed methods that involve extra training, fine-tuning, or restrictive assumptions over the form of models. 1 Introduction While large transformer-based autoregressive lan- guage models trained on massive amounts of data foundontheinternetexhibitexceptionalcapabilities to generate natural language text, effective methods for generating text that satisfy global constraints and possess holistic desired attributes remains an active area of research. These mechanisms for con- trolling the generation of language have the poten- tial to mitigate undesirable biases encoded by the large language models and prevent the generation of hate speech and toxic language (Xu et al.; Gehman et al., 2020; Sap et al., 2021; Baheti et al., 2021; Mireshghallah and Berg-Kirkpatrick, 2021). Much of the prior work has approached controlled gener- ation via either training domain-conditioned neu- ral language models (Prabhumoye et al., 2020; He et al., 2020; Lample et al., 2018; Shen et al., 2017; Krishna et al., 2020; Reif et al., 2021; Ficler and Goldberg, 2017; Khalifa et al., 2021) or finetun- ing/modifying an underlying large pre-trained base model for generation on domain-specific data for attribute sensitive generation (Ziegler et al., 2019; Keskar et al., 2019; Mai et al., 2020; Gururangan et al., 2020; Chronopoulou et al., 2021). Not only do these approaches involve computational overhead and estimation errors associated with the training of language models, but they are also dependent on ac- cess to a large amount of attribute-specific language data which can be impractical in many scenarios and exacerbate privacy concerns (Brown et al., 2022; Mireshghallah et al., 2021; Kandpal et al., 2022). Our approach eschews training and focuses on generation-time control from pre-trained modules. Recent work in this space has used attribute discriminators (Dathathri et al., 2020; Krause et …

Content truncated to 500 words