@article{Hazarika_Namazifar_Hakkani-Tür_2022, title={Attention Biasing and Context Augmentation for Zero-Shot Control of Encoder-Decoder Transformers for Natural Language Generation}, volume={36}, url={https://ojs.aaai.org/index.php/AAAI/article/view/21319}, DOI={10.1609/aaai.v36i10.21319}, abstractNote={Controlling neural network-based models for natural language generation (NLG) to realize desirable attributes in the generated outputs has broad applications in numerous areas such as machine translation, document summarization, and dialog systems. Approaches that enable such control in a zero-shot manner would be of great importance as, among other reasons, they remove the need for additional annotated data and training. In this work, we propose novel approaches for controlling encoder-decoder transformer-based NLG models in zero shot. While zero-shot control has previously been observed in massive models (e.g., GPT3), our method enables such control for smaller models. This is done by applying two control knobs, attention biasing and context augmentation, to these models directly during decoding and without additional training or auxiliary models. These knobs control the generation process by directly manipulating trained NLG models (e.g., biasing cross-attention layers). We show that not only are these NLG models robust to such manipulations but also their behavior could be controlled without an impact on their generation performance.}, number={10}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Hazarika, Devamanyu and Namazifar, Mahdi and Hakkani-Tür, Dilek}, year={2022}, month={Jun.}, pages={10738-10748} }