GenTUS: Simulating User Behaviour and Language in Task-oriented Dialogues with Generative Transformers

Abstract

User simulators (USs) are commonly used to train task-oriented dialogue systems (DSs) via reinforcement learning. The interactions often take place on semantic level for efficiency, but there is still a gap from semantic actions to natural language, which causes a mismatch between training and deployment environment. Incorporating a natural language generation (NLG) module with USs during training can partly deal with this problem. However, since the policy and NLG of USs are optimised separately, these simulated user utterances may not be natural enough in a given context. In this work, we propose a generative transformerbased user simulator (GenTUS). GenTUS consists of an encoder-decoder structure, which means it can optimise both the user policy and natural language generation jointly. GenTUS generates both semantic actions and natural language utterances, preserving interpretability and enhancing language variation. In addition, by representing the inputs and outputs as word sequences and by using a large pre-trained language model we can achieve generalisability in feature representation. We evaluate Gen-TUS with automatic metrics and human evaluation. Our results show that GenTUS generates more natural language and is able to transfer to an unseen ontology in a zero-shot fashion. In addition, its behaviour can be further shaped with reinforcement learning opening the door to training specialised user simulators.

ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Format

“…These scripts include commonly used metrics such as: turn accuracy (ACC) and dialogue act F1 score for natural language understanding (NLU) (Zhu et al, 2020b), joint goal accuracy (JGA) and slot F1 score for dialogue state tracking (DST) , BLEU and slot error rate (SER) for natural language generation (NLG) (Wen et al, 2015), BLEU and Combined score (Comb.) for End2End dialogue modeeling (Mehri et al, 2019), turn accuracy, slot-value F1 score and SER for user simulators (Lin et al, 2021a(Lin et al, , 2022.…”

“…Besides existing models in ConvLab-2 (Zhu et al, 2020b), we integrate new transformer-based models supporting the unified data format, including SetSUMBT (van Niekerk et al, 2021) andTripPy (Heck et al, 2020) for dialogue state tracking (DST), DDPT (Geishauser et al, 2022) and LAVA (Lubis et al, 2020) for policy learning, SC-GPT for natural language generation (NLG), and SOLOIST with T5 as backbone model (Peng et al, 2022) for end-to-end modeling (End2End). We also integrate multiple powerful data-driven user simulators (US): TUS (Lin et al, 2021a) that outputs user dialogue acts, GenTUS (Lin et al, 2022) that outputs both user dialogue acts and response, and EmoUS (Lin et al, 2023) that additionally outputs emotions.…”

“…The vast amount of possible user behaviours and tasks that a TOD system might assist with necessitates the study of generalization and transfer towards new users and datasets. While many datasets for studying task-oriented dialogue have been proposed (Wen et al, 2016;Byrne et al, 2019;Eric et al, 2020;Rastogi et al, 2020;Zhu et al, 2020a;Feng et al, 2022), the various dialogue, ontology and database formats hinder researchers from validating their models on unseen data. In this work we propose a unified format to bridge the gap between different TOD datasets and models and provide a unified training and evaluation framework that accelerates the study of generalization capabilities.…”